@sabaiway/agent-workflow-kit 10.2.0 → 10.4.0

package/CHANGELOG.md

@@ -4,6 +4,78 @@ Semantically versioned ([semver](https://semver.org)), newest first. The `versio
 is the current release. `upgrade` mode reads a project's `docs/ai/.workflow-version` and applies
 every `migrations/<version>-<slug>.md` newer than it, in semver order.
 
+## 10.4.0 — who does what is a project setting, and a subagent is a first-class carrier of every kind of work (AD-124)
+
+The rule "design, then hand execution to a frontier subagent" lived in an agent's memory and in a
+prose bullet of one project's `agent_rules.md`. It is now a VALUE in `docs/ai/orchestration.json`,
+resolved and rendered by the surfaces that already resolve and render every recipe.
+
+**One registry** (`tools/carriers.mjs`, contract `docs/ai/specs/kit/carriers.md`, re-exported by
+`recipes.mjs` so no importer moves): three activities — `plan-authoring` (`author`, `review`),
+`plan-execution` (`execute`, `review`) and the new `routine` (`carrier`, `parallel`); the fifth recipe
+`subagent` (a full-tool frontier subagent carries a bounded, file-disjoint slice; the orchestrator
+verifies it and commits); `parallel` is a switch (`on | off`) resolved outside the recipe lattice.
+Computed defaults stay `solo` (placing the vehicle never flips one); the seed config keeps its
+two-activity shape, so an older kit accepts it; `routine` carries no autonomy level of its own.
+
+**The executor vehicle.** `references/agents/executor.md` — model opus, all tools, the dispatch form in
+its prompt, never a git write, the project's own language rules — is the fifth bundled vehicle the
+`agents` writer places beside the four read-only ones. `tools/cheap-agents-read.mjs` (the writer's
+read core, so the read-only advisors never import a writer) surveys it as `placed | customized |
+unusable | missing` through a stated YAML subset; `composeReadiness` surveys the vehicle first and
+hands a bridge-detector failure to `onDetectError`, so neither axis masks the other; a review-role
+computation never counts the executor.
+
+**Every surface speaks the carrier.** `set-recipe` writes every slot (value-neutral diagnostics);
+`procedures` renders the dispatch form per `subagent` slot and the `parallel × carrier` cells;
+`status` shows the resolved carrier per slot and the executor state; the advisor raises ONE
+`attention` item for a configured `subagent` whose vehicle is missing or unusable; the catalog and
+every mode doc name five recipes and three activities. A routine chore is classified first:
+read-only rides a placed read-only vehicle (or is carried solo, stated), write-capable rides the
+executor.
+
+## 10.3.0 — a deployed project is never in an unnamed spec-adoption state, and a skip names a fact the tree can check (AD-123)
+
+A consumer's `upgrade` printed `specs: skipped-no-node — no package.json at the project root` beside
+its own deployed `scripts/check-docs-size.mjs`; the same project's advisor said `no recommendations —
+flow optimal.` over a tree with no `docs/ai/specs/` at all. Both lines were false about the tree they
+described, and nothing in the kit could say so.
+
+**Node is PROVEN, never proxied.** `tools/node-evidence.mjs` (contract `docs/ai/specs/kit/node-evidence.md`)
+answers `package-json` · `deployed-node-scripts` (any kit-seeded `scripts/*.mjs`, the list pinned
+against the bundle) · `none` · `unreadable`. The enforcement-script and spec-layer ensures seed on either
+evidence, skip ONLY on `none` with the new token `skipped-no-node-evidence` — a line naming every probe
+and every wrong-kind path — and fail closed on `unreadable` with the new cause
+`node-evidence-unverifiable`. `skipped-no-node` is retired: a skip whose reason the tool could itself
+disprove may not exist. `upgrade.md` and `deploy-tail.md` add the agent-facing half — a skip line that
+contradicts the observed tree is raised as a finding in the report, never pasted as neutral.
+
+**The adoption state is a surface.** `tools/spec-adoption.mjs` (contract `kit/spec-adoption`) reads the
+store through `spec-check`'s now-exported census and read (`kit/spec-check` rev 2) and answers
+`not-adopted` · `adopting` · `adopted` · `unreadable`. The advisor's 18th probe renders `spec-adoption`:
+the seed on an absent store (apply: the spec-layer ensure one-liner; recipe line: the decline
+preview as a named hand-apply alternative), the decline while a store holds no live contract — both
+OPTIONAL, the frozen registry keeping attention for a broken configured declaration — and a stated
+skip over a store it cannot read;
+so `flow optimal` cannot render over a store nobody observed. `status` prints one `specs` line in every
+state, with ` — declined` once the `spec-adoption` ack lane (`specAdoptionAck`) records the choice, and
+its own `(decline ack unreadable: …)` when that read fails.
+
+**The ack store has one reader.** `tools/ack-store.mjs` (contract `kit/ack-store`) now owns the store
+path, the keys, the closed lane registry, `factFingerprint` and `readAckValue`; the advisor re-exports
+them and `recipeFingerprint` derives through the same leaf. The leaf read moved from a path-based
+`readFile` after `lstat` to the descriptor-bound no-follow door.
+
+Docs: `status.md` documents the line and doc-parity binds the four state tokens into it; the
+`recommendations.md` posture note names both arms and the lane; both `agent_rules.md` templates carry
+the re-rendered Spec-first lens, the zero-state wording in §1.2 and the contradicted-skip bullet in
+§2.5 (`COMMS_PRIORS` gains the outgoing state-block canon so a deployed §2.5 refreshes instead of
+reading as a custom edit). Tarball pin 259 → 262.
+
+Not shipped, with reason: the brief's mechanical refusal of a bare "zero governing specs" once the
+store exists — no plan-shape checker exists and the citation has no literal grammar; queued with its
+entry condition.
+
 ## 10.2.0 — a review can no longer pass a change it called broken (AD-122)
 
 Ships antigravity-cli-bridge **5.4.0** in the bundled bridge tree. A consumer recorded a clean

package/README.md

@@ -231,10 +231,10 @@ file), or run the guarded `/agent-workflow-kit uninstall`.
 | `/agent-workflow-kit backends` | any time | **read-only** check of the optional execution-backends (the `codex` / `agy` bridges): what's set up vs missing and the next step. Never writes, never commits, never runs a subscription CLI (credentials = marker-file presence, not a live login). |
 | `/agent-workflow-kit gates` | any time | **project gate runner** — runs the verification commands **your project itself declares** in `docs/ai/gates.json` (seeded at deploy; hand-editable `{ id, title, cmd }` entries plus the optional boolean `lcovProducer`, each `cmd` one bash line) as one batch: a per-gate **PASS/FAIL table** + one machine-readable summary line, exit 0 iff all green; a failing gate's own output is shown verbatim; `--only <id>` re-runs one. Honest distinct outcomes for a missing / empty / malformed declaration — never a silent green. The runner writes nothing **by default** and never commits — opt-in `--final` runs the FULL declared matrix and mints ONE final-run receipt into the git-dir core-evidence store (status green/red, pre/post tree fingerprints, the declaration, the consumed lcov's sha; the receipt the commit-guard binds); it executes only your own declared commands (a batching convenience, not a sandbox). The velocity tier auto-approves only the exact no-`--final` form — the recording run stays explicit. |
 | `/agent-workflow-kit setup [backend]` | opt-in, any time | **link-only** auto-setup of a bridge: places the bundled bridge skill (only into an absent / empty / managed dir — never overwrites an unmanaged one) + links its wrappers onto `PATH` via managed symlinks (idempotent; refuses to clobber a non-symlink; try `--dry-run` to preview). The binary install + the one-time subscription login stay **manual**: it prints the exact **login** command and points the binary install at each bridge's `setup/README.md`. POSIX wrappers — on Windows use WSL. Never commits, never runs a subscription CLI. |
-| `/agent-workflow-kit status` | any time | **read-only** single view of **versions + deployment + settings + bridges**: which members (kit / memory / engine / the two bridges) are installed and at what version (with an honest "installed on this machine" note when one is behind) and — in a project — what's deployed (`docs/ai`, the version stamps, and the **visibility**: visible / hidden / unclear), plus your settings (orchestration recipes, attribution, velocity) and the bridges' readiness. The two version axes (package number vs deployment-structure head) stay decoupled. Never writes, never commits, never runs a subscription CLI. |
-| `/agent-workflow-kit recipes` | any time | **read-only** orchestration advisor: presents four named recipes for composing the bridges into plan → execute → review — **Solo / Reviewed / Council / Delegated** — plans + recommends one for your environment (degrading with a stated reason when a backend isn't ready), and offers the choice. The orchestrator runs it via the bridge skills and **always commits**; the kit never executes a recipe, never runs a subscription CLI, never commits. |
-| `/agent-workflow-kit procedures <activity>` | any time | **read-only** activity-procedures advisor: prints a named activity's ordered steps (`plan-authoring` / `plan-execution`) read **live** from the engine, plus the **resolved recipe per slot** from your `docs/ai/orchestration.json` (agent-writable via `set-recipe`, or hand-edited) + backend readiness (default Reviewed when a backend is ready, Council on request, slot-aware incl. Delegated) — and, for every dispatched backend, the **full driving contract at the point of use** (exact copy-pasteable invocation, grounding levers like agy's `--facts`/`--decided`, the round-2 `--continue` delta, guarded passthrough), verbatim from the bridge manifests (drift-guarded; each wrapper's `--help` prints the same). `--override <slot>=<recipe>` adjusts one slot per run. Composes with `recipes`; never writes, never commits, never runs a subscription CLI. |
-| `/agent-workflow-kit set-recipe` | any time | **config writer** for `docs/ai/orchestration.json`: tell the agent your preference in plain language and it maps it to explicit `--set <activity>.<slot>=<recipe>` / `--unset` ops; the kit validates, **previews by default**, and writes only on `--write` (deployment-gated, atomic, symlink/TOCTOU-safe), resolving the effective recipe vs live readiness. Writes **only** that file — **never runs a backend, never commits**; hand-editing stays fully supported. |
+| `/agent-workflow-kit status` | any time | **read-only** single view of **versions + deployment + settings + bridges**: which members (kit / memory / engine / the two bridges) are installed and at what version (with an honest "installed on this machine" note when one is behind) and — in a project — what's deployed (`docs/ai`, the version stamps, and the **visibility**: visible / hidden / unclear), and the **feature-spec adoption state** (`not adopted` / `adopting (N draft)` / `adopted (N live, M draft)` / `could not be read`, plus `declined` when recorded), plus your settings (orchestration recipes, attribution, velocity) and the bridges' readiness. The two version axes (package number vs deployment-structure head) stay decoupled. Never writes, never commits, never runs a subscription CLI. |
+| `/agent-workflow-kit recipes` | any time | **read-only** orchestration advisor: presents five named recipes for composing the carriers of a step — the bridges and the full-tool executor subagent — into plan → execute → review — **Solo / Reviewed / Council / Delegated / Subagent** — plans + recommends one for your environment (degrading with a stated reason when a backend isn't ready, or when the executor vehicle is missing/unusable), and offers the choice. The activity/slot registry (three activities) is rendered by `procedures` and by `set-recipe --help`. The orchestrator runs it via the bridge skills or the executor vehicle and **always commits**; the kit never executes a recipe, never runs a subscription CLI, never commits. |
+| `/agent-workflow-kit procedures <activity>` | any time | **read-only** activity-procedures advisor: prints a named activity's ordered steps (`plan-authoring` / `plan-execution` / `routine`) read **live** from the engine, plus the **resolved recipe per slot** from your `docs/ai/orchestration.json` (agent-writable via `set-recipe`, or hand-edited) + carrier readiness (default Reviewed when a backend is ready, Council on request, slot-aware incl. Delegated and Subagent) — and, for every dispatched backend, the **full driving contract at the point of use** (exact copy-pasteable invocation, grounding levers like agy's `--facts`/`--decided`, the round-2 `--continue` delta, guarded passthrough), verbatim from the bridge manifests (drift-guarded; each wrapper's `--help` prints the same). `--override <slot>=<value>` adjusts one slot per run. Composes with `recipes`; never writes, never commits, never runs a subscription CLI. |
+| `/agent-workflow-kit set-recipe` | any time | **config writer** for `docs/ai/orchestration.json`: tell the agent your preference in plain language and it maps it to explicit `--set <activity>.<slot>=<value>` / `--unset` ops; the kit validates, **previews by default**, and writes only on `--write` (deployment-gated, atomic, symlink/TOCTOU-safe), resolving the effective recipe vs live readiness. Writes **only** that file — **never runs a backend or a subagent, never commits**; hand-editing stays fully supported. |
 | `/agent-workflow-kit review-state` | any time | **read-only review-receipt checker** — makes "reviewed ≠ shipped" detectable: the bridge review wrappers append a receipt per successful review (into a file inside the git dir — never committable); this checks that every backend your configured `plan-execution.review` recipe names holds a **fresh, grounded receipt for the current uncommitted tree** (any later edit moves the fingerprint and stales the receipt; a review continuation never re-attests a folded tree). `--check` gives a gate exit code to declare in `docs/ai/gates.json` **by hand or via the consent-gated seeder** (preview → your explicit yes; never without consent). `--await [--timeout <s>]` (AD-049) BLOCKS until every recipe-named backend has receipted the current tree — the durable completion signal is the receipt, never a process event — so you wait for the bridges instead of hand-polling. Never writes, never commits, never runs a subscription CLI; it spawns read-only `git` queries to fingerprint the tree — and `git commit --no-verify` stays possible (discipline, not a sandbox). |
 | `/agent-workflow-kit sandbox-masks` | any time | **cosmetic exclude lane for sandbox device masks** — an OS sandbox (Claude Code) injects character-device masks into the work tree as untracked `git status` noise; the review domain already ignores them **by construction** (never-committable untracked classes — char/block devices, FIFOs, sockets — are excluded from the fingerprint, the assembled review payload, and the clean checks). This mode hides them from `git status` too: flagless = read-only probe (derives the CURRENT mask set from the unfiltered walk + lstat — never a frozen list — and revalidates fenced entries, loudly flagging one that became a real path); `--apply` = consent-gated FULL-BLOCK replace of its own fenced block in `git rev-parse --git-path info/exclude` (stale masks drop by construction; `--clear` always means REMOVE the block — it takes precedence over the derivation). Writes ONLY its fence — never `.gitignore`, never global config; symlinked/non-regular exclude paths and malformed fences fail closed. Watch note: a real file at an excluded path is silently skipped by bulk staging (`git add -A`/`git add .`) — delete the stale line first; the probe flags exactly this case. |
 | `/agent-workflow-kit mcp` | Claude Code · opt-in | **typed-channel registration** — the kit ships a read-only stdio **MCP server** exposing its two promptless readers as TYPED tools (`path_inventory`: exists / type / size / line count / listing / a small file's text, many paths in ONE call; `repo_search`: literal search, the pattern a JSON string). Their arguments are named JSON fields rather than a string handed to a shell, so a pipe, a redirect or a quote inside a pattern or a path stays DATA and is never interpreted — legal bytes to search for, with no shell to read them as operators. Shipping the server does nothing on its own — a client sees it only once the project declares it, and this mode is that declaration: the `agent-workflow` entry in **`.mcp.json`** (command `node`, args = the absolute path of the RUNNING kit's server) plus `enabledMcpjsonServers` and the two derived tool allow rules in **`.claude/settings.json`**. Preview by default and the **exact entry is printed before consent** (registering a server means your client will run that command); `--apply` writes `.mcp.json` FIRST, then settings, merge-don't-clobber with each file's EOL kept, and a re-apply adds nothing twice. An existing `agent-workflow` entry that **structurally differs** from what this kit copy would write is refused unwritten (the comparison ignores key order, so re-serialized identical bytes are the same registration) — silently changing what an MCP server launches is what consent must not slide past. Where an OS sandbox masks `.mcp.json` with a device node, it writes nothing, hands you both paste-ready texts and exits 0. The server is a read-only child of your client (no write, no exec API) running outside the Bash sandbox as the client does. Never writes `settings.local.json`; never commits. |
@@ -242,13 +242,13 @@ file), or run the guarded `/agent-workflow-kit uninstall`.
 | `/agent-workflow-kit core-evidence` | any time | **the ONE loop-evidence writer** (strip-the-kit) — every core evidence record lands in a single append-only JSONL store inside the git dir (never committable; versioned schema, latest-per-key supersession, byte-identical duplicates refused, malformed lines fail every reader closed). `red-proof "<file>#<pattern>"` declares an observed-red **BEFORE a bugfix** (N/N red runs + content custody + base + the pre-fix fingerprint; green/mixed/timeout are DISTINGUISHED refusals — nothing written); `degrade --backend --reason` is the ONLY escape for an unavailable review backend (per-tree, never all backends); `summary` renders the whole loop state statelessly (gate result · per-backend verdicts · red-proofs · degrades) — no ledger, no rounds, nothing remembered. Honest residual: records are forgeable — self-discipline, not a security boundary. Never commits, never runs a subscription CLI. |
 | `/agent-workflow-kit coverage-check` | any time | **the final-run checker** (D3(c)+(d)) — **certifies coverage ONLY inside the `--final` run that owns the lcov** (ownership is exclusive by CONVENTION over the fixed path, not enforced — a concurrent writer to it is a stated residual, queued as LCOV-EXCLUSIVE-OWNERSHIP): an artifact on disk proves nothing about the tree it came from, so a standalone run prints its findings and states `attested=no` / `NO VERDICT` rather than a PASS (an lcov that predates an edit would otherwise certify a line the suite never executed). `attested=` claims a verdict was ISSUED, pass or fail — a run over uncovered lines still reads `attested=yes` and still exits 1, and a run whose coverage arm never executed (no lcov) reads `attested=no` even inside `--final`, because nothing was read and nothing is certified. The runner passes a nonce whose one-way commitment over `{nonce, fingerprint, base}` is the `final-start.attempt` it recorded; a context describing another tree, or matching no recorded attempt, is a REFUSAL, never a verdict. Findings are unchanged — reads the lcov the declared `unit-tests` gate produced at the FIXED git-dir path and fails on any uncovered CHANGED executable Node line (listed `file:line`; a changed file absent from the map is a file-level red; out-of-domain/unsupported files are LISTED — the claim narrowed honestly); VERIFIES every current-base red-proof declaration (bound test exists · custody hash unchanged · green N/N now · pre-fix fingerprint differs); prints `lcov-sha256=<hex|none>` of the exact bytes it consumed — the sha the `--final` receipt binds and re-hashes. An absent lcov is a LOUD `skipped-no-lcov`; a symlinked path is a refusal. `--check` is the gate exit code — declare it as the LAST gate (`run-gates --final` refuses otherwise). Read-only. |
 | `/agent-workflow-kit commit-guard` | any time | **the read-only pre-commit guard** (D10) — makes the commit capture the whole current working tree, so «verified» and «about to be committed» are the same bytes (the receipt itself has a stated residual — see the mode doc). FIRST it refuses an **INDEX that lags the verified working tree** (the gates and the fingerprint describe the WORKING tree while `git commit` takes the INDEX alone, and the fingerprint cannot tell them apart — so a lagging index used to ship a strict subset of what was verified): unstaged tracked paths or reviewable untracked-not-ignored paths, named up to a bounded cap with the remainder stated, a dirty tracked **submodule** named separately with its own recovery, and fail-closed on an undecidable probe. This deliberately blocks a partial commit. Then it binds the LATEST completed `run-gates --final` receipt to the EXACT current tree: refuses on a missing/red/stale receipt, fingerprint drift under the run, a dangling later attempt, declaration content drift, evidence-hash or lcov drift, or unsatisfied review obligations (the same review-state decision, recomputed over a sanitized env — forged out-of-repo stores never satisfy). Re-runs NO gate or test. Wire it into `.git/hooks/pre-commit` (the installer writes the RESOLVED invocation). `git commit --no-verify` stays the stated residual. |
-| `/agent-workflow-kit recommendations` | any time (every `upgrade` ends with it) | **read-only deployment advisor** (AD-044) — computes what in THIS deployment is configured sub-optimally (allowlist not seeded, autonomy render drifted, OS sandbox unavailable, gates undeclared, bridge friction, sandbox-mask clutter, an unacknowledged sandbox recipe) and renders **verdict-first**: one composed verdict line (does anything need attention?), then each item as **{severity · what · one-line benefit · an optional `recipe:` line (the sandbox-lane live recipe, the worktrees-dir hand-apply-first grant advice, or the agents hidden-mode reconcile follow-up) · the exact consent-gated apply one-liner}**. The agent PRESENTS the section in the user's conversational language — every fact and count, nothing added or dropped; commands, paths, hosts and rule strings byte-exact; raw tool block on request — and runs EXACTLY the rendered one-liners only on your yes, surfacing each item's posture note first. Renders **present-even-when-empty** (`no recommendations — flow optimal.`); a failed probe degrades to a stated skip line. Registry strings are fact-true frozen one-line data (posture/risk notes live in the mode doc at the consent moment); the kit never seeds `sandbox.network.allowedDomains` / `filesystem.allowWrite` (**HAND-APPLY** territory), and the sandbox-lane item's convergence is a neutral fingerprint acknowledgement recorded by a consent-gated ack writer into `docs/ai/acks.json` — never a security key (the recipe is documented per bridge in `capability.json` `networkHosts` + `writableDirs`). `--cwd` is required (the target project is explicit); never writes, never commits, never runs a subscription CLI. |
+| `/agent-workflow-kit recommendations` | any time (every `upgrade` ends with it) | **read-only deployment advisor** (AD-044) — computes what in THIS deployment is configured sub-optimally (allowlist not seeded, autonomy render drifted, OS sandbox unavailable, gates undeclared, bridge friction, sandbox-mask clutter, an unacknowledged sandbox recipe, a feature-spec layer never adopted) and renders **verdict-first**: one composed verdict line (does anything need attention?), then each item as **{severity · what · one-line benefit · an optional `recipe:` line (the sandbox-lane live recipe, the worktrees-dir hand-apply-first grant advice, the agents hidden-mode reconcile follow-up, or the spec-adoption decline preview) · the exact consent-gated apply one-liner}**. The agent PRESENTS the section in the user's conversational language — every fact and count, nothing added or dropped; commands, paths, hosts and rule strings byte-exact; raw tool block on request — and runs EXACTLY the rendered one-liners only on your yes, surfacing each item's posture note first. Renders **present-even-when-empty** (`no recommendations — flow optimal.`); a failed probe degrades to a stated skip line. Registry strings are fact-true frozen one-line data (posture/risk notes live in the mode doc at the consent moment); the kit never seeds `sandbox.network.allowedDomains` / `filesystem.allowWrite` (**HAND-APPLY** territory), and the sandbox-lane item's convergence is a neutral fingerprint acknowledgement recorded by a consent-gated ack writer into `docs/ai/acks.json` — never a security key (the recipe is documented per bridge in `capability.json` `networkHosts` + `writableDirs`). `--cwd` is required (the target project is explicit); never writes, never commits, never runs a subscription CLI. |
 | `/agent-workflow-kit doc-parity` | any time | **read-only doc-parity lint** (AD-049) — kills the doc-drift class where a mode-contract doc silently lags a code constant (a `--check` doc still reading `300` after the diff cap moved to `400`): a **closed, exported registry** binds each live constant (review caps, schema versions, the ledger's own class/scope vocabulary, and the autonomy-doctor EXIT/status/trusted-dir contract) to the exact token its `references/modes/*.md` contract must carry, and asserts the CURRENT value renders into every bound file — a drifted doc, an unreadable file, or an absent token **fails closed**. The values are sourced from the live imports (never re-typed), so the lint can't itself go stale; adding a binding is adding a checked entry (closed-world, edit-safe). `--check` is a gate exit code for `docs/ai/gates.json`. Never writes, never commits, never runs a subscription CLI. |
 | `/agent-workflow-kit dispatch` | any time | **the delegation engine** — makes "how much does delegating a sub-task actually buy?" a measured number instead of a feeling. `check <file>` validates a sub-task brief's contract block and exits 0/1 naming the first violated field — **form only**: whether the task is genuinely bounded, its design decided and its acceptance adequate stays your judgment, and a well-formed absurdity passes here by construction. `advise --step-class <c>` answers the question that comes BEFORE that one — which vehicle should carry this kind of sub-task, whether it is even present on this machine, and what the ledger has already recorded for threads of that class (finished, failed, closed without a fold, and still open — counted separately) — and it decides nothing: it refuses no dispatch, gates no verb, and a choice that diverges from the advice is noted rather than blocked. It reads the filesystem only: nothing is launched to find out what is installed, an absent ledger prints "no recorded history", an unreadable one prints the store's own words, and either way the advice still prints. The same block appears as a footer under a form-valid `check` — never under a refusal, so it can never hide one. `register` pre-registers an acceptance wave (step classes, pairing key, minimum observations per class, the mean and first-pass thresholds) so the bar can never be chosen after the results it judges — immutable per wave. `observe` records ONE hand-written observation (`solo-construction`, the baseline whose ratio is 1 by construction — except over a scope measuring zero bytes, which has no ratio at all and is recorded ineligible by name — or `self-reported`) — delegated numbers are never hand-written, they are derived. The writer verbs are where that derivation happens: `open` puts a delegated thread on the record with every mint-time field copied from the brief's own header, refusing a deadline the wrapper's cap plus its kill grace would not fit inside, and recording whether the tree it started from was clean (a dirty one makes the result honestly unmeasurable rather than quietly counted); `await` waits for that one dispatch to answer and writes nothing — only the finished receipt satisfies it, a run still holding the nonce means keep waiting, and a wait that runs out says so with its own exit code, names whether the deadline or your own timeout ended it, and authorizes nothing: a wait that ended without an answer is a question for you, never permission to dispatch again; `return` absorbs the receipt the wrapper minted — only a finished one, checked against the contract it actually ran, its deadline and its own report, and refused outright when the tree hides changes from git or moves while the return is being computed — and derives the bytes from git rather than from anyone's claim; `fold` is the acceptance, and it refuses if the tree moved since the return — precisely, it re-confirms **equality of the visible canonical payload**, which is a change detector rather than a cryptographic identity of the tree: that payload is unframed and carries no file mode, so a content or symlink target that imitates the marker opening the next entry can alias two trees, and an executable-bit flip moves nothing (both named as residuals in the mode doc, with the fix queued). Where the payload cannot follow an object's bytes at all — a binary, a non-regular path, a submodule, a symlink whose target is not valid UTF-8 — `return` and `fold` **refuse** rather than promise what they cannot check. `degrade` closes a thread that never earned a fold, on the record and with its reason. `aggregate` prints one wave: the registered thresholds, every observation as context, and per step class the finished threads — a folded success with git-provable bytes contributes its ratio, one whose bytes are unprovable is excluded from the mean but still counts in the first-pass rate, and a failed thread, a degrade-closed one, or one folded after failing acceptance each count as a real zero. Below the registered minimum nothing is computed (insufficient); at or above it is computed and labeled PILOT evidence. It REFUSES rather than guessing: no pre-registration, an unfinished thread in scope, a recorded refusal-to-delegate that never opened a thread, or an ambiguous wave each stop the computation by name. `handoff-return --slug <s>` closes the worktree loop after `land --prepare`: it re-attests that main still holds exactly the prepared tree under the same HEAD (both recorded in the handoff at prepare time), prints the satellite handoff's user-owned content byte for byte with its boundaries, byte lengths and the main-owned destinations each part folds into, prints the handoff digest and both OIDs as its proof, states the after-the-fold order (a fold landed after the gates leaves them stale), and records ONE self-reported worktree-stream observation only when the whole prepared change set is measurable — a deletion, a rename, a symlink, a submodule or a mode-only change ends with a named NOT RECORDED instead, never a partial number. Writes only its own append-only ledger inside the git dir (never committable); never commits, never runs a subscription CLI. |
 | `/agent-workflow-kit worktrees` | any time | **parallel feature worktrees** — run several features in DIFFERENT agent sessions on one repo, zero interference on working-tree files (the ONE exception is the dependency cache, below): `provision <slug> --plan <file>` creates a sibling git worktree on branch `aw/<slug>` and populates it (registry-derived footprint copy-if-missing — a tracked file is never overwritten; EXACTLY ONE seeded feature plan; the `handoff-<slug>.md` record from minute zero; `node_modules` symlinked where the link stays ignored — a shared MUTABLE dependency cache: writes through it hit MAIN's node_modules; for isolation run the printed isolated-install command (`--install` only PRINTS it; on `--resume` run the printed unlink-first recovery first — printed only for a link whose RAW TARGET is MAIN's `node_modules`, since a foreign or unreadable link is reported as such with no removal advised); absolute root-pinned gate commands rebased on untracked copies only, and only while their bytes equal the MAIN source or its rebased form — user-modified copies stay untouched); `list` is read-only (slug, branch, base, dirty, handoff); `prompt <slug>` is read-only too and re-prints the satellite's cold-start prompt — the same text `provision` ends its report with: where the worktree is, its ONE seeded plan, the handoff as the one channel back, MAIN's orientation (shared series index, landing) and, under its own heading because it is probed on the satellite, that checkout's install posture — every value derived LIVE rather than replayed from the frozen provision record, a recorded value that no longer matches NAMED as a divergence (with the cause its source makes likely) instead of printed as the runnable one, every offered command marked with WHO runs it (`MAIN $ …` for the landing, `HERE $ …` for this checkout's own install, a posture with nothing to run staying prose), and a control character in any rendered value a typed STOP rather than a forged prompt line; `land <slug> --prepare` locks the common git dir, fail-closes on divergence or incomplete satellite state, transfers the complete accepted satellite diff onto a CLEAN main, runs sync plus the declared gates, and reports HEAD/TRANSFER/PREPARED OIDs — the commit ALWAYS stays a dialogue ask; `cleanup <slug>` takes the same lock and removes a LANDED worktree only after live landed-verification against main HEAD, while `--abandon` is the ONE destructive arm (destroys unlanded work; **no preview step** on any writer). The parent dir is the `docs/ai/worktrees.json` `parentDir` setting (default: the repo's sibling parent); an unwritable parent degrades to printed maintainer-pasted commands, and the one-time host consent that makes it promptless surfaces via `recommendations`. Never commits, never pushes, never runs a subscription CLI. |
 | `/agent-workflow-kit uninstall` | opt-in, any time | **guarded teardown** — the inverse of `init` / `setup`. Removes only what's **provably ours** (managed skill dirs + bridge wrappers; in a project, the hidden-mode git-ignore block it added + the pre-commit hook it installed); **never deletes** your `docs/ai` / `AGENTS.md` (prints the exact `rm` to run by hand) or your `.claude/settings.json` (prints an **edit** — remove the attribution key, review any velocity `permissions.*` — never an `rm`). Always `--dry-run` first; preflight-then-mutate; never commits. |
 | `/agent-workflow-kit velocity` | Claude Code · opt-in | **onboarding velocity profile** — seeds a fixed, audited **read-only** allowlist into `.claude/settings.json` so routine read-only commands stop idling on approval prompts while you're away; opt-in `acceptEdits`; plus a **read-only advisory** of likely project gate commands to add by hand. Writes **only** `.claude/settings.json` — **never** allowlists commit/push/publish, never writes `settings.local.json`, never commits. A seeded entry is a **trust posture, not a sandbox** (a runtime residual remains at the settings level — its guard ships as the opt-in `hook` command); a direct commit/push/publish still asks. `--dry-run` first. |
-| `/agent-workflow-kit agents` | Claude Code · opt-in | **read-only subagents** — places bundled subagent definitions into `.claude/agents/`. **No vehicle gets `Bash`**, and that is the load-bearing property: a read-only fan-out on a full-tool subagent shells out for facts it could have read, and every shelled command is an approval prompt you never needed to see. Three ride a **cheap model** (haiku, low effort) for mechanical work — extraction sweeps, changelog fact-skeletons, gate-failure triage; the fourth, **`review-lens`**, is an ADDITIONAL independent read-only review opinion on code your configured backends have already seen (never a replacement for your review recipe, advisory like every review). Writing code and running gates stay on your main lane, and every vehicle's output is verified. Preview by default (`--apply` writes); an existing customized file is **preserved, never overwritten**; never touches `settings*.json`, never commits. |
+| `/agent-workflow-kit agents` | Claude Code · opt-in | **subagent vehicles** — places the five bundled subagent definitions into `.claude/agents/`: **four read-only vehicles + one full-tool `executor`**. **No read-only vehicle gets `Bash`**, and that is the load-bearing property: a read-only fan-out on a full-tool subagent shells out for facts it could have read, and every shelled command is an approval prompt you never needed to see. Three of the four ride a **cheap model** (haiku, low effort) for mechanical work — extraction sweeps, changelog fact-skeletons, gate-failure triage; the fourth, **`review-lens`**, is an ADDITIONAL independent read-only review opinion on code your configured backends have already seen (never a replacement for your review recipe, advisory like every review). The fifth, **`executor`** (`model: opus`, all tools), is the ONE vehicle with a shell and the instrument behind the **Subagent** recipe: dispatched only for a bounded, file-disjoint execution / authoring / routine slice you verify afterwards — never for read-only work, never as a review backend, and it never commits. Its state (`placed` / `customized` / `unusable` / `missing`) is what a `subagent` slot's readiness resolves from. Writing code and running gates stay off the four read-only vehicles; the executor carries a bounded slice you re-verify on your main lane, and every vehicle's output is verified. Preview by default (`--apply` writes); an existing customized file is **preserved, never overwritten**; never touches `settings*.json`, never commits. |
 | `/agent-workflow-kit hook` | Claude Code · opt-in | **gate-approval hook** — places a self-contained PreToolUse hook (`.claude/hooks/`) and wires it into `.claude/settings.json`: a Bash command **byte-identical** to a gate you declared in `docs/ai/gates.json` (run from the project root) is auto-approved — no prompt, no idle; a seeded read-only command carrying a runtime residual (output redirection, command substitution, `--output` writes) now **asks** even where an allow rule would have silently passed it (proven live — hook `ask` overrides an allow rule). Detection is a conservative string scan, so it over-asks on a byte that is ordinary text — searching for `=>`, or a read wearing `2>/dev/null`, prompts. That is a documented open limit: 4.1.0 built three mechanisms to narrow it and removed all three in review, each counterexample kept as a test (see Mode: hook). Exact matches only, never patterns; never `deny`; a broken `gates.json` only disables auto-approval, never the guard. An opt-in **read-lane** (`--read-lane` → `docs/ai/lanes.json`, a **separate** file from `gates.json`) additionally auto-approves *compounds* of seeded read-only commands carrying no shell metaprogramming; `--apply --read-lane` verifies the placed hook is current first (delete-to-reseed otherwise). Preview by default; never writes `settings.local.json`; never commits. |
 | `/agent-workflow-kit state-block-guard` | Claude Code · opt-in | **closing-block detector** — a `Stop` hook that reads the turn's final assistant message and warns when the closing state block is defective: the «what I need from you» slot answering *nothing* (a turn that ENDS always needs a resume, so the answer is false, not merely unhelpful), or a first-person promise of imminent work in a turn that is over. Judged on the slot's first clause, so a real ask followed by a clause break and "nothing else" passes, and a promise gated on something named passes; matching is word-bounded and Unicode-aware, quoted and fenced examples are stripped, and the last STARTED block decides — an incomplete tail counts as no block rather than falling back to an earlier one. A message carrying no block at all is silent unless you pass `--require-block` — this kit does not mandate the block, and a hook that runs every turn must not warn every turn. The judgement is lexical and the mode doc names every residual it leaves. **Detection, never prevention** — a `Stop` hook cannot un-send the message it judges; what it buys is that a silent recurrence becomes a visible one. Warns via `systemMessage` and **exits 0 on every path**: never `deny`, never blocks the stop, never re-enters the model. Reads nothing but the message, makes no network call, approves nothing. This mode is **read-only and has no writer** — it ships the self-contained hook and a paste-ready wiring block you merge into `.claude/settings.json` yourself. |
 | `/agent-workflow-kit bridge-settings` | opt-in, any time | **host-level bridge settings** — read or change the bridges' `KEY=VALUE` config file (`${XDG_CONFIG_HOME:-~/.config}/agent-workflow/bridge-settings.conf`), the **one place a knob survives kit upgrades** (it lives outside every kit tree; a refresh never touches it, and now states loudly if it ever overwrote a local edit). First knobs: the **codex Fast tier** (`CODEX_SERVICE_TIER=priority` — ~1.5× speed at a **2.5× credit rate**, quality-neutral, default off — a consented spend), the codex/agy hard timeouts, the codex review byte cap, and `AGY_REVIEW_MAX_TOTAL_BYTES` (the ceiling on what an oversized agy code review may feed before it refuses pre-spend). `AGY_REVIEW_ALLOW_ADDDIR` is a **retired** compatibility key: still recognized so an existing line never warns as unknown, but it arms nothing — the writer refuses to set it and `--unset` clears it. Allowed keys + value rules come from the bundled bridge manifests; **model/effort are never settable** (the quality guard is untouched). **Previews by default**; refuses an unknown key, an out-of-range value, or a duplicate-carrying file; writes atomically (symlink/TOCTOU-safe). Never commits, never runs a subscription CLI. |
@@ -292,7 +292,7 @@ agent-workflow-kit  —  the composition root (installed via npx … init)
 - **Delegates** substrate deployment to **`@sabaiway/agent-workflow-memory`** when a healthy
   standalone copy is present, else uses its **bundled fallback** — same `docs/ai/` either way.
 - **Injects** three bounded pointers into the deployed `AGENTS.md` — the workflow **methodology**, the
-  **orchestration recipes** (Solo / Reviewed / Council / Delegated), and the **autonomy policy** (the
+  **orchestration recipes** (Solo / Reviewed / Council / Delegated / Subagent), and the **autonomy policy** (the
   `docs/ai/autonomy.json` read contract) — read **live** from the installed
   **`agent-workflow-engine`** (the canonical narrative; a published member, never one of the shipped
   backends). `/agent-workflow-kit recipes` surfaces + plans a recipe for your environment, read-only.

package/SKILL.md

@@ -3,7 +3,7 @@ name: agent-workflow-kit
 description: Deploy or upgrade a portable AI-agent memory-and-workflow system in any project. Use when the user wants to bootstrap `docs/ai/` + an entry-point `AGENTS.md` (+ `CLAUDE.md` alias) + cap/archive/index enforcement in a new or existing repo, set up the Memory Map and session protocols, install the docs-rotation pre-commit hook, or run `/agent-workflow-kit` / `/agent-workflow-kit upgrade`. Triggers on phrases like "set up the memory system", "deploy the AI workflow here", "bootstrap docs/ai", "upgrade the workflow".
 disable-model-invocation: true
 metadata:
-  version: '10.2.0'
+  version: '10.4.0'
 ---
 
 # agent-workflow-kit

package/capability.json

@@ -3,7 +3,7 @@
   "schema": 1,
   "name": "agent-workflow-kit",
   "kind": "composition-root",
-  "version": "10.2.0",
+  "version": "10.4.0",
   "provides": [],
   "roles": {},
   "detect": {

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@sabaiway/agent-workflow-kit",
-  "version": "10.2.0",
+  "version": "10.4.0",
   "description": "Portable, cross-agent memory & workflow for AI coding agents — Claude Code, Codex, Cursor, Devin Desktop. One command deploys an AGENTS.md entry point + docs/ai context with cap/archive/index enforcement into any repo.",
   "keywords": [
     "ai-agents",

package/references/agents/executor.md

@@ -0,0 +1,40 @@
+---
+name: executor
+description: Executes ONE bounded slice — an execution, authoring, or write-capable routine slice — on behalf of the orchestrator; only the files the brief names, their suites, and a return block. Never dispatched for read-only work: a sweep, an inventory or a review rides a read-only vehicle instead.
+model: opus
+effort: high
+---
+
+You are the EXECUTOR vehicle: the one full-tool subagent this kit ships. The orchestrator owns the
+plan, the review and the commit; you own ONE slice of it, end to end, and nothing else.
+
+- **One slice, the named files only.** The brief names exactly one slice and lists the files you may
+  change. You change those and no other file — not a neighbour that would be tidier, not a test
+  outside the list. A file you believe the slice needs and the brief did not name is a red line,
+  not a decision you get to make.
+- **Read before you edit.** The plan, the governing contract and the project rules the brief names
+  are read first. An edit written before them is guesswork wearing the shape of work.
+- **You never commit, and you never touch what governs you.** No git write at all: no `add`,
+  `commit`, `push`, `stash`, `reset`, `checkout`, `tag`, no history rewrite. You never edit the plan
+  or the contract under `docs/ai/specs/` that governs YOUR OWN slice, the ADR, the changelog, the
+  handover documents or `docs/ai/source-size.json` — those are the orchestrator's, and the
+  orchestrator is the only one who commits. A plan draft, a contract draft or a regenerated document
+  that the brief names as your DELIVERABLE (an authoring or a routine slice) is a named file like
+  any other.
+- **You run the suites and report what they printed.** The brief maps every file you touch to the
+  exact test files and commands to run; where it does not, run the paired `<name>.test.mjs` when one
+  exists — never hand an implementation file to `node --test`, which would run it as an empty suite
+  and pass vacuously — plus every gate command the brief names, and the REAL output goes into your
+  return block. A failing
+  test is reported as failing; papering over it, skipping it, or weakening an assertion to reach
+  green is the worst thing you can do here.
+- **You stay inside the budget the brief states.** Every file keeps to the line cap it names. A
+  comment exists only where the code truly cannot carry the fact. No attribution of any kind — to
+  an agent, a model or a tool — anywhere: code, comments, messages, documents. The project's
+  language and encoding rules come from its `AGENTS.md` and the brief — never assume English or ASCII.
+- **A red line STOPS you.** An approval ask, a need for the network or a credential, a file outside
+  your slice, or a finding that the brief itself is wrong: you stop and report it. You never
+  improvise around it and never widen your own scope to repair it.
+- **Your final message IS the return value.** The exact paths you changed, the commands you ran with
+  their results, and anything left undone with the reason. Nothing else: the orchestrator verifies
+  every returned slice by running its suites again.

package/references/modes/agents.md

@@ -1,15 +1,20 @@
 ### Mode: agents
 
 <!-- opt-in-capability: agents -->
+<!-- opt-in-capability: executor-vehicle -->
 
-The opt-in **read-only subagent writer** — the family's second `.claude/` writer, on the velocity discipline. It places the bundled subagent definitions (`references/agents/*.md`) into the project's `.claude/agents/`. **Claude-Code-specific** (like velocity): other agent hosts ignore `.claude/agents/`.
+The opt-in **subagent-vehicle writer** — the family's second `.claude/` writer, on the velocity discipline. It places the **five** bundled subagent definitions (`references/agents/*.md`) into the project's `.claude/agents/`: **four read-only vehicles** and **one** full-tool `executor`. **Claude-Code-specific** (like velocity): other agent hosts ignore `.claude/agents/`.
 
-**Every vehicle grants READ-ONLY tools and NO `Bash`** — that is the load-bearing property, not a detail. A read-only fan-out on a full-tool vehicle shells out for facts it could have read, and each shelled command is an approval prompt the maintainer never needed to see; a vehicle with no shell structurally cannot do that. Two lanes ride on it:
+**Every READ-ONLY vehicle grants READ-ONLY tools and NO `Bash`** — that is the load-bearing property, not a detail. A read-only fan-out on a full-tool vehicle shells out for facts it could have read, and each shelled command is an approval prompt the maintainer never needed to see; a vehicle with no shell structurally cannot do that. Two lanes ride on it:
 
 - **cheap lane** (`model: haiku`, `effort: low`) — `mechanical-sweep`, `changelog-skeleton`, `gate-triage`: extraction sweeps, changelog fact-skeletons, gate-failure triage. Extraction/drafting only; the orchestrator applies judgment and verifies the output.
 - **review lens** (`review-lens`, review-capable model) — an ADDITIONAL independent read-only opinion on code the configured review backends have already seen. It exists because a third lens otherwise has **no vehicle at all**: the cheap vehicles are scoped away from judgment, and a review-capable full-tool subagent is the prompt-flood shape. It never replaces the configured review recipe, and it is advisory like every other review.
 
-Writing code, running gates, and user-facing copy never move to these vehicles.
+Writing code, running gates, and user-facing copy never move to these four vehicles.
+
+**The fifth vehicle, `executor`, is the ONE full-tool one** (`model: opus`, every tool — a shell included). It is the instrument behind the **Subagent** recipe, dispatched ONLY for a **bounded, file-disjoint slice** the orchestrator verifies afterwards by running its suites: a slice of execution (`plan-execution.execute`), a plan/contract authoring brief (`plan-authoring.author`), or a bounded chore (`routine.carrier`). It **never commits** (no git write at all), is **never a review backend**, is **never a bridge substitute**, and is **never dispatched for read-only work** — a sweep, an inventory or a review rides a read-only vehicle instead.
+
+**Its readiness is the vehicle FILE.** `surveyExecutorVehicle` answers exactly one of four states: **`placed`** (the bundled bytes at `.claude/agents/executor.md`), **`customized`** (a readable regular file whose frontmatter names `executor` and whose tools are not read-only), **`unusable`** (a symlink, a non-regular or unreadable file, or one failing that check — with the reason), **`missing`**. `placed` and `customized` are dispatchable; on `unusable` or `missing` a `subagent` slot **degrades to Solo** with a reason naming this mode's apply command. `/agent-workflow-kit status` shows the state in its `agents` block and the deployment advisor raises it when a configured slot names `subagent` and the vehicle is `unusable` or `missing` — that item is **`executor-vehicle`** (attention-class: a configured declaration that is broken), a DIFFERENT capability from this mode's placement offer (`agents`), which converges the moment nothing is left to place and therefore can never observe a present-but-unusable vehicle. It is a claim about the FILE, never about the host: a Claude Code lane, like this mode itself.
 
 Run `node ${CLAUDE_SKILL_DIR}/tools/cheap-agents.mjs [--dry-run | --apply] [--cwd <dir>]`:
 
@@ -17,4 +22,4 @@ Run `node ${CLAUDE_SKILL_DIR}/tools/cheap-agents.mjs [--dry-run | --apply] [--cw
 2. **Only on an explicit yes**, re-run with `--apply`. It writes **only** under `.claude/agents/` — never `settings.json` / `settings.local.json`, never a commit. `--apply` is deployment-gated (the stamp must be at the lineage head) and symlink-safe (a symlinked `.claude` / `.claude/agents` / target file is a STOP).
 3. **Hidden-mode deployments:** after apply, run the hide-footprint reconcile (`node ${CLAUDE_SKILL_DIR}/tools/hide-footprint.mjs --dir <project> --reconcile`) so the placed files stay invisible to `git status` — `/.claude/agents/` is in the known-footprint registry; the apply report reminds you.
 
-**Invariants:** writer (writes only `.claude/agents/`) · preview by default · a diverged existing file is reported and preserved, never clobbered · never touches settings · never commits · **no vehicle grants `Bash`** · the cheap-lane vehicles are pinned to `model: haiku` + `effort: low`, and the review lens is pinned OFF the cheap model (all content-tested).
+**Invariants:** writer (writes only `.claude/agents/`) · preview by default · a diverged existing file is reported and preserved, never clobbered · never touches settings · never commits · **no READ-ONLY vehicle grants `Bash`, and exactly one bundled vehicle, `executor`, grants a shell** · the cheap-lane vehicles are pinned to `model: haiku` + `effort: low`, and the review lens is pinned OFF the cheap model (all content-tested).

package/references/modes/procedures.md

@@ -2,18 +2,27 @@
 
 <!-- opt-in-capability: none — an inspection surface that configures nothing -->
 
-Read-only **activity-procedures advisor**. Answers *"what are the steps of this named activity, and which recipe applies at each slot here?"* It composes the orchestration recipes (`${CLAUDE_SKILL_DIR}/references/modes/recipes.md`) into **named activities** with **typed recipe slots**. It **never writes, never commits, never runs a subscription CLI** — the deterministic resolution lives in the kit; the orchestrator runs the resolved recipe via the bridge skills and **owns any commit when the activity has a commit boundary** (a backend never commits). Not every activity commits: `plan-authoring` ends at approval and produces no commit (plans are ephemeral, never committed); `plan-execution` commits per ledger row.
+Read-only **activity-procedures advisor**. Answers *"what are the steps of this named activity, and which recipe applies at each slot here?"* It composes the orchestration recipes (`${CLAUDE_SKILL_DIR}/references/modes/recipes.md`) into **named activities** with **typed recipe slots**. It **never writes, never commits, never runs a subscription CLI** — the deterministic resolution lives in the kit; the orchestrator runs the resolved recipe via the bridge skills or the executor vehicle and **owns any commit when the activity has a commit boundary** (every other carrier never commits). Not every activity commits: `plan-authoring` ends at approval and produces no commit (plans are ephemeral, never committed); `plan-execution` commits per ledger row.
 
-The two v1 activities (canon in the **installed engine**, `references/procedures.md`):
+The three activities (canon in the **installed engine**, `references/procedures.md`; the registry is `tools/carriers.mjs`):
 
-- **`plan-authoring`** (slot: `review`) — research → draft → self-review → **review {recipe}** → fold/loop → present for approval; enforce the mandatory Cleanup.
-- **`plan-execution`** (slots: `execute`, `review`) — per ledger row: resolve the recipe → if Delegated, dispatch execution first → implement → self-review → **review {recipe}** → gates → commit boundary; after the last row, the project-declared stages and Phase: Cleanup run as rows of their own.
+- **`plan-authoring`** (slots: `author`, `review`) — research → draft (the resolved `author` carrier drafts: Solo writes it, Subagent drafts from the orchestrator's brief) → self-review → **review {recipe}** → fold/loop → present for approval; enforce the mandatory Cleanup.
+- **`plan-execution`** (slots: `execute`, `review`) — per ledger row: resolve the recipe → if Delegated, dispatch execution first; if Subagent, dispatch file-disjoint slices to the executor vehicle and verify each returned slice → implement → self-review → **review {recipe}** → gates → commit boundary; after the last row, the project-declared stages and Phase: Cleanup run as rows of their own.
+- **`routine`** (slots: `carrier`, `parallel`) — name the chore and its file-disjoint slices → resolve → carry it (Solo, or Subagent: a read-only slice rides a placed read-only vehicle, a write-capable one rides the executor; `parallel` on → concurrently) → verify every returned slice; the commit boundary is unchanged.
 
-Run **`node ${CLAUDE_SKILL_DIR}/tools/procedures.mjs <activity> [--override <slot>=<recipe>]… [--json]`**. It reads the activity's steps live from the engine and prints them **verbatim**, then the **resolved effective recipe per slot** from the per-project config + the read-only backend detector:
+Value sets per slot type: `review` accepts `solo | reviewed | council`; `execute` accepts `solo | delegated | subagent`; a carrier slot (`author`, `carrier`) accepts `solo | subagent`; `parallel` is a **switch**, `on | off`, resolved outside the recipe lattice. Defaults when the config is silent: `review` → Reviewed if a review-capable backend is ready, else Solo; `author`, `execute`, `carrier` → Solo (a placed executor never flips a default); `parallel` → on. The orchestrator owns every commit; every other carrier — a bridge or a subagent — never commits.
 
-1. **Config = `docs/ai/orchestration.json`** — strict JSON, **agent-writable via `/agent-workflow-kit set-recipe` (`${CLAUDE_SKILL_DIR}/references/modes/set-recipe.md`) OR hand-edited** (the kit reads + validates it; `procedures`/`recipes` stay read-only — the writer is `set-recipe`). Shape: `{ "<activity>": { "<slot>": "<recipe>" } }`; all slots optional (an absent slot → its computed default, stated); an optional `"_README"` string is allowed + ignored; a `"flow"` object must carry the NUMERIC `"schema": 1` (the kit's accepted flow schema version) and validates against the CLOSED structural schema-1 key set (unknown flow keys and malformed per-key shapes refuse loudly; deep environment floors stay on the `set-flow` arming path). `review` accepts `solo|reviewed|council`; `execute` accepts `solo|delegated`. Seeded by `init` (a user-editable template) — see `${CLAUDE_SKILL_DIR}/references/modes/bootstrap.md`.
-2. **Default resolution (config silent):** `review` → Reviewed if any review-capable backend is `ready`, else Solo (never Council by default); `execute` → Solo (Delegated is opt-in). **Degradation:** a config/computed default degrades **gracefully with a stated reason** (Council → Reviewed → Solo; Delegated → Solo); a per-run **`--override <slot>=<recipe>`** that can't be satisfied degrades **loudly** (a flagged warning, so you tell the user) — but is **still exit 0** (a valid request that gracefully degraded).
-3. **Exit codes:** `0` success; `2` usage (unknown `<activity>` / bad `--override` — a bare `--override <recipe>`, an unknown slot, an invalid recipe-for-slot, or a duplicate slot); `1` config error (malformed / schema-invalid / unreadable `orchestration.json`) **or** engine error (the installed engine is absent / invalid / **too old** to ship `references/procedures.md` — upgrade it with `npx @sabaiway/agent-workflow-engine@latest init`). A `1`/`2` failure is loud (`path: reason`), never a silent fallback. **Lagging-kit honesty:** a kit predating the `"flow"` key that reads a config carrying one fails this config load loudly (exit `1`, reddening its full gate matrix); the `set-flow` arming path now enforces the declared `kitMinVersion` floor with a null-guarded comparison (an unparseable version never passes), while tolerate-first ordering remains the only protection for readers older than the `"flow"` key itself — no in-config floor can reach a kit that dies on the unknown key.
+Run **`node ${CLAUDE_SKILL_DIR}/tools/procedures.mjs <activity> [--override <slot>=<value>]… [--json]`**. It reads the activity's steps live from the engine and prints them **verbatim**, then the **resolved effective recipe per slot** from the per-project config + the read-only backend detector:
+
+1. **Config = `docs/ai/orchestration.json`** — strict JSON, **agent-writable via `/agent-workflow-kit set-recipe` (`${CLAUDE_SKILL_DIR}/references/modes/set-recipe.md`) OR hand-edited** (the kit reads + validates it; `procedures`/`recipes` stay read-only — the writer is `set-recipe`). Shape: `{ "<activity>": { "<slot>": "<value>" } }`; all slots optional (an absent slot → its computed default, stated); an optional `"_README"` string is allowed + ignored; a `"flow"` object must carry the NUMERIC `"schema": 1` (the kit's accepted flow schema version) and validates against the CLOSED structural schema-1 key set (unknown flow keys and malformed per-key shapes refuse loudly; deep environment floors stay on the `set-flow` arming path). `review` accepts `solo|reviewed|council`; `execute` accepts `solo|delegated|subagent`; a carrier slot (`author`, `carrier`) accepts `solo|subagent`; `parallel` accepts `on|off`. Seeded by `init` (a user-editable template) — see `${CLAUDE_SKILL_DIR}/references/modes/bootstrap.md`.
+2. **Default resolution (config silent):** `review` → Reviewed if any review-capable backend is `ready`, else Solo (never Council by default); `execute`, `author`, `carrier` → Solo (Delegated and Subagent are opt-in; a placed executor never flips a default); `parallel` → on. **Degradation:** a config/computed default degrades **gracefully with a stated reason** (Council → Reviewed → Solo; Delegated → Solo; Subagent → Solo when the executor vehicle is missing or unusable, the reason naming the apply command; a switch never degrades); a per-run **`--override <slot>=<value>`** that can't be satisfied degrades **loudly** (a flagged warning, so you tell the user) — but is **still exit 0** (a valid request that gracefully degraded).
+3. **Exit codes:** `0` success; `2` usage (unknown `<activity>` / bad `--override` — a bare `--override <recipe>`, an unknown slot, a value outside the slot's list, or a duplicate slot); `1` config error (malformed / schema-invalid / unreadable `orchestration.json`) **or** engine error (the installed engine is absent / invalid / **too old** to ship `references/procedures.md` — upgrade it with `npx @sabaiway/agent-workflow-engine@latest init`). A `1`/`2` failure is loud (`path: reason`), never a silent fallback. **Lagging-kit honesty:** a kit predating the `"flow"` key that reads a config carrying one fails this config load loudly (exit `1`, reddening its full gate matrix); the `set-flow` arming path now enforces the declared `kitMinVersion` floor with a null-guarded comparison (an unparseable version never passes), while tolerate-first ordering remains the only protection for readers older than the `"flow"` key itself — no in-config floor can reach a kit that dies on the unknown key.
+
+**The dispatch form (a slot resolved to `subagent`).** A carrier that is only NAMED is a name, not an instruction, so after such a slot's resolved-recipe line the advisor prints — indented under it, in place of the one-line vehicle mention — the form the dispatch must take, in five parts: (1) what a SLICE is for THIS activity — for `execute`, a set of file-disjoint ledger rows, wording copied verbatim where wording is a red line; for `author`, a brief naming the goal, the governing spec(s) and the ledger constraints, whose returned draft the orchestrator reviews as its own; for `routine.carrier`, a bounded mechanical task, where a read-only chore (a sweep, gate triage) rides its placed read-only vehicle — or is carried solo with a stated reason when that vehicle is absent — a write-capable one (a regeneration, a fixture build) rides the executor, and the changelog stays the orchestrator's; (2) the vehicle and its surveyed state — `.claude/agents/executor.md` (`placed` / `customized` / `unusable` / `missing`, from the same survey `status` and the advisor read) — dispatched **in the background**; (3) that the orchestrator **verifies every returned slice by running its suites itself**; (4) that the subagent is **never told to commit, never a review backend, never a bridge substitute**; (5) the **honest limit** — a Claude Code lane: on a host that cannot dispatch the vehicle, follow this form BY HAND and say so, never report it as a subagent dispatch. The wording is the kit's own (`tools/carriers.mjs`) and is printed, never re-worded. A slot resolved to `solo` or `delegated` renders exactly what it rendered before.
+
+**`routine`'s `parallel` switch renders against the EFFECTIVE carrier.** The flag always renders with its source (`parallel: on` / `parallel: off`); the concurrency claim — *file-disjoint slices dispatch concurrently* — renders **only** while the resolved `carrier` is `subagent`. Under a `solo` carrier the line states its own inertness instead, `(no effect while the carrier is solo)`: a switch never degrades, so the flag keeps the value you set and the render simply stops promising a concurrency nothing can perform. That makes four cells (`on`/`off` x `subagent`/`solo`), and only the `subagent`+`on` cell claims concurrency.
+
+**`--override <slot>=<value>` is a PER-RUN session override — it never writes.** Repeatable, at most one value per slot, precedence **override > config > computed default**; it changes THIS render only and leaves `docs/ai/orchestration.json` byte-identical (this mode is read-only; the writer is `set-recipe`). There is no persisted session state — the next run without the flag resolves from the config again — and an override that cannot be satisfied degrades loudly (above) while still exiting 0.
 
 **Flow armed-halves block (session-start read side).** When the config carries a `flow` block, the advisor also renders `Flow (schema 1) — armed halves (config · chain · bookkeeping):` — the **config half** (preset · councilRounds · kitMinVersion), the **chain half** (a light read-only probe of the flow store on the checker's fixed path: ARMED at an adoption record, UNARMED for an absent or unadopted store, fail-closed BROKEN wording for a malformed one), and the **bookkeeping half** (each declared path: declared non-excluded — the tracked-file floor verifies on the `set-flow` arming path — vs loudly DECLARED-EXCLUDED). A config with no `flow` block renders byte-identically to before and pays no store probe.
 

package/references/modes/recipes.md

@@ -2,19 +2,22 @@
 
 <!-- opt-in-capability: none — an inspection surface that configures nothing -->
 
-Read-only **orchestration advisor**. Answers *"how should I compose the optional execution-backends into plan → execute → review here, and which recipe fits?"* It **never writes, never commits, never runs a subscription CLI, and never executes a recipe** — the orchestrator (you) runs the chosen recipe through the bridge skills and makes the single commit; a backend is advisory or delegated, never autonomous.
+Read-only **orchestration advisor**. Answers *"how should I compose the carriers of a step — the optional execution-backends and the full-tool executor subagent — into plan → execute → review here, and which recipe fits?"* It **never writes, never commits, never runs a subscription CLI, and never executes a recipe** — the orchestrator (you) runs the chosen recipe through the bridge skills or the executor vehicle and makes the single commit; a backend or a subagent is advisory or delegated, never autonomous.
 
-The four recipes (defined over each bridge's `provides` roles — `codex`: execute + review; `agy`: review + probe), canonical narrative in the **installed engine** (`references/orchestration.md`):
+The five recipes (defined over each bridge's `provides` roles — `codex`: execute + review; `agy`: review + probe — plus the `carry` role the placed **executor vehicle** provides), canonical narrative in the **installed engine** (`references/orchestration.md`):
 
 - **Solo** — you plan, execute, and self-review; no backend (always available; the floor).
 - **Reviewed** — you execute; **one** backend reviews the result (advisory). Prefers `codex` when both are ready (`agy` carries a standing health caveat).
 - **Council** — **both** backends review independently; you synthesize the two opinions.
 - **Delegated** — you hand a **bounded** execution sub-task to a backend (`codex exec`), then review the returned diff and commit.
+- **Subagent** — a **full-tool frontier subagent**, dispatched from the placed executor vehicle (`.claude/agents/executor.md`), carries a **bounded, file-disjoint** slice — of execution, of plan/contract authoring, or of routine work; you verify the returned slice by running its suites yourself and you make the commit. It is **never a review backend**, **never a bridge substitute**, and is **never told to commit**; it **degrades to Solo** when the vehicle is `missing` or `unusable`, with the reason. Readiness here is the **vehicle FILE, never the host** — a **Claude Code lane**, like the `agents` writer itself: on a host that cannot dispatch the vehicle, the rendered dispatch form is an instruction you follow by hand and report as such, never as a subagent dispatch.
 
-1. Run **`node ${CLAUDE_SKILL_DIR}/tools/recipes.mjs`** (the read-only planner; `--json` for the structured form). It runs the backend detector, lists the four recipes, and prints — for the current environment — a **per-recipe dispatch plan that degrades with a stated reason** when a backend isn't `ready` (Council → Reviewed → Solo; Delegated → Solo), plus advisory **quota/health notes** (prefer the cheapest model; Council spends two backends' quota; `agy` may stall on substantive prompts — Issue-001, prefer `codex`).
+1. Run **`node ${CLAUDE_SKILL_DIR}/tools/recipes.mjs`** (the read-only planner; `--json` for the structured form). It runs the backend detector, lists the five recipes, and prints — for the current environment — a **per-recipe dispatch plan that degrades with a stated reason** when a carrier isn't `ready` (Council → Reviewed → Solo; Delegated → Solo; Subagent → Solo when the executor vehicle is `missing`/`unusable`), plus advisory **quota/health notes** (prefer the cheapest model; Council spends two backends' quota; `agy` may stall on substantive prompts — Issue-001, prefer `codex`).
 2. **Offer the choice** via **`AskUserQuestion` where your agent supports it** (`AskUserQuestion` in Claude Code) — one option per recipe, the `recommendRecipe` choice listed **first** — otherwise in prose. Then print `planRecipe(chosen, detection)` (the per-stage dispatch + degradation reasons + quota/health notes) so the user sees exactly what running it entails.
 3. **Availability = `readiness === ready`, full stop.** Every other readiness supplies the human reason (needs-skill → "not installed — `/agent-workflow-kit setup`"; needs-cli → "install the CLI"; needs-credentials → "log in"; degraded → "wrapper not on PATH — `/agent-workflow-kit setup`"). This is set-up state only — **never** a claim that a backend's service is responsive (the detector cannot observe a runtime stall; `agy`'s Issue-001 is a *standing advisory*, not a readiness signal).
 
+**The activities and their slots.** One registry (`tools/carriers.mjs`, re-exported by `recipes.mjs`) names **three** activities and their typed slots: `plan-authoring` → `author`, `review`; `plan-execution` → `execute`, `review`; `routine` → `carrier`, `parallel`. Each slot's accepted values follow its TYPE — `review` accepts `solo|reviewed|council`; `execute` accepts `solo|delegated|subagent`; `carrier` accepts `solo|subagent`. **`parallel` is a flag (`on|off`), not a recipe:** it resolves OUTSIDE the recipe lattice, never degrades, and never reaches the planner. A silent slot takes its **computed default** — `solo` for `author`, `execute` and `carrier` (placing the executor vehicle never flips a default; the subagent carrier is opt-in exactly as `delegated` is), `reviewed`/`solo` by readiness for `review`, and `on` for `parallel`.
+
 **The configured-recipe line (`--active-line`, read-only).** `node ${CLAUDE_SKILL_DIR}/tools/recipes.mjs --active-line` prints exactly **one** machine-composed line: the **CONFIGURED** recipe of every activity/slot, resolved from the target project's `docs/ai/orchestration.json` (read from the current directory) + live readiness — each slot with its source (configured vs computed default), its degradation stated, and its dispatched wrapper set — explicitly contrasted with the readiness **recommendation** (which is informational; the configured recipes are what runs). Paste it verbatim: it fills the session-start discovery step (the deployed `agent_rules.md` §1.1) and the handover "Active recipes:" slot; `set-recipe` echoes the same line after every successful write. A malformed config fails loud (exit 1), never a silent fallback.
 
-**Invariants:** read-only · never runs a subscription CLI · never commits · the orchestrator executes the recipe via the bridge skills, not the kit.
+**Invariants:** read-only · never runs a subscription CLI · never commits · the orchestrator executes the recipe via the bridge skills or the executor vehicle, not the kit.

package/references/modes/recommendations.md

@@ -4,7 +4,7 @@
 
 Requires: ${CLAUDE_SKILL_DIR}/references/shared/report-footer.md
 
-The **read-only deployment advisor** — the deterministic section every `upgrade` run ends with, also invocable on its own. It computes what in THIS deployment is configured sub-optimally (allowlist not seeded, autonomy render drifted, sandbox unavailable, gates undeclared, a declared gate matrix that verifies nothing, bridge friction, sandbox-mask clutter, an unacknowledged sandbox recipe) and renders **verdict-first**: one composed verdict line, then each item as **{severity · what is sub-optimal · the benefit in ONE plain line · an optional `recipe:` line (the `sandbox-lane` live recipe — egress hosts + resolved writable dirs — the `worktrees-dir` hand-apply-first grant advice, or the `agents` hidden-mode reconcile follow-up) · the exact consent-gated apply one-liner}**. The tool computes deterministic English DATA; **you PRESENT the section in the user's conversational language** — every fact, count and item from the tool, nothing added or dropped; commands, paths, hosts and rule strings stay **byte-exact**; show the raw tool block on request (the AD-032 report-contract lane — the tool cannot know the dialogue language, so the language rendering is your presentation layer).
+The **read-only deployment advisor** — the deterministic section every `upgrade` run ends with, also invocable on its own. It computes what in THIS deployment is configured sub-optimally (allowlist not seeded, autonomy render drifted, sandbox unavailable, gates undeclared, a declared gate matrix that verifies nothing, bridge friction, sandbox-mask clutter, an unacknowledged sandbox recipe, a configured `subagent` carrier whose executor vehicle cannot carry it) and renders **verdict-first**: one composed verdict line, then each item as **{severity · what is sub-optimal · the benefit in ONE plain line · an optional `recipe:` line (the `sandbox-lane` live recipe — egress hosts + resolved writable dirs — the `worktrees-dir` hand-apply-first grant advice, or the `agents` / `executor-vehicle` hidden-mode reconcile follow-up) · the exact consent-gated apply one-liner}**. The tool computes deterministic English DATA; **you PRESENT the section in the user's conversational language** — every fact, count and item from the tool, nothing added or dropped; commands, paths, hosts and rule strings stay **byte-exact**; show the raw tool block on request (the AD-032 report-contract lane — the tool cannot know the dialogue language, so the language rendering is your presentation layer).
 
 **Live host/session facts are tool-composed only.** Every fact this section states about the current
 host or session — prompts fired, sandbox scope, whether a bypass was needed, network reachability,
@@ -20,6 +20,8 @@ Run `node ${CLAUDE_SKILL_DIR}/tools/recommendations.mjs --cwd <project-root> [--
 3. **The apply-through-agent lane — an explicit informed-consent checkpoint:** after presenting, OFFER to apply; the user selects items in plain language; for each selected item you **surface its posture note inline** where one exists (the per-item notes below cover exactly the risk-marked keys; for `sandbox-lane` the note INCLUDES the sandbox-lanes ladder — present the whole ladder inline at the consent moment, never as a bare pointer). The user **explicitly confirms**, and **only then** — **no command runs before confirmation** — do you run the rendered command. Do NOT infer safety from the presence or absence of an `--apply` flag: most items' rendered command IS the mutation and completes on that one run, **including a no-`--apply` mutation** such as `family-freshness`'s `npx … init`. Some items instead render a **dry-run preview** that changes nothing and prints an explicit follow-up `--apply`/mutating command to run NEXT (e.g. `sandbox-lane`'s ack-write — a NEUTRAL recipe fingerprint into the family-owned `docs/ai/acks.json`, never a security key — and the `gates-declaration` seeder): after the SAME confirmation you run that printed follow-up command — no second ask, no improvisation (each writer keeps its own consent semantics: previews, `--apply` flags, refusals). An item marked **HAND-APPLY** (e.g. the `read-lane` stale/missing arms) is **never run by you and never written by the kit** — hand the user its rendered line together with its posture note; HAND-APPLY is **maintainer territory wherever it renders** — the apply slot or the `recipe:` line. For `worktrees-dir` the two classes COMPOSE in one item and the ORDER is part of the contract: its `recipe:` line is the HAND-APPLY grant advice, its apply one-liner is the dry-run ack preview, and you **wait for the maintainer to confirm the grant is applied (or the terminal fallback chosen)** before running that preview and the exact `--apply` command it prints — the ack RECORDS a choice that must already have been made, and against a trusted host NO the item renders no ack at all.
 4. Registry strings (benefits + item texts) are frozen tool data, fact-true, ONE line under the pinned shape cap — posture/risk detail lives in the notes below at the consent moment, never inline in the overview. The dual velocity+security wording (`safer — blast radius bounded by the OS sandbox, not human attention`) rides ONLY the items with a real security delta (the autonomy render, the sandbox provisioning); the bridge-wrappers item claims **velocity only**.
 
+**The `executor-vehicle` item (the carrier the project already CONFIGURED — beside the `agents` offer, never the same item).** It fires on ONE pair of facts: a slot in `docs/ai/orchestration.json` names `subagent` while the executor vehicle (`.claude/agents/executor.md`) is `missing` or `unusable` — so every such slot silently degrades to solo. That is a configured declaration that is broken, hence **`attention`**, not an offer; its text names the state, its reason and how many configured slots are affected across the three activities. **`placed` and `customized` render NOTHING** (a working vehicle is not a recommendation), a config naming no `subagent` slot renders nothing, and a config the validated reader refuses is a stated **skip**, never an item computed over a shape nothing accepted. It is deliberately DISTINCT from its two neighbours, neither of which can observe this state: the `agents` offer converges the moment nothing is left to PLACE — which a present-but-unusable executor also satisfies — and the review-recipe probe skips a slot configured `subagent` by construction. Its apply is the agents writer's own `cheap-agents.mjs --apply` (the same writer the `agents` item previews; here the rendered line IS the mutation, so read the item's state before confirming), and its `recipe:` line is the hidden-mode reconcile follow-up (`hide-footprint --reconcile`), for a hidden deployment only. Honest limit on convergence: the apply places an ABSENT vehicle, so it clears `missing`; it never overwrites a diverged file and STOPs on a symlink, so on `unusable` the item's apply line carries a `HAND-APPLY:` precondition (fix or remove the file, then run the writer) and an `unusable` vehicle converges only after the maintainer fixes or deletes the file the reason names (the delete-to-reseed the agents mode documents) and applies then. Risk profile: create-only writes under `.claude/agents/` — never `settings.json`, never a commit.
+
 **Per-item posture notes (the consent moment — surface BEFORE running or handing over the apply):**
 
 - `sandbox-lane` — surface this note TOGETHER with the sandbox-lanes ladder below (the ladder IS the practical half of the note — inline, never a pointer). Pure DISCOVERABILITY: it surfaces the manifest-declared observed session-sandbox recipe (egress hosts ∪ resolved writable state dirs — `networkHosts` ∪ `writableDirs` of the wired bridges' `capability.json`, the single documentation source) and converges on a NEUTRAL fingerprint acknowledgement recorded by the consent-gated **ack writer** into the family-owned `docs/ai/acks.json` (`sandboxLaneAck`; a changed recipe re-fires the item). The store is family-owned so no host settings validator guards it (AD-055 relocated the ack off the Claude Code settings schema, which rejected the unknown key); the legacy `"agentWorkflow": { "sandboxLaneAck": … }` settings-scope key is still READ for one deprecation window (until the next kit MAJOR). It never claims the settings security keys take effect on any host class, never recommends writing them, and the kit never seeds `sandbox.network.allowedDomains` / `sandbox.filesystem.allowWrite` (bridge council 2026-07-11, both backends concur: a network pre-allow widens egress for EVERY sandboxed command; a write allowance on CLI state dirs would expose credential dirs). Posture history: an IDE-managed session sandbox was live-observed (2026-07-11/12) ignoring hand-applied settings security keys in BOTH scopes, and codex needs a writable HOME (EROFS `~/.codex` in-sandbox); whether a session's sandbox honors the settings keys is runtime-unknowable from the advisor (a denial-only signal) — which is exactly why the item states only detectable facts and no zero-prompt promise on any host class.
@@ -33,6 +35,7 @@ Run `node ${CLAUDE_SKILL_DIR}/tools/recommendations.mjs --cwd <project-root> [--
 - `gate-hook` — the base arm is the ordinary opt-in wiring offer. The **`marker-stale`** arm is not: the placed hook validates your declaration through its OWN baked copy and goes dark on any key it does not know, so a declaration carrying the `lcovProducer` key under a hook that predates it silently turns auto-approval OFF, and every gate prompts again with no error anywhere. The condition is the key's PRESENCE, not its value — an older hook rejects a key it does not know whatever that key says, so `"lcovProducer": false` darkens it exactly as `true` does. The arm is deliberately marker-scoped — a stale hook is otherwise harmless — and its recovery is the writer's own: `gate-hook --apply` places only an ABSENT target, so converging means deleting the placed hook and re-placing it. That makes it a destructive **HAND-APPLY** (`rm` + `--apply`, absolute path so it can only delete this project's hook), never something the consent flow runs for you. When the read-lane is also enabled, this arm and `read-lane.stale` would report the same file with the same recovery, so exactly one renders — **this one**, because its cause is the true one: a hook that postdates the read-lane and merely predates the marker key reads `lanes.json` perfectly well, and the read-lane arm's wording would be false over it. Risk profile: deleting one placed hook file, then re-placing it from the bundle; the declaration is never touched.
 - `mcp-channel` — the offer is to REGISTER the kit's read-only stdio MCP server in this project, which is a different kind of consent from the other velocity items: a registration is a command your MCP client will RUN, so the apply here is the mode's own **flagless preview**, which prints the exact entry and writes nothing — the `--apply` that follows is a SEPARATE step you run after reading that entry, and the consent flow never carries it. What the registration buys: path questions and literal searches become typed tool calls whose arguments are named JSON fields instead of a string handed to a shell, so a pipe, a redirect or a quote inside a pattern or a path stays DATA and is never interpreted — they are perfectly legal bytes to search for, there is simply no shell to read them as operators. Posture: the server is a **read-only child of your client** (path/type/size/line facts and literal search over this project root; no write and no exec API), and like the client itself it runs **outside the Bash sandbox** — the sandbox is not what bounds it, the server's own root containment is. The two allow rules it adds make those two tools promptless and nothing else. Two arms are **HAND-APPLY** and never run for you: **`.differing`** — an `agent-workflow` entry already stands in `.mcp.json` and **structurally differs** from what this kit copy would write (another kit copy, a hand-edited path, an added `env`; the comparison ignores key order, so re-serialized identical bytes are the same registration), and silently changing what an MCP server launches is exactly what consent must not slide past, so the remedy is your edit; and the **masked** arm, where an OS sandbox hides `.mcp.json` behind a device node — the kit cannot write there, so it hands you the text to paste from outside the sandbox. When the file is masked but the settings half is already complete, the item **does not render at all**: what is unobservable becomes a stated SKIP, so optimality is withheld rather than a registration you already made being offered again. Stated limit: this item does **not** detect a `disabledMcpjsonServers` veto, so a converged `mcp-channel` means *what the mode writes is in place*, not *the client will load it* — see `${CLAUDE_SKILL_DIR}/references/modes/mcp.md` for why that check was subtracted rather than half-built. Risk profile: a new read-only channel your client will launch; no write or exec exposure, and no existing declaration is touched.
 - ADDITIONAL `gates-inert` arms (the third outcomes) — two further arms, and they differ in whether anything is BROKEN. **`producer-unrecognized`** — a checker with no producer anywhere in the declaration, on a tracked tree the changed-line coverage domain cannot reach (`.ts`/`.tsx`/`.jsx`/`.mts`/`.cts` strictly outnumber `.mjs`/`.cjs`/`.js`): the dead pair is real, so this arm is **HAND-APPLY** and the two remedies are marking the real producer with `"lcovProducer": true` or dropping the checker. Never a `node --test` prescription over a project that has no such suite, never the fill preview, and never an acknowledgement — a dead pair is broken, not narrow, and removing a producer after an acknowledgement lands right back in this arm. **`coverage-domain-narrow`** — the producer/checker pair IS live and the tree is still dominated by what the domain excludes: nothing is broken, and the honest sentence is that certification covers the assessable minority. Its apply is the consent-gated **ack writer** preview (a NEUTRAL fingerprint into `docs/ai/acks.json` as `coverageDomainAck`, never a security key); after the SAME confirmation you run the `--apply` it prints. The fingerprint binds the FACT — the verdict plus the unsupported extensions present, never the file counts — so an acknowledged project stays quiet as it grows and re-fires when a new unsupported language arrives or the verdict flips. The census reads the TRACKED tree with a read-only `git ls-files`; a tree it cannot read (a non-git deployment) becomes a stated skip, so optimality is withheld rather than assumed. Risk profile: no enforcement change of any kind — one acknowledgement recorded in a family-owned file, and one hand edit that stays the maintainer's.
+- `spec-adoption` — the feature-spec layer's ADOPTION STATE, judged from `docs/ai/specs/` alone through the same census `spec-check --all` runs, so a store the checker would refuse to observe is never counted here either. Both arms are OFFERS (`optional`) — the layer is opt-in, and `attention` stays reserved for a configured declaration that is broken. **`not-adopted`** (no store): every plan then cites zero governing specs by default and nothing says adoption never started; its apply is the spec-layer ensure one-liner (`ensure-configs --reconcile --only specs`, the same seed `upgrade` runs — it writes the reader/checker pairs and the store root, create-only, and skips with a stated reason where no Node evidence exists), and its `recipe:` line carries a NAMED **HAND-APPLY alternative** — the DECLINE preview (`ack-write --lane spec-adoption`, a dry-run that prints the exact `--apply`), which records `specAdoptionAck` in the family-owned `docs/ai/acks.json`. **The two are exclusive, and the order is part of the contract:** ask which the maintainer wants BEFORE the confirmation; on "seed" run the apply; on "decline" run NOTHING — hand over the preview line and let them run it and its printed `--apply`; never run the seed after a decline was chosen, and never run the decline preview for them. **`adopting`** (a store with no live contract): an optional item naming the draft count; its apply is that same decline preview (a dry-run; after the SAME confirmation you run the `--apply` it prints), and the honest remedy is authoring a contract from the skill's `SPEC_TEMPLATE.md`. A recorded decline silences BOTH arms and shows on `status` as ` — declined`; one live contract makes the decline moot. An unreadable store is a stated skip, never `flow optimal`. Risk profile: the seed writes only create-only files under `scripts/` and `docs/ai/specs/`; the decline writes one key into the ack store; nothing here authors a spec or blocks a plan.
 - `adr-store-migration` — other items write project files too; what is unique here is that the crossing **overwrites and deletes files the project already has**: it replaces the deployed enforcement scripts in `scripts/` (the directional subset — only basenames the project already has; a locally-edited copy is snapshotted first, never silently clobbered) and, where a retired archive file exists, DELETES it once conservation has been proven. That is why it is **HAND-APPLY** and why the command shown in the apply slot is a **`--dry-run`** — it writes nothing and prints the whole plan. `--apply` is a SEPARATE step, run only after that plan has been shown and **fresh consent** obtained for it; the consent flow executes only the apply slot, so an item that needs consent AFTER its preview cannot use that lane at all. Every write is idempotent and the run is re-runnable to completion after any interruption, so a re-run repairs rather than double-applies. It never commits. Risk profile: overwrite + delete of existing project files, gated on a preview you have actually read.
 
 **Sandbox lanes (what to DO with the `sandbox-lane` recipe, per host class):**

package/references/modes/set-recipe.md

@@ -7,20 +7,37 @@ The **config writer** for `docs/ai/orchestration.json` — the answer to *"set m
 
 **Map the user's plain language → explicit ops** (the kit ships no NL parser; it performs no `all`-magic, so you expand scope explicitly, asking when unclear):
 
-The intents are listed in English; a user speaking any other language expresses the same four, and
+The intents are listed in English; a user speaking any other language expresses the same ones, and
 mapping their wording onto them is your job, not a shipped phrase list.
 
 | user means | op | scope |
 |---|---|---|
 | "both review" | `--set <activity>.review=council` | **disambiguate**: which activity? If both, pass `--set plan-authoring.review=council --set plan-execution.review=council`. |
 | "one reviewer" | `--set <activity>.review=reviewed` | per the named activity, else ask |
-| "delegate execution" | `--set plan-execution.execute=delegated` | execution only |
+| "delegate execution" | `--set plan-execution.execute=delegated` | execution only (a **bridge** runs the change) |
+| "let a subagent do it" | `--set <activity>.<slot>=subagent` | **disambiguate**: which work? `--set plan-execution.execute=subagent` (a slice of the change), `--set plan-authoring.author=subagent` (a plan/contract brief), `--set routine.carrier=subagent` (a bounded chore) |
+| "one slice at a time" | `--set routine.parallel=off` | `routine` only — `parallel` is a **flag**, not a recipe |
 | "revert / do it myself" | `--unset <activity>.<slot>` | the named slot → its computed default |
 
-Run **`node ${CLAUDE_SKILL_DIR}/tools/set-recipe.mjs [--set <activity>.<slot>=<recipe>]… [--unset <activity>.<slot>]… [--write] [--json]`**:
+Run **`node ${CLAUDE_SKILL_DIR}/tools/set-recipe.mjs [--set <activity>.<slot>=<value>]… [--unset <activity>.<slot>]… [--write] [--json]`**:
 
-1. **Grammar — always fully-qualified `<activity>.<slot>`** (the kit never guesses the activity; a bare `review=council` is rejected). `review` accepts `solo|reviewed|council`; `execute` accepts `solo|delegated`. Activities/slots: `plan-authoring.review`, `plan-execution.execute`, `plan-execution.review`.
-2. **Preview by default** — prints `current → proposed` for the **changed** slots only, plus the **effective recipe resolved against live backend readiness** (degradation stated honestly, e.g. *council requested, 1 ready reviewer → runs reviewed until a 2nd backend is ready*). It writes **nothing**. Re-run with **`--write`** to apply (same effective/degradation note — a direct `--write` is never quieter than the preview). `--unset` returns a slot to its computed default (reverting needs no hand-edit either). A no-op `--set` (slot already equals) writes nothing and never re-seeds the onboarding note.
+1. **Grammar — always fully-qualified `<activity>.<slot>`** (the kit never guesses the activity; a bare `review=council` is rejected). The writer takes **every slot of the three activities**, and `--help` prints the registry (`tools/carriers.mjs`) as two blocks:
+
+   ```
+   Activities and their slots:
+     plan-authoring → author, review
+     plan-execution → execute, review
+     routine → carrier, parallel
+
+   Accepted values per slot type:
+     review slots accept solo | reviewed | council
+     execute slots accept solo | delegated | subagent
+     carrier slots accept solo | subagent
+     switch slots accept on | off
+   ```
+
+   `parallel` is a **flag**, not a recipe: it resolves outside the recipe lattice and is never degraded. Examples: `--set routine.carrier=subagent`, `--set routine.parallel=off`, `--set plan-authoring.author=subagent`. A value outside its slot's list is a **usage** error (`2`) naming the accepted values, never a coercion to a neighbour.
+2. **Preview by default** — prints `current → proposed` for the **changed** slots only, plus the **effective recipe resolved against live carrier readiness** (degradation stated honestly, e.g. *council requested, 1 ready reviewer → runs reviewed until a 2nd backend is ready*; *subagent requested, the executor vehicle is `missing` → runs solo until the vehicle is placed, naming the apply command*). A `parallel` value is reported as requested — a flag has nothing to degrade against. It writes **nothing**. Re-run with **`--write`** to apply (same effective/degradation note — a direct `--write` is never quieter than the preview). `--unset` returns a slot to its computed default (reverting needs no hand-edit either). A no-op `--set` (slot already equals) writes nothing and never re-seeds the onboarding note.
 3. **`--write`** applies via a hardened, atomic write (deployment-gated — refuses to scatter a config into a repo with no `docs/ai`; exclusive-create temp + rename; symlink/TOCTOU-safe; last-writer-wins). It preserves the onboarding note + every untouched slot, normalizing to canonical 2-space JSON.
    **Standing-consent advisory (after a successful `--write` only, and only when the written config names a `reviewed`/`council` recipe — a solo recipe gets NO advisory):** advise the ONE-TIME **hand-adds** to the maintainer's `.claude/settings.local.json` — `Bash(codex-review:*)` + `Bash(agy-review:*)` + `Bash(node <skill-dir>/tools/grounding.mjs:*)`, with the path your project actually reaches the kit by. State plainly: (a) auto-approving a review wrapper **spends subscription quota without a per-run prompt** — that is exactly what standing consent means here, so it is the maintainer's call; (b) the kit **never writes that file** — these stay hand-adds; (c) `grounding.mjs --out` writes ONE scratch facts file — that write is what the standing consent covers; (d) the entry must match the invocation **byte-form your project actually uses, INCLUDING quoting** — the procedures advisor renders a QUOTED skill path, and a hand-add covering it must use the same spelling (a mismatched spelling is a dead rule that simply prompts).
 4. **Exit codes:** `0` success (an explicit recipe that gracefully degrades is still `0`); `2` usage (a bare/duplicate op, or `--write` with no ops); `1` config error (malformed/unreadable config — the file is left **untouched**, never clobbered) or a write STOP (no deployment / a symlinked config). A `1`/`2` failure is loud; on a malformed config, offer to show the parse error so you can help the user fix the JSON.

package/references/modes/status.md

@@ -11,12 +11,12 @@ Run `node ${CLAUDE_SKILL_DIR}/tools/family-registry.mjs --json [--dir <project>]
 1. **Versions — a status-only render from `installed[]` + `deploymentHead`** (this is **NOT** the shared notes-based version block — see the separation note below): the **`docs/ai` structure version** (named as such, never "lineage head"), then each member by its `display` showing its `version` (or, when there is no version, the plain phrase for its `state`, mapped above), plus the two-axes disambiguation. **Freshness comes from `installed[].refresh`, not from `notes`:** for each member whose **`refresh.behind`** is `true`, show a **localized "needs refresh"** label and the **verbatim `refresh.recommend`** command **exactly once** (the command/package name stays source-language; **do not also paste the English `notes` caveats** — `refresh.recommend` is the single source of the recovery step, so the command is never duplicated on this surface). A member whose **`refresh.freshness`** is **`unknown`** is surfaced too — a localized *"couldn't be checked"* label; it is **never counted as current and never as behind** (its `notes` caveat carries the detail on the notes-based surfaces; here the label is enough). Lead with a one-line **headline count** derived from `installed[].state` + `refresh.behind` + `refresh.freshness` (e.g. *"5 members installed · 1 needs a refresh · 1 couldn't be checked"* — omit a zero count).
 
 > **Status reads `refresh`; the shared version block + the bootstrap/upgrade footers stay `notes`-based (unchanged this release).** `${CLAUDE_SKILL_DIR}/references/modes/status.md` has its OWN status-only render (above), keyed on `installed[].refresh.behind` / `refresh.recommend`. The shared **version block** (under *The version block + welcome mat* in `${CLAUDE_SKILL_DIR}/references/shared/report-footer.md`) and the bootstrap (step 11) + every upgrade (steps 4 / 8) report footer still consume `installed[].notes` verbatim — that wiring is deliberately **untouched** here (their migration onto `refresh` is deferred). Do not rewrite those footers onto `refresh`.
-2. **Deployment (`--dir`)** (from `project`): whether `docs/ai/` is deployed + the deploy stamps by `display`; and **visibility** — render `project.visibility.state` in **user-safe words only**: *visible (tracked)* / *hidden (git-ignored, local-only)* / *unclear (uncommitted or partially set up)* — **never** the words "hidden fence" or any marker term. A `visibility.error` → surface it plainly. When `project.adrLayout` is **`old`** or **`old-unrotated`**, add a plain-language note that the project still uses an **older ADR layout** and should run the opt-in **`/agent-workflow-kit migrate-adr-store`** to move to the one-file-per-ADR store (preview first; it never commits) — the note is the SAME for both, they differ only in how the older layout was detected (`old` = a retired archive file is still on disk; `old-unrotated` = the project's deployed rotation script predates the store); `migrated` / `none` need no note.
+2. **Deployment (`--dir`)** (from `project`): whether `docs/ai/` is deployed + the deploy stamps by `display`; and **visibility** — render `project.visibility.state` in **user-safe words only**: *visible (tracked)* / *hidden (git-ignored, local-only)* / *unclear (uncommitted or partially set up)* — **never** the words "hidden fence" or any marker term. A `visibility.error` → surface it plainly. When `project.adrLayout` is **`old`** or **`old-unrotated`**, add a plain-language note that the project still uses an **older ADR layout** and should run the opt-in **`/agent-workflow-kit migrate-adr-store`** to move to the one-file-per-ADR store (preview first; it never commits) — the note is the SAME for both, they differ only in how the older layout was detected (`old` = a retired archive file is still on disk; `old-unrotated` = the project's deployed rotation script predates the store); `migrated` / `none` need no note. Then **one `specs` line, always** (from `project.specs` — the feature-spec layer's adoption state, judged from the store alone): `not adopted` (no `docs/ai/specs/` — the layer was never seeded), `adopting (N draft)` (a store with no live contract yet), `adopted (N live, M draft)`, or `could not be read — <reason>` (the store or a document in it could not be observed; never counted as any of the other three). A recorded decline (`project.specs.declined`) appends ` — declined` to the first two. The internal tokens are `not-adopted` / `adopting` / `adopted` / `unreadable`; render the plain phrases above, never the tokens. An envelope without the field says the installed kit predates it — say so rather than inventing a state.
 3. **Settings (`--dir`, one line each)** (from `project.settings`):
-   - **recipes** — the effective recipe per slot (detail → `/agent-workflow-kit procedures` / `recipes`); a `recipes.detectError` → say the backends couldn't be checked, so recipes floored at solo.
+   - **recipes** — the effective recipe per slot, **one line per slot** over the three activities (`plan-authoring.author` / `.review`, `plan-execution.execute` / `.review`, `routine.carrier` / `.parallel`); each line also carries **where the value came from** (`source` — the project's config, an explicit override, or a computed default) and, when the resolved recipe is not the one that was asked for, **what it degraded from** (`degradedFrom`). Say both in plain words (never the field names): an effective recipe alone cannot tell a deliberate choice from a default, nor a degrade from a config that really names the resolved recipe — and a slot showing `solo` after a degrade from `subagent` is exactly the case the **subagents** line below explains. Detail → `/agent-workflow-kit procedures` / `recipes`; a `recipes.detectError` → say the backends couldn't be checked, so bridge-backed recipes floored at solo; the executor vehicle is unaffected.
    - **attribution** — `includeCoAuthoredBy` effective; call out a **local override** only when `local` is non-null **and** differs from `project` (a `null` `local` means the key is absent there, so the project value stands — that is not an override).
    - **velocity** — the effective `permissions.defaultMode` + whether an allowlist is seeded (detail → `/agent-workflow-kit velocity`).
-   - **subagents** — how many of the kit's read-only subagent vehicles are placed (`agents.placed` of `agents.bundled`; zero placed → the optional `/agent-workflow-kit agents` opt-in). None of them grants a shell; three ride a cheap model for mechanical work and one is a read-only review lens.
+   - **subagents** — how many of the kit's subagent vehicles are placed (`agents.placed` of `agents.bundled`; zero placed → the optional `/agent-workflow-kit agents` opt-in), then the **split the line always states separately**: the **read-only vehicles** (`agents.readOnly` — four; none of them grants a shell, three ride a cheap model for mechanical work and one is a read-only review lens) and the **ONE full-tool `executor`**, whose own state is `agents.executor`: *placed* / *customized* (both dispatchable) / *unusable* (`agents.executorReason` carries the reason — say it) / *missing*. That state is what decides whether a slot configured `subagent` can ride it: on **unusable** or **missing** every such slot runs solo instead, so surface it plainly beside the recipes lines and point at `/agent-workflow-kit agents` to place it. It is a claim about the FILE, never about the host. An envelope with no executor state says the installed kit predates the field — say so rather than inventing a state.
    - **gate hook** — wired / hook file placed / declaration present, plus **`hook.declaredGates`** (0 = absent or an empty list; `null` = present but unreadable → say *couldn't be counted*, never a number; detail → `/agent-workflow-kit hook` and the gates guide).
    - **bridge knobs** — a settings entry carrying **`retired`** is a key that is CONFIGURED but arms nothing: say so plainly (the reason is in the field) and point at `bridge-settings --unset <KEY> --apply` to clear it. Never render a retired key as an active setting.
    - Any area's **`error`** field → surface it **loudly** in plain language; the rest of `status` still renders (never a crash).