mandrel 2.65.0 → 2.67.0

package/.agents/agents/acceptance-critic.md

@@ -12,8 +12,8 @@ effort: medium
 
 <!--
   Shared common core — byte-identical across every `.agents/agents/*.md` role
-  context, ordered FIRST so all role boots share one prompt-cache prefix
-  (prompt-cache is keyed on the exact byte prefix; the role delta comes last).
+  context, ordered FIRST so every role binds the same baseline rules (the
+  roles pin different effort levels and share no cache prefix; delta last).
   Edit it in every role file at once —
   tests/bootstrap/agent-shared-prefix.test.js fails on any divergence.
   security-baseline stays inviolable and single-sourced — @-import it, never
@@ -31,9 +31,9 @@ role-delta marker below; the workflow prose your caller hands you supplies
 the step-by-step. This shared core binds every role:
 
 - **Non-interactive.** You have no input channel mid-run. Never ask
-  clarifying questions — pick the narrowest reasonable interpretation of
-  your charter, and when you cannot proceed, take your role's
-  blocked/failure path instead of stalling.
+  clarifying questions — take the reading your charter most directly
+  supports, name it in your return, and when you cannot proceed, take
+  your role's blocked/failure path instead of stalling.
 - **Absolute paths only.** Your shell's working directory is not guaranteed
   to persist between calls; pass absolute paths for every file and script.
 - **Anti-thrashing.** When the same error class recurs despite the same fix,
@@ -98,8 +98,8 @@ For each acceptance item:
 
 ## Verdict schema (MUST)
 
-Write **one** verdict file under `temp/` (e.g.
-`temp/acceptance-verdict-<storyId>-r<round>.json`) conforming to
+Write **one** verdict file under `temp/scratch/story-<storyId>/` (e.g.
+`temp/scratch/story-<storyId>/acceptance-verdict-r<round>.json`) conforming to
 [`acceptance-eval-verdict.schema.json`](../schemas/acceptance-eval-verdict.schema.json):
 one `criteria[]` record per acceptance item, in acceptance-array order, with
 `index` being the criterion's position in that array.

package/.agents/agents/auditor.md

@@ -12,8 +12,8 @@ effort: medium
 
 <!--
   Shared common core — byte-identical across every `.agents/agents/*.md` role
-  context, ordered FIRST so all role boots share one prompt-cache prefix
-  (prompt-cache is keyed on the exact byte prefix; the role delta comes last).
+  context, ordered FIRST so every role binds the same baseline rules (the
+  roles pin different effort levels and share no cache prefix; delta last).
   Edit it in every role file at once —
   tests/bootstrap/agent-shared-prefix.test.js fails on any divergence.
   security-baseline stays inviolable and single-sourced — @-import it, never
@@ -31,9 +31,9 @@ role-delta marker below; the workflow prose your caller hands you supplies
 the step-by-step. This shared core binds every role:
 
 - **Non-interactive.** You have no input channel mid-run. Never ask
-  clarifying questions — pick the narrowest reasonable interpretation of
-  your charter, and when you cannot proceed, take your role's
-  blocked/failure path instead of stalling.
+  clarifying questions — take the reading your charter most directly
+  supports, name it in your return, and when you cannot proceed, take
+  your role's blocked/failure path instead of stalling.
 - **Absolute paths only.** Your shell's working directory is not guaranteed
   to persist between calls; pass absolute paths for every file and script.
 - **Anti-thrashing.** When the same error class recurs despite the same fix,
@@ -116,13 +116,12 @@ and a surviving **Critical** halts the delivery gate:
 - **Info** — the floor: a grounded observation asking for no scheduled work
   (accepts `Informational`). Never a home for findings that fail the bar below.
 
-## Self-cross-check bar (mandatory before you write the report)
+## Self-cross-check bar
 
-You are your own adversarial reviewer. After drafting the Detailed Findings and
-**before** writing the artifact, re-open every finding and keep it only when
-**all** hold: a **grounded** `path:line` you actually read; **reproducible
-evidence** (a tool reading, a quoted snippet, or a specific standard it
-violates) — never "this looks wrong"; **in-scope** under the scope filter; and
+A finding goes in the report only when **all** hold: a **grounded**
+`path:line` you actually read; **reproducible evidence** (a tool reading, a
+quoted snippet, or a specific standard it violates) — never "this looks
+wrong"; **in-scope** under the scope filter; and
 an **actionable** recommendation. Drop anything resting on a sanctioned test
 seam, an entry point / public API surface, dynamic/framework reachability, an
 intentional documented deviation, or a formatter-governed style nit.
@@ -136,14 +135,14 @@ Beside it, carry one machine-readable tally of the findings you kept —
 included, `Info` never counted. `audit-to-stories` cross-checks that line
 against its parse and refuses a report whose tally is missing or wrong.
 
-## Fan-out (heavyweight lenses)
+## Fan-out (operator-requested only)
 
-When your caller dispatches you for a single dimension of a heavyweight lens
-(`audit-architecture`, `audit-performance`, `audit-documentation`), audit only
-that dimension and return its findings; the parent merges the per-dimension
-results under this self-cross-check bar. Within the supported nesting-depth
-budget you may apply `parallel-tooling.md` Rule 3 to your own independent
-sub-units.
+By default you audit the whole lens. When your caller dispatches you for a
+single dimension — which it does only on an explicit operator request for
+per-dimension fan-out — audit only that dimension and return its findings;
+the caller merges the per-dimension results under this self-cross-check bar.
+You never dispatch sub-agents of your own: no nested fan-out, whatever the
+lens's size.
 
 ## Return contract
 

package/.agents/agents/plan-critic.md

@@ -12,8 +12,8 @@ effort: medium
 
 <!--
   Shared common core — byte-identical across every `.agents/agents/*.md` role
-  context, ordered FIRST so all role boots share one prompt-cache prefix
-  (prompt-cache is keyed on the exact byte prefix; the role delta comes last).
+  context, ordered FIRST so every role binds the same baseline rules (the
+  roles pin different effort levels and share no cache prefix; delta last).
   Edit it in every role file at once —
   tests/bootstrap/agent-shared-prefix.test.js fails on any divergence.
   security-baseline stays inviolable and single-sourced — @-import it, never
@@ -31,9 +31,9 @@ role-delta marker below; the workflow prose your caller hands you supplies
 the step-by-step. This shared core binds every role:
 
 - **Non-interactive.** You have no input channel mid-run. Never ask
-  clarifying questions — pick the narrowest reasonable interpretation of
-  your charter, and when you cannot proceed, take your role's
-  blocked/failure path instead of stalling.
+  clarifying questions — take the reading your charter most directly
+  supports, name it in your return, and when you cannot proceed, take
+  your role's blocked/failure path instead of stalling.
 - **Absolute paths only.** Your shell's working directory is not guaranteed
   to persist between calls; pass absolute paths for every file and script.
 - **Anti-thrashing.** When the same error class recurs despite the same fix,

package/.agents/agents/story-worker.md

@@ -9,8 +9,8 @@ description: >-
 
 <!--
   Shared common core — byte-identical across every `.agents/agents/*.md` role
-  context, ordered FIRST so all role boots share one prompt-cache prefix
-  (prompt-cache is keyed on the exact byte prefix; the role delta comes last).
+  context, ordered FIRST so every role binds the same baseline rules (the
+  roles pin different effort levels and share no cache prefix; delta last).
   Edit it in every role file at once —
   tests/bootstrap/agent-shared-prefix.test.js fails on any divergence.
   security-baseline stays inviolable and single-sourced — @-import it, never
@@ -28,9 +28,9 @@ role-delta marker below; the workflow prose your caller hands you supplies
 the step-by-step. This shared core binds every role:
 
 - **Non-interactive.** You have no input channel mid-run. Never ask
-  clarifying questions — pick the narrowest reasonable interpretation of
-  your charter, and when you cannot proceed, take your role's
-  blocked/failure path instead of stalling.
+  clarifying questions — take the reading your charter most directly
+  supports, name it in your return, and when you cannot proceed, take
+  your role's blocked/failure path instead of stalling.
 - **Absolute paths only.** Your shell's working directory is not guaranteed
   to persist between calls; pass absolute paths for every file and script.
 - **Anti-thrashing.** When the same error class recurs despite the same fix,

package/.agents/docs/agentrc-reference.json

@@ -87,7 +87,8 @@
         "orchestrationLogs": true,
         "validationEvidence": true,
         "auditResults": true,
-        "planDirs": true
+        "planDirs": true,
+        "scratch": true
       }
     },
     "deliverRunner": {

package/.agents/docs/configuration.md

@@ -139,13 +139,14 @@ Everything `/mandrel-deliver` and `single-story-close` consume: worktree isolati
 | `execution.fullSuiteLock` | No | `boolean` | `true` | Serialize full-suite spawns (`npm test` / `npm run test:coverage`) behind a host-level advisory lock, so two concurrent deliveries on one checkout do not run two suites against the same cores. Best-effort: a wait that expires spawns anyway, so the lock can never fail a delivery. Set false — or export `MANDREL_FULL_SUITE_LOCK=0` for one invocation — to disable. |
 | `docsFreshness` | No | `object` | — | Documentation-freshness scope: the files a change of consequence is expected to touch. Read by the audit-documentation lens to seed its target set; no delivery gate enforces it. |
 | `docsFreshness.paths` | No | `array<string>` | `["README.md"]` | Repo-relative documentation paths the audit-documentation lens adds to its target set. |
-| `tempRetention` | No | `object` | — | Story #4794. Auto-purge of spent temp artifacts once their Story lands. Classification is an allowlist: only the declared classes below are ever deleted, so operator scratch files under tempRoot are reported with their size and left alone. signals.ndjson is never purged by any path. |
+| `tempRetention` | No | `object` | — | Story #4794. Auto-purge of spent temp artifacts once their Story lands. Classification is an allowlist: only the declared classes below are ever deleted, so unrecognized files under tempRoot are reported with their size and left alone (`/clean-temp` is the operator path for them). signals.ndjson is never purged by any path. |
 | `tempRetention.enabled` | No | `boolean` | `true` | Master switch. Default true — reclaiming a landed Story's gate transcripts and validation evidence is the behaviour, and this knob turns it off. When false every purge path is a reported no-op. |
 | `tempRetention.classes` | No | `object` | — | Per-class opt-out. Each defaults to true; set one false to keep that family while the rest are purged. |
 | `tempRetention.classes.orchestrationLogs` | No | `boolean` | `true` | <tempRoot>/orchestration/*.log — close gate transcripts and terse-result detail dumps. |
 | `tempRetention.classes.validationEvidence` | No | `boolean` | `true` | Per-Story validation-evidence.json, lifecycle.ndjson, and manifest.md under the standalone and per-run story trees. |
 | `tempRetention.classes.auditResults` | No | `boolean` | `true` | <tempRoot>/audits/ — audit lens reports. |
 | `tempRetention.classes.planDirs` | No | `boolean` | `true` | <tempRoot>/plan-<slug>/ — abandoned plan authoring dirs. Age-floored only; the current run is always excluded. |
+| `tempRetention.classes.scratch` | No | `boolean` | `true` | <tempRoot>/scratch/ — agent-authored scratch. `scratch/story-<id>/` is purged when that Story lands; any other `scratch/` entry is age-floored. |
 | `deliverRunner` | No | `object` | — | Bounded-concurrency knob for the /mandrel-deliver fan-out. |
 | `deliverRunner.concurrencyCap` | No | `integer` | `3` | Maximum ready Stories dispatched by /mandrel-deliver at once. Default 3. Moderate by design — keeps host-quota consumption predictable while allowing a small ready-set fan-out. Set 1 for strictly sequential delivery; raise further on hosts with adequate parallel-agent quota. See deliver.md for the sequencing model and throughput tradeoff. |
 | `deliverRunner.footprintGuard` | No | `"enforce"` \| `"advisory"` | `"enforce"` | How a file-footprint collision affects dispatch. 'enforce' (default, and the behaviour to keep unless you have a reason) withholds a Story whose footprint races a peer admitted this beat or one still in flight — the guard encodes delivery-time-only knowledge (open implementation windows, foreign leases, ground that moved since planning) that no depends_on edge can carry. 'advisory' still DETECTS every collision and reports each would-be withhold in the tick envelope, but lets dispatch follow the declared depends_on edges alone — a deliberate throughput trade for a run whose ordering is fully declared. See stories-wave-tick.js and helpers/deliver-reference.md. |

package/.agents/docs/execution-reference.md

@@ -72,11 +72,12 @@ and schema mechanics are in [§ Friction telemetry](#friction-telemetry) above.
 ## FinOps & token budgeting (economic guardrails)
 
 Mandrel does **not** enforce live LLM spend from response metadata. It bounds
-two things, both **fixed framework constants** rather than operator knobs, and
-both **fail closed**: the assembled `/mandrel-plan` context envelope, and plan-time
-Story sizing. Your host runtime (editor / CLI) owns session quota and hard
-stops. Consult this section when reasoning about why `/mandrel-plan` refused an
-over-ceiling envelope or an over-budget Story count.
+one thing, a **fixed framework constant** rather than an operator knob that
+**fails closed**: the assembled `/mandrel-plan` context envelope. Plan-time
+Story sizing is not bounded (retired by Story #5312). Your host runtime
+(editor / CLI) owns session quota and hard stops. Consult this section when
+reasoning about why `/mandrel-plan` refused an over-ceiling envelope, or when
+choosing the session effort and model for a command.
 
 > **There is no configurable context budget.** `planning.context.maxBytes` /
 > `summaryMode` were removed outright in Story #4541, along with the
@@ -126,3 +127,24 @@ over-ceiling envelope or an over-budget Story count.
   nothing at plan time scores its authored mass.
 - **Host runtime**: session billing, quota exhaustion, and operator overrides
   are enforced by your provider (e.g. Claude Code), not by Mandrel scripts.
+
+### Session effort and model
+
+Effort is the operator's dial, set once per session. Pick it deliberately up
+front, because changing effort mid-session invalidates the prompt cache for
+everything that follows.
+
+- **Recommended session effort.** `medium` for `/mandrel-deliver`: Stories
+  are well-scoped by construction, so delivery rarely needs more. `high` for
+  `/mandrel-plan`: a Spec defect costs a redraft or a blocked Story
+  downstream, which is dearer than the planning turn.
+- **Role agents.** `story-worker` declares no effort and inherits the
+  session's (Story #5426). The evaluator roles (`acceptance-critic`,
+  `plan-critic`, `auditor`) pin `medium`.
+- **Where pins live.** Effort and model pins belong only on role agents under
+  `.agents/agents/`, never in workflow or command frontmatter: a command that
+  pinned its own effort would change effort mid-session and break the prompt
+  cache.
+- **Escalation is an operator step.** The Agent tool takes no per-call
+  effort, so no workflow can escalate on its own. Before resuming a blocked
+  Story, raise session effort one step; raise effort before switching models.

package/.agents/docs/workflows.md

@@ -32,7 +32,7 @@ by `node .agents/scripts/generate-workflows-doc.js`; `npm run docs:check`
 fails when it drifts from the on-disk workflow set. To change a command’s
 description, edit the workflow file’s front-matter and regenerate.
 
-## Commands (29)
+## Commands (31)
 
 | Command | Description |
 | --- | --- |
@@ -55,7 +55,9 @@ description, edit the workflow file’s front-matter and regenerate.
 | `/audit-sre` | "Audit production-readiness for a release candidate: SLOs, observability, runbooks, error budgets, and rollback paths." |
 | `/audit-to-stories` | Convert findings produced by the audit-\* workflows into actionable GitHub Stories. Reads temp/audits/audit-\*-results.md, groups findings cross-audit, deduplicates against existing Issues by fingerprint, and either chains into /mandrel-plan --seed-file or opens standalone Stories. |
 | `/audit-ux-ui` | Audit UX/UI consistency and design system adherence |
-| `/git-cleanup` | Tidy the local checkout in four phases: fast-forward `main`, prune stale remote-tracking refs, sweep merged branches (squash-aware), and triage `git stash` entries — each step gated by operator confirmation. |
+| `/clean-git` | Tidy the local checkout in four phases: fast-forward `main`, prune stale remote-tracking refs, sweep merged branches (squash-aware), and triage `git stash` entries — each step gated by operator confirmation. |
+| `/clean-temp` | Clear the temp-tree backlog the land-time purge cannot attribute: sort every top-level entry under the project's tempRoot into framework, closed-issue, aged and kept buckets, preview by default, and delete only confirmed buckets. |
+| `/clean-worktrees` | Reclaim disk from dead worktrees: list every worktree of this project as a removal candidate (closed Story, merged branch, orphaned directory, detached HEAD) or as kept with a reason, then remove candidates only on `--execute`. |
 | `/git-deliver` | Single ad-hoc delivery command for working-tree changes. Detects the git setup and escalates to the right terminal step — commit only, commit + push, or commit + push + open a PR with native auto-merge — picking the default from observable state and letting flags pin any level explicitly. Replaces the retired git-commit-all, git-push, and git-pr-all trio. |
 | `/mandrel-deliver` | Unified delivery entry point. Takes Story ids or a plain-language prompt, derives which path the work belongs on, and lands it via the single deliver-story engine — story-<id> → PR → main. |
 | `/mandrel-plan` | Unified planning entry point. Interrogate → author → persist. Emits one Story by default; splits into N>1 only under the default-single split policy. |

package/.agents/instructions.md

@@ -118,7 +118,7 @@ truncates with a note naming what was cut:
 
 ## 3. Core Philosophy
 
-1. **Context First.** **Digest-first reading (Story #4433):** never
+1. **Context First.** **Digest-first reading:** never
    ingest the whole `project.docsContextFiles` set up front — read the
    docs digest and pull files on demand at the section it names. No
    digest (ad hoc task, `docsContextFiles` unset, null `docsDigestPath`)
@@ -127,8 +127,10 @@ truncates with a note naming what was cut:
    present. Always read the current Story's body (`## Spec` +
    `acceptance[]` / `verify[]`); prefer targeted retrieval over broad
    reads.
-2. **Plan First.** For non-trivial tasks (3+ steps or architectural
-   decisions), update the Story's `## Spec` via `/mandrel-plan` before code.
+2. **Plan First.** Planned work carries its plan in the Story's
+   `## Spec`, authored via `/mandrel-plan`; an unplanned prompt takes
+   `/mandrel-deliver`'s light path, which escalates to `/mandrel-plan`
+   when its gate trips.
 3. **Artifacts over Chat.** Write test/build/debug output to log
    files, not into chat.
 4. **Idempotency.** Scripts must be safe to run repeatedly.
@@ -137,16 +139,13 @@ truncates with a note naming what was cut:
 
 ## 4. Execution & Quality Discipline
 
-- **Re-Plan on Failure.** If a strategy fails, STOP and re-plan.
 - **Subagent Strategy.** Each spawn re-pays the full always-loaded
   context — a cost decision. Prefer inline search for small lookups;
   spawn only when the work justifies replicating context. One objective
   per subagent; depth compounds the cost (every nested level re-pays).
-- **Anti-Laziness / No Dead Code.** NEVER use placeholder comments like
-  `// ... existing code ...`; every edit must leave complete, runnable code.
-  Remove unused imports, commented-out code, and dead branches before
+- **No Dead Code.** Every edit leaves complete, runnable code. Remove
+  unused imports, commented-out code, and dead branches before
   finalizing.
-- **Verification.** Include explicit verification steps in every plan.
 
 ---
 
@@ -182,7 +181,8 @@ never delivered): `/mandrel-plan` offers one above 2 Stories and
 
 All temporary files, scratch scripts, and intermediate outputs MUST
 live in the gitignored workspace-root `/temp/` directory — do NOT commit
-anything under it.
+anything under it. Put ad-hoc scratch in `temp/scratch/story-<id>/` (or
+`temp/scratch/` with no Story), the layout the temp purge reaps.
 
 ---
 
@@ -191,7 +191,6 @@ anything under it.
 `/mandrel-plan` sizes each Story as a **capability slice a frontier model
 delivers and self-verifies in one pass** — a broad footprint is normal
 when the change is cohesive, and no plan-time ceiling scores it; do not
-re-slice it into per-module fragments. On an out-of-scope task: **plan
-first** in numbered cohesive sub-steps, **commit incrementally** per
-sub-step, and **fail fast** — STOP and report if any sub-step fails
-validation.
+re-slice it into per-module fragments. On an out-of-scope task,
+**commit incrementally** per cohesive sub-step, and when a sub-step
+fails validation, stop and apply § 1.I (re-plan or yield).

package/.agents/rules/ci-remediation.md

@@ -137,9 +137,9 @@ run — a blind fix to a suite nobody exercised is how the gap compounds.
 
 `capacity` and `unreproducible-tier` name failures that are proven properties
 of the **environment**: no commit on the branch can move the head SHA to clear
-them, so the no-rerun rule used to strand a correct delivery until a human
-cleared it by hand. Those two verdicts — and only those two — now buy exactly
-one rerun:
+them, so without an allowance the no-rerun rule would strand a correct
+delivery until a human cleared it by hand. Those two verdicts — and only those
+two — buy exactly one rerun:
 
 1. Reach the verdict with its required readings (§ above). A green on re-run is
    never one of those readings.

package/.agents/rules/gherkin-standards.md

@@ -143,8 +143,9 @@ authored:
    widen the regex, updating every call site in the same PR.
 4. **Add a new definition only when no reasonable match exists**, in the
    correct domain directory. Never copy-paste a step implementation to support
-   a paraphrased scenario, and never author new step definitions during
-   scenario authoring — record the missing step as a named gap instead.
+   a paraphrased scenario. A prose-only authoring pass (one whose scope
+   excludes step-definition code) records the missing step as a named gap
+   instead of writing it.
 
 When a step is superseded, mark it deprecated and migrate every call site in
 the same PR; do not leave two near-identical steps live.

package/.agents/rules/git-conventions-reference.md

@@ -15,7 +15,9 @@ Mandrel ships as the `mandrel` npm package, whose consumers pin an
 exact lockfile version; they opt into breaks at upgrade time. Operator policy
 for any contract change (config shape, baseline shape, schema, lifecycle
 payload, ticket label, dispatch artifact, public API of a script) is
-therefore:
+therefore as follows. It governs Mandrel's own framework contracts; a
+consumer's product API keeps the expand–contract rule in
+[`api-conventions.md`](api-conventions.md).
 
 1. **Hard cutovers only.** Contract changes ship as a single in-tree
    migration of every producer and consumer. There is no parallel
@@ -94,13 +96,13 @@ signature is worth naming:
 
 **Invariant (stated in the core): the delivering flow owns tidying the local
 checkout — reaping its own merged refs and fast-forwarding the base branch.
-`/git-cleanup` is a recovery tool, not a routine chore.** The outcome every
+`/clean-git` is a recovery tool, not a routine chore.** The outcome every
 delivering flow (`/mandrel-deliver`, `/git-deliver`) guarantees, with the mechanics
-owned by `boot-sweep.js` / `git-cleanup.js`:
+owned by `boot-sweep.js` / `clean-git.js`:
 
 - **`main` is fast-forwarded** by the flow itself in its cleanup phase, so the
   next init seeds from a current base. No workflow ends by telling the operator
-  to run `/git-cleanup` to catch up.
+  to run `/clean-git` to catch up.
 - **Merged local refs are reaped** at the next workflow boot's protected sweep
   (`boot-sweep.js`) — every local branch whose PR is already merged, skipping
   any candidate with unpushed work, a dirty worktree, or a still-open parent
@@ -110,9 +112,9 @@ owned by `boot-sweep.js` / `git-cleanup.js`:
   weaker content-equivalence signal (`detectedBy: 'content-merged'` — content
   already landed in the base by another route, with no merged PR or git
   ancestry of its own) is **never** reaped by the boot sweep; it is surfaced
-  under `contentMerged` for the operator to send to `/git-cleanup` for a
+  under `contentMerged` for the operator to send to `/clean-git` for a
   confirmed, eyeballed reap.
-- **`/git-cleanup` is recovery, not routine.** Run it by hand only for a state
+- **`/clean-git` is recovery, not routine.** Run it by hand only for a state
   the automated hygiene does not cover — triaging stashes, reaping across
   non-standard namespaces, or `--remote` pruning after a force-push. Reaching
   for it after every routine delivery signals the owning flow's hygiene step
@@ -154,10 +156,10 @@ different hazards:
 
 ## Meta Labels (Retrospective Signal Routing)
 
-Two `meta::*` labels route retrospective signals into durable substrates so
+Three `meta::*` labels route retrospective signals into durable substrates so
 the `/mandrel-plan` Phase 0 fetcher (see
 [`prior-feedback-fetcher.js`](../scripts/lib/feedback-loop/prior-feedback-fetcher.js))
-can surface open feedback issues to the planner. Both labels live in
+can surface open feedback issues to the planner. All three live in
 [`label-constants.js`](../scripts/lib/label-constants.js) under the
 `META_LABELS` export — reference them by symbol from scripts rather than
 hard-coding the string.
@@ -180,3 +182,10 @@ project-local automation). The work is scoped to the consumer's
 framework changes. Issues that span both axes should carry both labels —
 `fetchPriorFeedback` dedupes by issue number so a dual-labeled issue
 appears exactly once in the planner context.
+
+### `meta::platform-gap`
+
+Apply this label to a GitHub issue whose fault lies in a shared base
+config, runner fleet, or cross-repo toolchain that neither the framework
+nor the consumer owns — the `--owner platform` bucket of
+[`ci-remediation.md`](ci-remediation.md).

package/.agents/rules/git-conventions.md

@@ -16,9 +16,8 @@ Every Story lands on a dedicated **Story branch** named
 `story-<storyId>`, seeded from `project.baseBranch` (`main` by default),
 isolated in its own worktree at `.worktrees/story-<id>/`. The runtime
 owns both via `single-story-init.js`; agents commit there only. Close
-opens a PR against `main` (squash + required checks). No `epic/<id>`
-integration branch, no `--no-ff` wave merge, no child tickets: commits
-land on `story-<storyId>` directly, the
+opens a PR against `main` (squash + required checks). Commits land on
+`story-<storyId>` directly, the
 subject referencing the Story via `(refs #<storyId>)` — see
 [`.agents/instructions.md` § 5.B](../instructions.md).
 
@@ -38,15 +37,18 @@ subject referencing the Story via `(refs #<storyId>)` — see
 
 ## Push Validation & Reliability (MUSTs)
 
-1. Run the configured validation commands locally **before** `git push`.
+1. Validate locally **before** `git push`. On a Story branch that is the
+   one credited suite run (`deliver-digest.md` § 5); close runs every
+   other gate, so do not pre-run them. Elsewhere, run the configured
+   validation commands.
 2. Do NOT assume a push succeeded unless the output confirms the remote
    ref was updated (`[new branch]`, `[up to date]`, `... -> ...`).
 3. If a `pre-push` hook rejects, fix the cause and create a NEW follow-up
    commit — never amend the rejected commit.
 4. **Never bypass hooks** (`--no-verify`, `--no-gpg-sign`, …) without
-   explicit operator authorization. The one recognized exception — a
-   Biome zero-match failure under a harness-managed worktree path — is a
-   consumer-tooling gap, **not** authorization; see
+   explicit operator authorization. A Biome zero-match failure under a
+   harness-managed worktree path is a known false negative — a
+   consumer-tooling gap, **not** authorization to bypass; see
    [`git-conventions-reference.md` § Push Validation](git-conventions-reference.md).
 
 ## Local checkout hygiene
@@ -54,7 +56,7 @@ subject referencing the Story via `(refs #<storyId>)` — see
 **The delivering flow owns tidying the local checkout** — it
 fast-forwards the base branch itself and reaps its own merged refs on
 the next workflow boot (the `boot-sweep.js` protected sweep).
-`/git-cleanup` is a recovery tool, not a routine chore — never end a
+`/clean-git` is a recovery tool, not a routine chore — never end a
 workflow by telling the operator to run it. Scope rules and the
 shared-checkout contention guard:
 [`git-conventions-reference.md` § Local checkout hygiene](git-conventions-reference.md).

package/.agents/rules/testing-standards.md

@@ -156,13 +156,14 @@ behaviour (`sets status to completed`, not `works`).
 
 A file that passes alone but fails inside the full `npm test` suite is **test
 pollution** — one test leaks shared state (env vars, temp files, the
-mock-module registry, global singletons) and a later test trips on it. Reach
-for `npm run test:isolate` before manually bisecting: it runs every matching
-file individually under `--test-concurrency=1`, then all together, flags files
-that pass alone but fail in the suite (**flippers**), binary-bisects the
-smallest reproducing subset, and reports any file that exited with leftover
-`process.env` mutations. The fix is almost always missing teardown — wrap the
-mutation in a `t.before` / `t.after` pair, or restore the prior value in
+mock-module registry, global singletons) and a later test trips on it. Run
+every matching file alone, then all together; the files that pass alone but
+fail in the suite (**flippers**) bound the search, and bisecting them finds
+the smallest reproducing subset. Mandrel's own repository automates this as
+`npm run test:isolate`, which also reports leftover `process.env`
+mutations; a consumer uses its runner's equivalent. The fix is almost
+always missing teardown — wrap the mutation in a `t.before` / `t.after`
+pair, or restore the prior value in
 `try` / `finally`.
 
 For browser-based changes, pair the cycle with runtime verification via Chrome

package/.agents/runtime-deps.json

@@ -18,6 +18,6 @@
     "chokidar": "^5.0.0",
     "jscpd": "^4.0.0",
     "knip": "^6.17.1",
-    "typescript": ">=5.0.0"
+    "typescript": ">=5.0.0 <7"
   }
 }

package/.agents/schemas/agentrc.schema.json

@@ -386,7 +386,7 @@
         },
         "tempRetention": {
           "type": "object",
-          "description": "Story #4794. Auto-purge of spent temp artifacts once their Story lands. Classification is an allowlist: only the declared classes below are ever deleted, so operator scratch files under tempRoot are reported with their size and left alone. signals.ndjson is never purged by any path.",
+          "description": "Story #4794. Auto-purge of spent temp artifacts once their Story lands. Classification is an allowlist: only the declared classes below are ever deleted, so unrecognized files under tempRoot are reported with their size and left alone (`/clean-temp` is the operator path for them). signals.ndjson is never purged by any path.",
           "properties": {
             "enabled": {
               "type": "boolean",
@@ -416,6 +416,11 @@
                   "type": "boolean",
                   "description": "<tempRoot>/plan-<slug>/ — abandoned plan authoring dirs. Age-floored only; the current run is always excluded.",
                   "default": true
+                },
+                "scratch": {
+                  "type": "boolean",
+                  "description": "<tempRoot>/scratch/ — agent-authored scratch. `scratch/story-<id>/` is purged when that Story lands; any other `scratch/` entry is age-floored.",
+                  "default": true
                 }
               },
               "additionalProperties": false