@zalom/plastic 1.8.0 → 1.10.0

package/skills/conventions/references/tiers-and-dispatch.md

@@ -0,0 +1,135 @@
+# Tiers and Dispatch
+
+This chapter holds tier depth beyond the S/M/L definition, the agent-model and dispatch mechanics, and the auto-mode human reporting contract.
+
+Speed comes from two levers only: artifact content depth and agent topology. The
+same-structure invariant holds: same file set, stage order, gates, and savepoint ledger at
+every tier and in both modes.
+
+S/M collapse the topology (one thinker agent writes spec.md then plan.md plus
+checklist.md plus at least one real action file in one context, consolidated into a single
+actions/ACTION_1.md at S/M and one file per task at L; a sonnet executor implements). L
+keeps the full team.
+
+Never cut at any tier: the independent reviewer, outcome.md as truth of delivery, the
+delivery lock, worktree isolation, intent creation via skill, INDEX as status truth, the
+QMD reindex at End.
+
+Guided mode is unchanged: full-depth artifacts, the human at every gate.
+
+Every lifecycle stage has exactly one dispatchable background agent, plus the enforcer that
+orchestrates them: see PLASTIC.md's Agent Models and Dispatch table for the stage-to-agent
+mapping (What, Why, How, Exec, Done).
+
+Final-gate code review stays an ad-hoc subagent the enforcer dispatches at the final gate, not
+a standing role.
+
+**The advisor: two consultation agents, never injected (intent 185).** Neither is a stage
+role: never in PLASTIC.md's Agent Models and Dispatch table, never dispatched by the auto
+pipeline, and neither ever touches a user's own session. `plastic-advisor` is the real advisor, ships `model: fable`,
+expensive, billed through usage credits. `plastic-faux-advisor` is the imitation advisor, ships
+`model: opus`, an ordinary model carrying the Operating Manual's reasoning discipline inlined
+in its own body (not injected into anything), so it reasons the same disciplined way at a
+fraction of the cost. The `plastic-agent-advisor` skill is the one front door: it teaches when
+consulting is worth the money (from the Advisor Protocol: buy one-way doors, plans, adversarial
+review, deadlocks, ranking; never buy what a tool can answer, code volume, or confirmation of a
+decision already made), routes to the configured agent, and can set the config on request. The
+user or the main session states a TIER (S, M, or L) and an EFFORT line in the brief; shipped
+effort is `xhigh` for `plastic-advisor` and `max` for `plastic-faux-advisor`.
+
+Config is harness-scoped, keys matching `InstallerCore::DEFAULT_AGENTS` exactly (`claude`,
+`codex`, `hermes`, never `claude_code`): `advisor.enabled` (false skips installing both agents and the
+skill), `advisor.claude.default` (which agent the skill routes to; an agent NAME never a model
+name, so it can point at a locally registered agent, and the only advisor routing key the
+installer writes). Each agent's actual model is a plain `agents.models.claude.<name>`
+override, the SAME harness-scoped mechanism every other agent uses, resolved through
+`InstallerCore#agent_model_overrides(harness:)`; there is no separate advisor-model key.
+`agents.models` is harness-scoped from this release (`agents.models.claude.*`,
+`agents.models.codex.*`), with the pre-existing flat form (`agents.models.<name>: value`)
+still honored as the claude harness and nested winning over flat. This closes a real latent
+bug: previously the same override map fed both the Claude frontmatter rewrite and the Codex
+TOML generator, so a literal Claude model id could leak into a Codex config; a model named
+under `claude` is now never emitted to `codex`. Install asks which advisor is the default
+(Claude Code only), with a plain description of each: Faux Fable (recommended, cheaper,
+available on any plan) or Fable 5 (the frontier model, billed through credits). Update asks
+the same question once when the key is unset, then never again. Claude-only for this release:
+the owner has not evaluated the Codex reasoning-model ecosystem long enough to judge it, so
+`generate_codex_agents` skips both agents by name, tracked at intent 186, not a permanent
+exclusion.
+
+**Auto-mode entry.** `plastic-auto` is the entry skill for autonomous delivery: it takes over How
+and Exec, spins up the stage-agent team named in PLASTIC.md's Agent Models and Dispatch table,
+and works the dashboard's dispatchable queue. The dashboard's
+`--data` output splits intents into a `dispatchable_queue` (work an agent can pick up) and
+`human_only` (intents that need a person); auto mode consumes the former.
+
+**Model contract.** Every agent in `agents/*.md` pins an explicit Claude Code model alias in
+its own frontmatter: `opus`, `sonnet`, or `haiku`. Never `inherit`, never Fable by default,
+unless an explicit `agents.models.<name>` config override names Fable for that role, in which
+case the override is honored as written. The two advisors, `plastic-advisor` and
+`plastic-faux-advisor`, are not lifecycle stage roles: the never-Fable rule governs stage
+agents only. Neither is ever dispatched by the auto pipeline; they are consultation roles
+summoned deliberately by the user or the main session, and their models are user configuration
+(fable and opus by default on Claude Code). Aliases track "latest
+per tier" so no Plastic release is required to advance a tier. The tier by role:
+`plastic-enforcer`, `plastic-brainstorming`, `plastic-planner` are `opus`;
+`plastic-spec-specialist`, `plastic-executor`, `plastic-intent-curator`,
+`plastic-future-intent-researcher`, `plastic-intent-discovery` are `sonnet`.
+
+**Config and installer mechanism.** `agents.models.<basename>` in a project's
+`<dir>/.plastic_store/config.yml` or the global `~/.plastic/config.yml` overrides one agent's
+tier. Precedence is project, then global, then the shipped default, matching every other
+`read-config` key. The installer applies the resolved override to each agent file's `model:`
+line at copy time (install, update, and repair, across every harness target). With no override
+configured, the shipped frontmatter passes through unchanged.
+
+**Dispatch-time contract.** Frontmatter is primary, and Claude Code reads it at dispatch, but
+because that read is a harness implementation detail rather than a contract Plastic controls,
+every dispatch site also resolves the target agent's model through the config chain
+(`read-config agents.models.<basename> --project <repo>`) and passes it explicitly at dispatch,
+belt-and-braces on top of the frontmatter pin.
+
+**Cross-harness portability.** The dispatch and model-tier contract above is harness-facing. The
+adapter layer that maps Plastic's hooks and model aliases onto each supported agent runtime
+(Claude, Codex, Hermes) is the cross-harness portability layer; see
+[`harness-adapters.md`](https://github.com/zalom/plastic/blob/main/docs/reference/harness-adapters.md) for the adapter contract.
+
+**Spawn preamble (intent 152).** `scripts/spawn-preamble` emits a live-state block purely from
+filesystem state: the active intent, stage, role/cycle-step, the honor instruction, and the
+report contract. When the intent's code worktree is resolvable and exists on disk, it also
+appends the worktree's absolute path plus a verbatim instruction to `cd` there directly, for
+harnesses whose `EnterWorktree` cannot discover a nested repo from a non-repo launch directory.
+Output is byte-identical when no worktree resolves.
+
+**Orchestrator advisory.** At auto-mode start, the orchestrator recommends once that the user
+run the main session on the best available thinking model (Fable, Opus, or whatever supersedes
+them). This is advisory only: it changes no behavior and blocks nothing if ignored, and it
+concerns the human's main session, never a dispatched subagent. The two advisors,
+`plastic-advisor` and `plastic-faux-advisor`, are not lifecycle stage roles: the never-Fable
+rule governs stage agents only. Neither is ever dispatched by the auto pipeline; they are
+consultation roles summoned deliberately by the user or the main session, and their models are
+user configuration (fable and opus by default on Claude Code).
+
+**`plastic-intent-discovery`.** The What-stage agent. It fires at intent activation, after the
+delivery lock is armed and before Why begins, running under that lock as the owner session (it
+does not acquire the lock itself and is not blocked by it): it reads the intent's
+`chain`/`sources` frontmatter, runs QMD-first discovery over completed predecessor work and
+related parked or future intents, and deposits findings to `resources/discovery--<slug>.md` in
+the intent directory ONLY. It never writes the intent file, `spec.md`, or any other lifecycle
+deliverable; the Why-stage `plastic-brainstorming` agent reads its deposit and enriches
+`## Context`.
+
+`savepoint.md`: a deterministic, append-only ledger of cycle-step milestones (one line per
+lifecycle boundary, newest at the bottom), written automatically by the gate hook. It is
+sugar on top of the conventions, not a source of truth: state is always derivable from
+files-on-disk, and the ledger is rebuildable. It exists so a resuming agent reads the cycle's
+succession at a glance (last line = where we are).
+
+### Auto-Mode Human Reporting (intent 92)
+
+In auto mode the orchestrator briefs the human at every lifecycle stage boundary in a fixed,
+impact-first shape (the EM-to-CTO report contract): State, then Risk, then Call. This is the
+depth at M and L; at S the briefing fires once, at How. It leads with
+what changed and why it matters, names one risk, and leaves the decision to the human. Separately,
+the `plastic-humanizer` skill cleans authored prose (specs, outcomes, READMEs, release notes) of
+AI tells and slop; it is for documents, not for every reply.

package/skills/dashboard/SKILL.md

@@ -157,7 +157,7 @@ To explain or debug a ranking or disposition, read `references/classification.md
 
 The eval is the payload + golden snapshots: run the engine against the fixture store and
 assert the `--data` payload shape/sorting/classification and the byte-identical `--json` +
-text goldens in `test/fixtures/dashboard/`. See `test/dashboard_test.rb`. Drift without an
+text goldens in [`test/fixtures/dashboard/`](https://github.com/zalom/plastic/tree/main/test/fixtures/dashboard). See [`dashboard_test.rb`](https://github.com/zalom/plastic/blob/main/test/dashboard_test.rb). Drift without an
 intentional change means the skill is broken.
 
 ## Notes

package/skills/doctor/SKILL.md

@@ -36,8 +36,9 @@ Each manifest maps a file path to its SHA256.
 
 **On failure**, the report states this guided route, in order:
 
-1. Run `plastic doctor --fix` (the Fix all / Select individually / Skip router from
-   Step 4-5 below).
+1. Offer fixes in the `/plastic-doctor` conversation (the Fix all / Select individually /
+   Skip router from Steps 4-5 below); doctor itself only reports, and each chosen repair
+   is dispatched to the maintenance tool or skill that owns it.
 2. If that does not resolve it, roll back to the last known-good version via
    `plastic-rollback` (restores from the local, append-only `versions.json` ledger of
    versions actually run).
@@ -85,6 +86,10 @@ per-project finding**; that is `--store <slug>`'s job (see above). This is what
 - When hooks aren't firing, skills aren't loading, or something seems broken
 - When the user says "check plastic", "diagnose", "what's wrong with plastic"
 
+Read `../plastic-conventions/references/gates-and-enforcement.md` for the transition-gate
+mechanics, the audited escape, and gate logging before diagnosing a stuck or misbehaving gate.
+This path resolves relative to this skill's own installed directory.
+
 ## Procedure
 
 ### Step 1: Run the diagnostic script
@@ -155,9 +160,9 @@ Use the `fix_hint` value to determine the correct action:
 | "Remove stale references from INDEX.md" | Edit INDEX.md to remove ghost references |
 | "Inject the missing required frontmatter field(s)" | Edit the intent's `{ID}--{slug}.md` frontmatter to add the missing key (e.g. `chain: []`) without touching other keys |
 | "Run: provision-project-store {slug}" | Run `provision-project-store <slug>` (or invoke the `plastic-store-provisioning` skill) to create the missing store |
-| "Re-run installer" | Run `npx -y @zalom/plastic@<channel> install --agent <agent>` (channel: -alpha->@alpha, -beta->@beta, else @latest) |
-| "Run the Plastic installer to bootstrap the store" | Run `npx -y @zalom/plastic@<channel> install --agent <agent>` (channel: -alpha->@alpha, -beta->@beta, else @latest) to restore the global store's plastic_home directory or INDEX.md |
-| "Dispatch plastic-store-curating ... revisions.md ..." | Invoke the `plastic-store-curating` (or the agent) to relocate the flagged section or ref into the intent's `revisions.md` via move-and-record (one dated, `[rule: <tag>]`-tagged entry per item), per PLASTIC.md > Structural maintenance and revisions.md. For a missing required section, restore or reproject it instead. |
+| "Re-run installer" | Run `npx -y @zalom/plastic@<channel> install --claude` (or `--codex`/`--hermes`/`--all` for that agent; channel: -alpha->@alpha, -beta->@beta, else @latest) |
+| "Run the Plastic installer to bootstrap the store" | Run `npx -y @zalom/plastic@<channel> install --claude` (or `--codex`/`--hermes`/`--all`; channel: -alpha->@alpha, -beta->@beta, else @latest) to restore the global store's plastic_home directory or INDEX.md |
+| "Dispatch plastic-store-curating ... revisions.md ..." | Invoke the `plastic-store-curating` (or the agent) to relocate the flagged section or ref into the intent's `revisions.md` via move-and-record (one dated, `[rule: <tag>]`-tagged entry per item), per plastic-conventions > references/maintenance-and-revisions.md. For a missing required section, restore or reproject it instead. |
 | "Run scripts/project-links ... PRESERVES ... --drop-unbacked-links" | Run `ruby ~/.plastic/scripts/maintenance-run --tool project-links --intent <id> --apply` for the one flagged id (never run bare `project-links` against a real store outside the rare owner-approved batch exception, D2) |
 
 For fixes the agent cannot handle automatically, explain what the user needs
@@ -165,6 +170,10 @@ to do manually. The `revisions.md` remedy is curator-applied (a move-and-record
 relocation, not a mechanical edit) and stays human-gated by the Step 4
 Fix / Select / Skip prompt.
 
+Read `../plastic-conventions/references/maintenance-and-revisions.md` for WORK versus
+MAINTENANCE, the `revisions.md` move-and-record contract, and the violation-tag catalog behind
+the `revisions.md` remedy above.
+
 ### Step 6: Verify
 
 After applying fixes, re-run the diagnostic script:
@@ -198,4 +207,4 @@ This keeps the update flow clean when nothing is wrong.
 
 ## References
 
-- Read `references/gates-stuck-detection.md` for the full gate enforcement table, bridge file pattern, and stuck detection thresholds when diagnosing gate failures or stuck agents
+- Read `references/gates-stuck-detection.md` for the full gate enforcement table, bridge file pattern, and the recorded stuck-detection signals when diagnosing gate failures or stuck agents

package/skills/doctor/references/gates-stuck-detection.md

@@ -28,11 +28,16 @@ Hard blocking — hooks exit with code 2 when gates fail.
 
 ## Stuck Detection
 
-| Condition | Threshold | Action |
-|---|---|---|
-| Consecutive gate failures | 3+ | Warning |
-| Consecutive gate failures | 5+ | Force savepoint + escalate |
-| No activity | 5+ min | Warning |
-| No activity | 10+ min | Force savepoint + escalate |
-| Context pressure | 80% | Warning |
-| Context pressure | 90% | Force savepoint |
+No automatic stuck detector ships today: no threshold fires, and nothing forces a savepoint
+or escalates on its own. What exists is recorded data, and reading it is the diagnosing
+agent's judgment:
+
+- `build.gate_failures` in the bridge file: `scripts/hook-gate-check` increments it on every
+  blocked write and resets it to 0 on a passing one. Nothing reads the counter back; a high
+  value is a signal for you, not a trigger for the system.
+- `build.last_activity` in the bridge file: updated on passing writes. There are no
+  inactivity timers, and context pressure is not tracked anywhere.
+
+When diagnosing, treat repeated denies of the same gate with no station progress (compare
+the savepoint ledger) as stuck: stop, read the deny reason, and route through the resolving
+command it names.

package/skills/doctor/report.md

@@ -97,4 +97,4 @@ Checked at: {{timestamp}}
   FOOTER -- always include this line exactly as written.
   ===================================================================== -->
 
-Run `plastic doctor --fix` to auto-fix all fixable issues, or ask me to fix them now.
+Doctor only reports; it never fixes anything itself. Ask me to fix these issues and I will offer Fix all / Select individually / Skip, then route each chosen repair through the tool that owns it.

package/skills/install/SKILL.md

@@ -187,7 +187,7 @@ Version:  none -> <installed>
 Doctor:   <summary or "all clear">
 ```
 
-Then: "Read `docs/guides/your-first-intent-in-10-minutes.md` for your first intent, start to finish."
+Then: "Read [`your-first-intent-in-10-minutes.md`](https://github.com/zalom/plastic/blob/main/docs/guides/your-first-intent-in-10-minutes.md) for your first intent, start to finish."
 
 ### Local Install (testing/legacy)
 

package/skills/intent-brainstorming/SKILL.md

@@ -8,8 +8,6 @@ user-invocable: true
 
 Help turn ideas into fully formed designs through natural collaborative dialogue.
 
-Announce: "I'm using the brainstorming skill to explore the design for intent {id}: {name}."
-
 Start by understanding the current project context, then ask questions one at a time, in prose, to refine the idea. Once you understand what you're building, present the design and collect the owner's rulings on it. This skill's product is the enriched Why, not spec.md.
 
 <HARD-GATE>
@@ -106,6 +104,10 @@ Do not author spec.md here.
 - **Produces:** the enriched Why (`## Context`, `### Decisions`, one `## Insights` entry per ruling).
 - **Next:** /plastic-intent-speccing consolidates the enriched Why into spec.md.
 
+Read `../plastic-conventions/references/lifecycle-and-savepoints.md` for the subagent
+report-home contract this handoff relies on. This path resolves relative to this skill's own
+installed directory.
+
 ## Key Principles
 
 - **One question at a time** - Don't overwhelm with multiple questions

package/skills/intent-continuing/SKILL.md

@@ -47,6 +47,10 @@ scanning the store with grep/Read run `ruby ~/.plastic/scripts/qmd-sync search "
 surface the candidate intent, then open the authoritative intent file for the hit you resume. The
 command is a no-op when QMD is absent, so fall back to the existing INDEX.md / file scan.
 
+Read `../plastic-conventions/references/lifecycle-and-savepoints.md` for the subagent
+report-home contract behind the resume below. This path resolves relative to this skill's own
+installed directory.
+
 For that intent's directory:
 
 1. **Read `savepoint.md` FIRST (intent 81).** It is a deterministic, append-only ledger

package/skills/intent-creating/SKILL.md

@@ -42,7 +42,7 @@ When creating a tactical intent in a project store:
 - **Global:** `~/.plastic/store/`
 - **Project:** `~/.plastic/projects/{slug}/store/`
 
-### 1b. Check for a Duplicate or Predecessor (QMD-first)
+### 2. Check for a Duplicate or Predecessor (QMD-first)
 
 QMD-first (when available): before scanning the store with grep/Read, run
 `ruby ~/.plastic/scripts/qmd-sync search "<terms>"` to surface candidate, prior, or duplicate
@@ -50,7 +50,7 @@ intents, then open the authoritative intent file for any hit you act on. The com
 when QMD is absent, so fall back to the existing INDEX.md / file scan. Do this before allocating
 the id so a near-duplicate can be reused and a true predecessor can be set in `--sources`.
 
-### 2. Decide Branch vs Root
+### 3. Decide Branch vs Root
 
 Decide this BEFORE scaffolding, because it sets whether you pass `--parent`.
 Having a "parent" in mind does NOT automatically mean branch. Choose by meaning:
@@ -71,8 +71,9 @@ Having a "parent" in mind does NOT automatically mean branch. Choose by meaning:
 
 When a branch intent exists because a late ruling arrived AFTER its parent was already
 completed (the owner's late-ruling rule), the parent is restored to v1 via
-`scripts/restore-intent-v1`, never by a hand-run `git checkout`/revert. See `PLASTIC.md` >
-Terminal immutability for the rule and the tool.
+`scripts/restore-intent-v1`, never by a hand-run `git checkout`/revert. See
+`plastic-conventions > references/maintenance-and-revisions.md`, WORK vs MAINTENANCE, for the
+rule and the tool.
 
 `## Links` is a DERIVED view of `sources`/`chain`. Never hand-write a `## Links` line; add the
 frontmatter edge and reproject. Links are decided by context influence (a `chain` edge has a high
@@ -80,7 +81,11 @@ bar: the candidate's context must materially help deliver this intent), not by s
 similarity score. To gather candidates with their context and record an edge, use the
 `plastic-intent-linking` skill and `scripts/link-suggest`.
 
-### 3. Determine Intent Properties
+Read `../plastic-conventions/references/knowledge-graph.md` for the full linking doctrine: the
+tiers of influence, sources versus chain, and how the `## Links` projection is derived. This path
+resolves relative to this skill's own installed directory.
+
+### 4. Determine Intent Properties
 
 Ask or infer from context:
 - **intent**: one-line description
@@ -95,11 +100,11 @@ Ask or infer from context:
 
 `chain` carries what this intent spawns AND related-but-not-spawned successors it leads to;
 it starts empty and is populated later. See
-`docs/concepts/how-plastic-sources-and-chains-intents.md` for the full model.
+[`how-plastic-sources-and-chains-intents.md`](https://github.com/zalom/plastic/blob/main/docs/concepts/how-plastic-sources-and-chains-intents.md) for the full model.
 Place the intent in `## Active` or `## Future` in INDEX.md (status is
 convention-derived, not a frontmatter field).
 
-### 4. Scaffold via new-intent (single call)
+### 5. Scaffold via new-intent (single call)
 
 Delegate id allocation, directory and file creation, the born-complete intent
 file, the sentinel placeholder lifecycle files, the reciprocal file links, and
@@ -107,7 +112,7 @@ self-validation to one `new-intent` invocation. Do NOT hand-author any of these
 files.
 
 ```bash
-"${CLAUDE_PLUGIN_ROOT}/scripts/new-intent" \
+ruby ~/.plastic/scripts/new-intent \
   --store "<STORE>" --intent "<one-line>" --slug "<slug>" \
   [--parent "<parent_id>"] [--author "<author>"] \
   [--sources "id,id"] [--tags "project-<slug>,tag"]

package/skills/intent-creating/references/lifecycle.md

@@ -73,7 +73,7 @@ State is derived from what exists, not from what's declared.
 
 1. Determine the target store: `~/.plastic/store/` for global intents (default), `~/.plastic/projects/{slug}/store/` for project intents
 2. Decide branch vs root (this sets whether you pass `--parent`)
-3. Scaffold with one call: `"${CLAUDE_PLUGIN_ROOT}/scripts/new-intent" --store <store> --intent "<one-line>" --slug <slug> [--parent <id>] [--sources id,id] [--tags ...]`. This allocates the id, creates the directory plus `actions/` and `resources/`, renders the born-complete intent file (frontmatter plus `## Intent`, `## Context`, `## Outcome`, `## Insights`, `## Links`), writes the sentinel placeholder lifecycle files, wires the reciprocal links, and self-validates.
+3. Scaffold with one call: `ruby ~/.plastic/scripts/new-intent --store <store> --intent "<one-line>" --slug <slug> [--parent <id>] [--sources id,id] [--tags ...]`. This allocates the id, creates the directory plus `actions/` and `resources/`, renders the born-complete intent file (frontmatter plus `## Intent`, `## Context`, `## Outcome`, `## Insights`, `## Links`), writes the sentinel placeholder lifecycle files, wires the reciprocal links, and self-validates.
 4. Update the appropriate `INDEX.md` — add to Active section and appropriate cluster
 
 The intent file is born complete with all five sanctioned `##` sections; the lifecycle files (`spec.md`/`plan.md`/`checklist.md`/`outcome.md`) are sentinel placeholders that read as "stage not reached" until an agent fills them and deletes the `<!-- plastic:placeholder -->` first line.

package/skills/intent-discovering/SKILL.md

@@ -11,8 +11,6 @@ user-invocable: false
 
 # Intent Discovery — What-stage context deposit
 
-Announce: "Discovering context for intent [ID] — [name]."
-
 Runs once, at intent activation, after the lock is armed and before Why. It gathers what is
 already known so Why does not start cold, and deposits it as a resource the
 Why-stage brainstorming agent reads.
@@ -21,9 +19,18 @@ Why-stage brainstorming agent reads.
 Inside `plastic-intent-starting`, right after the bridge is armed, under the
 lock. Dispatched as the `plastic-intent-discovery` background agent.
 
+**Precondition for skipping: a size of S already on record, and no graph edges.** Read the
+activating intent's `chain` and `sources` frontmatter fields first. When a `Tier: S` line is
+already stamped at the top of `spec.md` AND both fields are empty, the pass does not run:
+write the single line `no chain/sources, discovery skipped` to
+`resources/discovery--<slug>.md` and stop there. Sizing happens at Why, which is after this
+stage, so a first activation usually has no size yet and the full pass runs. Never guess a
+size to unlock the skip. At M or L, or when either field is filled, run the full pass below.
+
 ## What it does
 1. **Read the intent's links.** Load the activating intent file's `chain` and
-   `sources` frontmatter fields.
+   `sources` frontmatter fields. If both are empty and a size of S is already on record, apply
+   the skip above and stop.
 2. **QMD-first discovery.** Search the Plastic stores with
    `scripts/qmd-sync search "<terms>"` (or the `qmd` skill), scoped to the
    relevant `plastic-*` collections, across completed predecessor work named in

package/skills/intent-ending/SKILL.md

@@ -15,6 +15,10 @@ curator path, and releasing all call this skill (or its backing script,
 prose three times. `abandoned` is the SAME procedure as `delivered`, not a
 failure branch: only outcome.md content and the INDEX section differ.
 
+Read `../plastic-conventions/references/completion-and-done.md` for what "intent done" means and
+the End-stage tail behind the steps below. This path resolves relative to this skill's own
+installed directory.
+
 ## The 8 steps (0-7)
 
 | # | Step | Who does it |
@@ -58,8 +62,8 @@ for orchestrator-owned or completion-tracking items.
    `## Links` projection). On a refusal, fix via the OWNING tool, never a
    hand edit of the check's own output:
    - checklist/outcome content - finish it yourself, the same as before.
-   - links projection - `scripts/project-links --intent <id> --apply` via
-     `maintenance-run`.
+   - links projection - run
+     `ruby ~/.plastic/scripts/maintenance-run --tool project-links --intent <id> --apply`.
    - a savepoint issue - advisory only (WARN, never blocks): run
      `plastic-intent-savepoint` to rebuild via `Bridge.rebuild_savepoint` if
      you want it clean, but it never refuses the close on its own.
@@ -167,8 +171,9 @@ historical record of what was planned.
 
 ## Routing
 
-`plastic-releasing`, `plastic-auto`, the curator agent, `store-curating`, and
-`store-indexing` all delegate their mechanical close to this skill (or call
-`scripts/end-intent` directly for steps 1-5). None of them restate the
-outcome/INDEX/savepoint/disarm prose inline any more; if you find one that
-does, that surface has drifted and should route here instead.
+`plastic-releasing`, `plastic-auto`, `plastic-intent-executing`, the curator
+agent, `store-curating`, and `store-indexing` all delegate their mechanical
+close to this skill (or call `scripts/end-intent` directly for steps 1-5).
+None of them restate the outcome/INDEX/savepoint/disarm prose inline any
+more; if you find one that does, that surface has drifted and should route
+here instead.

package/skills/intent-executing/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: plastic-intent-executing
-description: Use when you have a written implementation plan to execute. Default mode is subagent-driven (dispatches fresh subagent per task with two-stage review). Fallback mode is inline execution for environments without subagent support. If superpowers:subagent-driven-development or superpowers:executing-plans are available, delegates to them.
+description: Use when you have a written implementation plan to execute. Default mode is subagent-driven (at L a fresh subagent per task with two-stage review, at S and M one executor dispatch for the whole consolidated action). Fallback mode is inline execution for environments without subagent support. If superpowers:subagent-driven-development or superpowers:executing-plans are available, delegates to them.
 user-invocable: true
 ---
 
@@ -8,9 +8,7 @@ user-invocable: true
 
 ## Overview
 
-Load plan from the active intent's `plan.md`, execute all tasks, review between tasks, report when complete.
-
-**Announce at start:** "I'm using the executing-plan skill to implement this plan."
+Load plan from the active intent's `plan.md`, execute all tasks, review per the tier gate below, report when complete.
 
 ## Step 0: Sync Worktree First
 
@@ -25,6 +23,10 @@ After syncing, verify the plan's target files exist at the paths plan.md names.
 If a named file or directory is missing (renamed or removed upstream), stop and
 report it rather than editing a stale path.
 
+Read `../plastic-conventions/references/locks-and-worktrees.md` for delivery isolation: the
+single-owner lock, claims, worktrees, solo mode, and the station ledger, before touching the
+worktree above. This path resolves relative to this skill's own installed directory.
+
 ## Mode Selection
 
 ### Check for superpowers first
@@ -38,7 +40,12 @@ If `superpowers:subagent-driven-development` is available as a skill, delegate t
 - Superpowers skills respect "user preferences for plan/spec location"; Plastic IS that preference
 
 ### Subagent-Driven (Default)
-Dispatches a fresh subagent per task. Controller never implements, only dispatches, reviews, and tracks progress. Two-stage review after each task: spec compliance first, then code quality.
+Dispatches subagents to do the work. The controller never implements. It dispatches, reviews, and tracks progress. How many dispatches it makes depends on the tier stamped at the top of `spec.md` (the `Tier:` line, the single authoritative record). `plan.md` carries a bold `**Tier:**` field copied from it, a convenience only:
+
+- **S or M:** one executor dispatch implements the whole consolidated action from `plan.md` plus `checklist.md` in one pass. There is no per-task implementer-then-two-reviewers loop.
+- **L:** a fresh subagent per task, and a two-stage review after each task: spec compliance first, then code quality.
+
+The final independent review in Step 3 runs at every tier. It is a separate agent with fresh context, and it is never the maker.
 
 ### Inline (Fallback)
 Executes tasks sequentially in the current session. Use when subagents aren't available or user explicitly requests inline mode.
@@ -55,6 +62,19 @@ Run Step 0 (Sync Worktree First) before this step.
 
 ### Step 2: Execute Each Task
 
+Read the `Tier:` line stamped at the top of `spec.md` first (the authority), then follow the matching branch. `plan.md`'s bold `**Tier:**` field is a convenience copy of the same value, useful when `spec.md` is not already open.
+
+#### At S or M: one executor dispatch
+
+Dispatch ONE executor subagent and give it the whole delivery: every task's full text from `plan.md` (pasted in, never a file reference), the checklist items it must tick, the project context from CLAUDE.md, and the active intent context from `{ID}--{slug}.md`. In auto mode this is the `plastic-executor` agent; elsewhere use the `implementer-prompt.md` template. The executor implements the consolidated action in order, ticks each item as it lands (see `## Tick-as-you-land`), and drives the test suite green.
+
+Read its response by code:
+- DONE or DONE_WITH_CONCERNS → proceed to Step 3. Run no per-task spec review and no per-task quality review at these tiers; Step 3's final review covers the work.
+- NEEDS_CONTEXT → provide the missing context, re-dispatch the executor.
+- BLOCKED → stop, report to the user, wait for resolution.
+
+#### At L: one subagent per task
+
 For each task sequentially (never parallel: conflict risk):
 
 **a. Dispatch implementer subagent**
@@ -81,17 +101,13 @@ Only after spec compliance passes. Reviews clean code, testing, architecture. Pa
 Follow `## Tick-as-you-land` below: move the task's checklist item to `## Completed` and add a `## Session Log` row in the same edit.
 
 ### Step 3: Final Review
-After all tasks complete, dispatch a final reviewer for the entire implementation.
+After all tasks complete, dispatch a final reviewer for the entire implementation. This runs at every tier, S, M, and L. The reviewer is a separate agent with fresh context and is never the maker. At S and M this is the only review the work gets, so if it returns changes, re-dispatch the executor to fix them, then re-review.
 
 ### Step 4: Update Intent and Complete
 Capture observations in `## Insights`. When ALL checklist items are checked:
 
-1. Write `outcome.md` with detailed results in the intent directory, using the `${CLAUDE_PLUGIN_ROOT}/templates/outcome.md` form. Set the frontmatter `disposition: delivered` (the delivered terminal). `outcome.md` is mandatory at every terminal and self-declares its disposition (canonical done-marker in PLASTIC.md).
-2. Write `## Outcome` summary in the intent file (1-2 sentences)
-3. Move intent from `## Active` to `## Completed` in INDEX.md (with today's date)
-4. Update cluster entries to show `_(completed)_`
-5. Auto-commit: `cd <store-root> && git add . && git commit -m "feat: complete intent <ID>: <name>"`
-6. QMD reindex LAST (canonical End tail). As the final End-tail step, after the terminal move and any disarm, ALWAYS refresh the QMD search index for this store (no-op when QMD is absent), running in the background so it never blocks the turn: `ruby ~/.plastic/scripts/qmd-sync reindex --store <store-root> --async`. Completion is the lifecycle event that keeps the search index fresh, and the reindex runs last so the index never references a bridge or lock that is about to disappear (see PLASTIC.md `## Delivery Isolation and the Single-Owner Lock`).
+1. Update the intent's cluster entries in `INDEX.md` to show `_(completed)_`. Do this first, so the store auto-commit in the next step picks it up. `plastic-intent-ending` does not cover cluster maintenance (`store-indexing` and `store-curating` own it), so doing it here keeps the step from being lost.
+2. Hand the mechanical close to `plastic-intent-ending`. It owns `outcome.md`, the intent file's `## Outcome` stamp, the INDEX terminal move, the savepoint `Done` line, the store auto-commit, disarm, the QMD reindex, and the EM-to-CTO owner report, as ONE delegation. Author the outcome.md content when that skill asks for it; do not restate the mechanical steps here.
 
 **This is NOT optional.** An intent with all checklist items done but no Outcome is a broken state. Complete the intent immediately, do not leave it for later.
 
@@ -113,12 +129,8 @@ For each task:
 ### Step 3: Update Intent and Complete
 Capture observations in `## Insights`. When ALL checklist items are checked:
 
-1. Write `outcome.md` with detailed results in the intent directory, using the `${CLAUDE_PLUGIN_ROOT}/templates/outcome.md` form. Set the frontmatter `disposition: delivered` (the delivered terminal). `outcome.md` is mandatory at every terminal and self-declares its disposition (canonical done-marker in PLASTIC.md).
-2. Write `## Outcome` summary in the intent file (1-2 sentences)
-3. Move intent from `## Active` to `## Completed` in INDEX.md (with today's date)
-4. Update cluster entries to show `_(completed)_`
-5. Auto-commit: `cd <store-root> && git add . && git commit -m "feat: complete intent <ID>: <name>"`
-6. QMD reindex LAST (canonical End tail). As the final End-tail step, after the terminal move and any disarm, ALWAYS refresh the QMD search index for this store (no-op when QMD is absent), running in the background so it never blocks the turn: `ruby ~/.plastic/scripts/qmd-sync reindex --store <store-root> --async`. Completion is the lifecycle event that keeps the search index fresh, and the reindex runs last so the index never references a bridge or lock that is about to disappear (see PLASTIC.md `## Delivery Isolation and the Single-Owner Lock`).
+1. Update the intent's cluster entries in `INDEX.md` to show `_(completed)_`. Do this first, so the store auto-commit in the next step picks it up. `plastic-intent-ending` does not cover cluster maintenance (`store-indexing` and `store-curating` own it), so doing it here keeps the step from being lost.
+2. Hand the mechanical close to `plastic-intent-ending`. It owns `outcome.md`, the intent file's `## Outcome` stamp, the INDEX terminal move, the savepoint `Done` line, the store auto-commit, disarm, the QMD reindex, and the EM-to-CTO owner report, as ONE delegation. Author the outcome.md content when that skill asks for it; do not restate the mechanical steps here.
 
 **This is NOT optional.** Complete the intent immediately when work is done.
 
@@ -138,6 +150,9 @@ the changed file, the installed output) rather than restating the intended
 change. Never present an unverified claim to the owner. If verification
 fails, fix it before the gate, not after.
 
+Read `../plastic-conventions/references/gates-and-enforcement.md` for the transition-gate
+mechanics, the audited escape, and gate logging behind every owner gate named here.
+
 ## Methods report (audits and sweeps)
 
 When the work is an audit or a sweep (checking many files or many instances of
@@ -164,7 +179,10 @@ persisting each ruling with `--stage Exec`.
 
 - **Before:** `plan.md` and `checklist.md` exist; the worktree is armed.
 - **Produces:** code changes, a ticked checklist, and (for audits or sweeps) a methods report in `resources/`.
-- **Next:** intent-ending owns `outcome.md` (see intent 161). This skill's own Update-Intent-and-Complete step above is unchanged by this note.
+- **Next:** `plastic-intent-ending` owns `outcome.md` and the rest of the mechanical close (see intent 161). The Update-Intent-and-Complete step above hands off to it.
+
+Read `../plastic-conventions/references/lifecycle-and-savepoints.md` for the subagent
+report-home contract this handoff relies on.
 
 ## Model Selection for Subagents
 

package/skills/intent-grilling/SKILL.md

@@ -53,20 +53,22 @@ This process is thorough. It typically takes 20-45 minutes for a complex design.
 
 > "We've covered [areas]. Still to explore: [areas]. Continue, or pause and capture what we have?"
 
-If the user wants to pause, capture all decisions made so far into the active intent's spec.md.
+If the user wants to pause, capture all decisions made so far into the active intent's `## Context` / `### Decisions`, ready for /plastic-intent-speccing to consolidate later.
 
 ### 5. Close Out
 
 When all branches are resolved:
 
-1. Write the complete spec to the active intent directory (`spec.md`)
+1. Record every ruling in the active intent's `## Context` / `### Decisions`, then hand off
+   to /plastic-intent-speccing to consolidate them into `spec.md` (that skill owns
+   `spec.md` exclusively)
 2. List all decisions made
 3. List any deferred items (things the user explicitly chose to decide later)
 4. Proceed to Autonomous Handoff Offer (step 6)
 
 ### 6. Autonomous Handoff Offer
 
-After closing out (spec written, decisions listed), assess whether the agent has enough context to deliver the intent autonomously.
+After closing out (decisions listed, spec consolidated by /plastic-intent-speccing), assess whether the agent has enough context to deliver the intent autonomously.
 
 **Self-assessment checklist:**
 - All key decisions resolved (no open "it depends" or "TBD")

package/skills/intent-linking/SKILL.md

@@ -26,6 +26,10 @@ Two distinct steps, do not conflate them:
 
 ## The three tiers (by context influence)
 
+Read `../plastic-conventions/references/knowledge-graph.md` for the full linking doctrine behind
+these tiers, the sources-versus-chain distinction, and the `## Links` projection. This path
+resolves relative to this skill's own installed directory.
+
 - **sources:** the foundational context that shaped this intent's CREATION (a split, an idea born
   during development, a merge). Earns an edge. Decided by origin, never inferred.
 - **chain:** the context that materially helps DELIVER this intent. HIGH bar: only the genuinely

package/skills/intent-locking/SKILL.md

@@ -12,6 +12,10 @@ session-keyed, liveness is a lease (the owner's hooks refresh the file mtime;
 stale means the heartbeat is older than the TTL). The /tmp bridge is only a
 cache; the lock file wins every disagreement.
 
+Read `../plastic-conventions/references/locks-and-worktrees.md` for delivery isolation in full:
+the single-owner lock, claims, worktrees, solo mode, and the station ledger behind every verb
+below. This path resolves relative to this skill's own installed directory.
+
 ## Verbs
 
 Run from the project (the intent resolves from this session's bridge), or pass