@zalom/plastic 1.14.0 → 2.0.0-alpha.1

package/skills/intent-planning/references/plan-format.md

@@ -1,130 +0,0 @@
-# Plan, Checklist, and Action Format
-
-The exact templates for `plan.md`'s header and task structure, and for the
-`checklist.md` and `actions/ACTION_N.md` artifacts. Read this before writing
-plan.md so the shape matches on the first pass.
-
-## Table of Contents
-
-- [Plan Document Header](#plan-document-header)
-- [Task Structure (worked example)](#task-structure-worked-example)
-- [checklist.md format](#checklistmd-format)
-- [actions/ACTION_N.md format](#actionsaction_nmd-format)
-
-## Plan Document Header
-
-**Every plan MUST start with this header:**
-
-```markdown
-# [Feature Name] Implementation Plan
-
-> **For agentic workers:** Use `plastic-intent-executing` to implement this plan task-by-task.
-
-**Goal:** [One sentence describing what this builds]
-
-**Architecture:** [2-3 sentences about approach]
-
-**Tech Stack:** [Key technologies/libraries]
-
-**Intent:** {id}: {name}
-
-**Tier:** S|M|L, copied from the spec's stamped `Tier:` line. Every tier produces at
-least one real `actions/ACTION_N.md`; S and M consolidate the delivery into one action
-file, L uses one `actions/ACTION_N.md` per task.
-
----
-```
-
-## Task Structure (worked example)
-
-````markdown
-### Task N: [Component Name]
-
-**Files:**
-- Create: `exact/path/to/file.rb`
-- Modify: `exact/path/to/existing.rb:123-145`
-- Test: `test/exact/path/to/test.rb`
-
-- [ ] **Step 1: Write the failing test**
-
-```ruby
-def test_specific_behavior
-  result = function(input)
-  assert_equal expected, result
-end
-```
-
-- [ ] **Step 2: Run test to verify it fails**
-
-Run: `ruby -Itest test/path/test.rb --name test_specific_behavior`
-Expected: FAIL with "undefined method"
-
-- [ ] **Step 3: Write minimal implementation**
-
-```ruby
-def function(input)
-  expected
-end
-```
-
-- [ ] **Step 4: Run test to verify it passes**
-
-Run: `ruby -Itest test/path/test.rb --name test_specific_behavior`
-Expected: PASS
-
-- [ ] **Step 5: Commit**
-
-```bash
-git add test/path/test.rb lib/path/file.rb
-git commit -m "feat: add specific feature"
-```
-````
-
-## checklist.md format
-
-Execution registry with one checkbox per task, following this FORM regardless
-of tier (S, M, or L):
-
-```markdown
-# Checklist: {name}
-
-## In Progress
-- [ ] Task 1: {task title}
-- [ ] Task 2: {task title}
-- [ ] Task 3: {task title}
-
-## Completed
-(empty at plan time; move each item here, checked, the moment its task lands)
-
-## Session Log
-| Date | Items Completed | Notes |
-|------|-----------------|-------|
-```
-
-- `## In Progress` holds every unchecked task, in plan order.
-- `## Completed` starts empty. As execution lands a task, move its item here
-  (checked) instead of leaving a checked box under `## In Progress`.
-- `## Session Log` gets one row per work session: the date, which items
-  completed, and any deviation or finding worth recording.
-- An owner-decision hard-gate item (see the parent SKILL.md's
-  `## Owner-decision hard-gate items`) is a normal checklist item prefixed
-  `[ORCHESTRATOR]`; it lives under `## In Progress` until the owner rules, then
-  moves to `## Completed` like any other item.
-
-## actions/ACTION_N.md format
-
-Every tier writes at least one real action file here (see the parent SKILL.md's
-`## Tier shapes`): S and M consolidate the whole delivery into a single
-`actions/ACTION_1.md`, L writes one file per task.
-
-Each action is self-contained: a subagent (or a solo executor) can execute it without
-reading the plan. It carries the ordered steps to deliver the task plus the exact changes
-to make (for code, the anchor or `file:line` and the old/new text).
-
-```markdown
-# Action {N}: {task title}
-
-{Full task text copied from plan.md: all steps, all code, all commands. Nothing omitted.}
-```
-
-Create the `actions/` directory inside the intent directory: `{intent_dir}/actions/`

package/skills/intent-researching/SKILL.md

@@ -1,123 +0,0 @@
----
-name: plastic-intent-researching
-description: "Research a topic for the active intent. Agent decides shallow vs deep based on scope. Produces reports in the intent's resources/ directory."
-user-invocable: true
----
-
-# Research
-
-Investigate a topic related to the active intent. Choose the right depth, produce a cited report.
-
-## Active Intent Gate
-
-Before proceeding, resolve the active intent:
-
-1. **Detect store:** Read `~/.plastic/projects.yml`, match CWD against registered project paths. If match → project store at `~/.plastic/projects/{slug}/store/`. If no match → global store at `~/.plastic/store/`.
-2. **Find active intent:** Read `INDEX.md` from the detected store. Look under `## Active`. If exactly one → use it. If multiple → ask which. If none → refuse: "No active intent. Create one first with /plastic-intent-creating"
-3. **Resolve intent directory:** `{store}/store/{id}--{slug}/`
-
-## Check Prior Work First
-
-QMD-first (when available): before scanning the store with grep/Read or searching the web, run
-`ruby ~/.plastic/scripts/qmd-sync search "<terms>"` to surface candidate, prior, or related intents
-and existing research, then open the authoritative intent file for any hit you act on. Reusing a
-prior report beats re-deriving it. The command is a no-op when QMD is absent, so fall back to the
-existing INDEX.md / file scan.
-
-## Depth Decision
-
-Before starting research, assess the question against these criteria:
-
-### Shallow Research
-Use when:
-- The question is narrow and factual (e.g., "what's the API for X?", "does library Y support Z?")
-- A single source or quick search is sufficient
-- The answer is likely well-documented
-- Time budget: minutes, not hours
-
-**Method:** Direct web search + codebase exploration + single-pass synthesis.
-
-### Deep Research
-Use when:
-- The question needs multiple sources and cross-verification
-- It's a landscape survey, competitive analysis, or architectural decision
-- The user explicitly asks for thorough/exhaustive/comprehensive research
-- Conflicting information exists and needs adversarial verification
-- Time budget: significant, user expects depth
-
-**Method:** Delegate to the native agent's deep research capability.
-- On Claude Code: invoke the `deep-research` skill via `Skill` tool
-- On other agents: use the agent's equivalent (see intent 7 for cross-agent mapping)
-- If no native deep research exists: fan out multiple web searches manually, cross-reference, synthesize
-
-### Decision Heuristic
-
-Ask yourself:
-1. Can I answer this with 1-2 searches? → **Shallow**
-2. Do I need to compare 3+ sources? → **Deep**
-3. Is the user asking for a survey or landscape view? → **Deep**
-4. Am I fact-checking a specific claim? → **Shallow**
-5. Could wrong information here cause architectural mistakes? → **Deep**
-
-Announce your choice: "This needs [shallow/deep] research because [reason]."
-
-## Output
-
-### File Location
-`{intent_dir}/resources/{type}--{topic}.md`
-
-Create the resources/ directory if it doesn't exist.
-
-### Naming Convention
-- `{type}` — one of: `deep-research`, `competitive-analysis`, `technical-spike`, `reference`, `landscape-survey`
-- `{topic}` — kebab-case description of the research subject
-
-Examples:
-- `deep-research--installer-patterns.md`
-- `technical-spike--sqlite-vec-performance.md`
-- `reference--claude-code-hooks-api.md`
-- `landscape-survey--ai-agent-ecosystem.md`
-
-### Report Structure
-
-Default to tabular-first per `PLASTIC.md` (## Tabular-First Reporting, intent 160): tables for findings and comparisons, prose for simple summaries.
-
-```markdown
-# {Type}: {Topic}
-
-**Intent:** {id} — {name}
-**Depth:** shallow | deep
-**Date:** YYYY-MM-DD
-
-## Summary
-[2-3 sentence executive summary]
-
-## Findings
-
-### [Finding 1 title]
-[Details with inline citations where applicable]
-
-### [Finding 2 title]
-...
-
-## Sources
-- [Source 1 title](url) — what was learned from this source
-- [Source 2 title](url) — ...
-
-## Relevance to Intent
-[How these findings affect the active intent's decisions or design]
-```
-
-## After Research
-
-1. Commit to store repo:
-   ```
-   cd {store_root} && git add . && git commit -m "research: {type} — {topic} (intent {id})"
-   ```
-
-2. Log in intent's `## Insights`:
-   ```
-   - Research: {type} — {topic}. Key finding: [one sentence]. See resources/{filename}.
-   ```
-
-3. Research does NOT chain to any other skill. It's a side quest — the user decides what to do with the findings.

package/skills/intent-researching/evals/evals.json

@@ -1,22 +0,0 @@
-{
-  "skill_name": "plastic-intent-researching",
-  "notes": "Intent 66a. Spec for the QMD-first step before researching (reuse prior intents/reports before grep/Read or web search). Runner is intent 76; spec only.",
-  "evals": [
-    {
-      "id": 1,
-      "scope": "behavior",
-      "set": "validation",
-      "prompt": "QMD is present. The user asks the agent to research installer patterns for the active intent.",
-      "expected_output": "Before scanning the store with grep/Read or searching the web, runs `ruby ~/.plastic/scripts/qmd-sync search \"installer patterns\"` to surface candidate, prior, or related intents and existing research, then opens the authoritative intent file for any hit it reuses. No-op fallback to INDEX.md / file scan when QMD is absent.",
-      "files": [],
-      "assertions": [
-        {
-          "type": "human",
-          "check": "qmd-sync search is run before grep/Read and web search; authoritative file opened for any prior report reused",
-          "observed": "SKILL.md (or agent file) carries the QMD-first step: run qmd-sync search before grep/Read, then open the authoritative file; no-op fallback when QMD is absent",
-          "result": "pass"
-        }
-      ]
-    }
-  ]
-}

package/skills/intent-savepoint/SKILL.md

@@ -1,83 +0,0 @@
----
-name: plastic-intent-savepoint
-description: Use when verifying or repairing an intent's savepoint ledger, when the user says "save" or "savepoint", or when a PreCompact hook fires. The ledger is written automatically by the gate hook at each lifecycle boundary; this skill only reads, verifies, and rebuilds it.
-user-invocable: false
----
-
-# Savepoint
-
-`savepoint.md` is a deterministic, append-only ledger of an intent's cycle steps, one line
-per lifecycle milestone, newest at the bottom:
-
-```
-2026-06-16T14:02Z  What  34--cycle-step-savepoints.md
-2026-06-16T14:20Z  Why   spec.md created
-2026-06-16T15:10Z  How   plan.md created
-2026-06-16T15:11Z  How   checklist.md created
-2026-06-16T16:40Z  Exec  outcome.md created
-```
-
-It is **sugar on top of the conventions**, not a source of truth. The gate hook
-(`hook-gate-check`) writes each line automatically when a stage file is created, so there is
-nothing to save by hand. State is always derivable from files-on-disk; the ledger just lets
-a resuming agent read the cycle's succession from one glance (last line = where we are).
-
-Read `../plastic-conventions/references/lifecycle-and-savepoints.md` for the subagent
-report-home contract that this ledger feeds. This path resolves relative to this skill's own
-installed directory.
-
-## When to Use
-- A PreCompact hook fires, or the user says "save" / "savepoint": verify the ledger is current.
-- Resuming an intent: read the ledger to learn the cycle's succession quickly.
-- The ledger looks stale, empty, or missing: rebuild it from the filesystem.
-
-## What this skill does NOT do
-- It does not write prose, "in progress", "next step", or "blockers". The old 50%-context
-  prose savepoint is retired. The semantic trace lives in `## Insights` (append-only,
-  newest at the bottom); the byte history lives in git.
-
-## Workflow
-
-### 1. Find Active Intent(s)
-Read the active store's `INDEX.md` and extract intents under `## Active`.
-
-### 2. For Each Active Intent — verify the ledger
-- Read `savepoint.md`. Confirm it exists and is non-empty.
-- Confirm the **last line's stage** matches the stage derived from files-on-disk
-  (`Bridge.derive_stage`). If they disagree, or the file is missing/empty, the ledger has
-  drifted.
-- Run `Bridge.savepoint_phantom_lines(intent_dir)` (pure, disk-only, no bridge or session
-  resolution; intent 134). It flags a line disk evidence contradicts: a file-landing milestone
-  whose file is absent or still a sentinel placeholder, a duplicate `(stage, milestone)` pair, or
-  a state line (`How  started` / `Exec  started`) whose stage prerequisites are absent. If it
-  returns any lines:
-  - **LIVE intent (INDEX `## Active`):** rebuild via step 3 below.
-  - **INDEX `## Completed`/`## Abandoned` intent:** REPORT the phantom lines and STOP. Do not
-    rewrite. Completed intents are immutable. A repair is available only under an explicit human
-    grant, following the 124a precedent: rebuild the file-landing skeleton (step 3), then
-    re-append the terminal `Done  <disposition>` bookend with the disposition read from
-    `outcome.md`'s `disposition:` frontmatter and the timestamp recovered from the merge commit or
-    the file's mtime, never invented.
-
-### 3. Rebuild on drift
-Reconstruct from the filesystem rather than hand-editing:
-
-```bash
-ruby -r ~/.plastic/scripts/lib/bridge -e \
-  'Bridge.rebuild_savepoint("<intent_dir>")'
-```
-
-This rewrites `savepoint.md` from the milestone files present (timestamps from mtimes),
-in stage order. Safe to run anytime: the ledger is derived.
-
-### 4. Commit (store only)
-If a rebuild changed the ledger, commit it in the store repo:
-```bash
-cd <store-root> && git add . && git commit -m "chore: rebuild savepoint ledger — [intent]"
-```
-Never push `~/.plastic/`.
-
-## References
-
-- Read `references/context-management.md` for the full save/continue protocol and how the
-  resume flow consumes the ledger.

package/skills/intent-savepoint/references/context-management.md

@@ -1,32 +0,0 @@
-# Context Management (Start-Save-Continue)
-
-## Save Point
-Triggered by PreCompact hook or manually:
-1. Find active intent(s) from `~/.plastic/INDEX.md`
-2. Update active intent's `checklist.md` (check off completed items)
-3. Update active intent's `savepoint.md` (in-progress, next steps, blockers, discoveries)
-4. Add observations to `## Insights`
-5. Update INDEX.md
-6. Commit: `cd ~/.plastic && git add . && git commit -m "chore: savepoint — [intent name]"`
-7. Notify user to `/clear`
-
-## Continue
-Triggered by UserPromptSubmit hook when user says "continue". Priority order:
-
-**1. Active intents first (resume work):**
-1. Read INDEX.md → find active intent(s)
-2. Read active intent's `intent.md` → what and why
-3. Read active intent's `savepoint.md` → where we left off
-4. Read active intent's `checklist.md` → what's next
-5. Announce: intent name, current state, next step, blockers
-6. Resume
-
-**2. No active intents → offer future intents:**
-1. List all future intents from INDEX.md
-2. Present them as options
-3. When user picks one, move to Active in INDEX.md
-
-**3. Stale future intents (untouched 3+ days) → triage:**
-- **activate** — start working on it now
-- **abandon** — mark as abandoned
-- **defer to agent** — implement, research, or ideate

package/skills/intent-starting/SKILL.md

@@ -1,151 +0,0 @@
----
-name: plastic-intent-starting
-description: >-
-  Board a session onto an intent: take the lock FIRST, confirm savepoint state, ask auto or
-  guided ONCE, then resume at the latest delivered station and run the cycle to Done. Use on
-  `continuing --intent {id}`, when a new intent is registered and the user asks to work it,
-  or when the user picks an intent to work. Requires the intent in INDEX `## Active`.
-user-invocable: true
----
-
-# Intent Starting — board a session onto an intent
-
-`plastic-intent-starting` is the Start procedure. It boards a session onto one intent: take
-the lock FIRST, confirm the delivery state, ask **auto or guided ONCE**, board at the latest
-delivered station, then run the cycle to Done. The What → Why → How → Exec stations are the
-train track; Start boards the train, the ending procedure (~93) exits it.
-
-## Precondition + trigger
-
-Fires when the user picks an intent to work, when an agent is told to continue a SPECIFIC
-intent, or on `continuing --intent {id}` (the `continuing` → `starting` router is 106's job;
-this skill is invokable standalone now).
-
-If the intent is **terminal** (Done / Abandoned in INDEX): report only. Take NO lock, run NO
-resume, do NOT reopen it. Summarize the outcome and ask what is next. Stop here.
-
-## Lock FIRST (the spine)
-
-The lock is non-negotiable and comes before any mutating work. The ACTION-3 lock-gate
-enforces it: without a held lock, mutating writes to this active intent's dir are denied with
-"run /plastic-intent-starting to lock and begin".
-
-Read `../plastic-conventions/references/locks-and-worktrees.md` for delivery isolation: the
-single-owner lock, claims, worktrees, solo mode, and the station ledger behind everything below.
-This path resolves relative to this skill's own installed directory.
-
-1. **Ensure the intent is in INDEX `## Active`.** If it sits in `## Future`, activate it
-   (move it to `## Active`, auto-commit) before arming. Creation precedes activation, so a
-   brand-new What intent is activated here, then locked.
-2. **Self-heal the lock state first.** Run:
-   `ruby ~/.plastic/scripts/plastic-lock fix --intent-dir <STORE>/<dir>`
-   This is the one repair function (same one /plastic-lock exposes): it removes
-   corrupt or legacy lock state and rebuilds the lock and bridge from disk for
-   this session. If it reports `held`, another session owns the intent: STOP
-   and tell the user who holds it. If it reports `stale`, ask the user before
-   running `plastic-lock reclaim` (takeover is audited).
-3. **Arm the bridge.** Which arm is chosen by the mode answer (below), but the lock itself is
-   taken first. Reuse the arm one-liner shape from `plastic-auto`:
-   ```bash
-   # guided (lock only):
-   ruby -r ~/.plastic/scripts/lib/bridge -e \
-     'codex=ENV["CODEX_THREAD_ID"].to_s.strip; claude=ENV["CLAUDE_CODE_SESSION_ID"].to_s.strip; harness=!codex.empty? ? "codex" : (!claude.empty? ? "claude" : nil); session=!codex.empty? ? codex : (!claude.empty? ? claude : nil); Bridge.arm_guided(session, intent_id: "<ID>", intent_dir: "<STORE>/<dir>", store: "<STORE>", name: "<name>", harness: harness, agent: "plastic-enforcer", thread: (!codex.empty? ? codex : nil))'
-   # auto (lock + auto), then hand to plastic-auto:
-   ruby -r ~/.plastic/scripts/lib/bridge -e \
-     'codex=ENV["CODEX_THREAD_ID"].to_s.strip; claude=ENV["CLAUDE_CODE_SESSION_ID"].to_s.strip; harness=!codex.empty? ? "codex" : (!claude.empty? ? "claude" : nil); session=!codex.empty? ? codex : (!claude.empty? ? claude : nil); Bridge.arm_auto(session, intent_id: "<ID>", intent_dir: "<STORE>/<dir>", store: "<STORE>", name: "<name>", harness: harness, agent: "plastic-enforcer", thread: (!codex.empty? ? codex : nil))'
-   ```
-   Replace `<ID>`, `<STORE>` (`~/.plastic/projects/<slug>/store` or `~/.plastic/store`),
-   `<dir>` (the `ID--slug` directory), and `<name>`.
-4. **Dispatch What-stage discovery (under the lock).** Right after arming, when the intent
-   was just activated in step 1 (on a resume that already has
-   `resources/discovery--<slug>.md`, skip: discovery runs once per intent, at activation
-   only), dispatch the `plastic-intent-discovery` agent (see the `plastic-intent-discovering`
-   skill), now that this session owns the lock, deposit authorized as the owner session. Resolve its
-   model explicitly and pass it at dispatch time (belt-and-braces): `read-config
-   agents.models.plastic-intent-discovery --project <repo>`. The agent runs QMD discovery
-   over the intent's `chain`/`sources` and deposits findings to
-   `resources/discovery--<slug>.md` only; it never writes the intent file, so the
-   lock-owner-only rule is untouched. This is advisory context for Why, not a gate: if
-   discovery yields nothing, proceed to Why normally.
-
-   **Skip the dispatch only at Tier S, when there is nothing to discover.** The skip fires
-   only when BOTH hold: a size of S is already on record for this intent, and the activating
-   intent's `chain` and `sources` frontmatter fields are both empty. On record means a
-   stamped `Tier: S` line at the top of `spec.md`. Sizing happens at Why, which is after this
-   step, so a first activation usually has no size yet: run the pass. The skip mainly earns
-   its keep on a re-activated intent that is already sized S. Never guess a size here to
-   unlock the skip. When both conditions hold, write the single line
-   `no chain/sources, discovery skipped` to `resources/discovery--<slug>.md` in its place,
-   then go to Why.
-
-**Session id resolution (verbatim from `plastic-auto`).** The first argument is the session
-id the bridge is keyed by: pass the hook stdin `session_id` when you have it; in the executable
-snippets, a nonblank `CODEX_THREAD_ID` identifies Codex, otherwise a nonblank
-`CLAUDE_CODE_SESSION_ID` identifies Claude, otherwise identity remains unknown. Never infer a
-harness from an absent variable. Both arms call `resolve_session`, which
-picks the first non-empty of: the explicit id you pass → `CLAUDE_CODE_SESSION_ID` → a
-deterministic derived key (a hash of the store and intent id). It never returns nil, so the
-lock is taken even when every session env var is empty; arming prints a one-line stderr
-notice when it falls through to the derived key.
-
-**What the lock IS.** Ownership is session-keyed and lease-based: arming writes a durable
-`delivery.lock` file in the intent dir naming this session as owner, and the owner's hooks
-refresh the file mtime on tool activity (the lease heartbeat). The /tmp bridge is only a
-cache of that file; on any disagreement the lock file wins, so a wiped /tmp never strands
-the owner. Idempotent re-arm: arming again with the same owner just refreshes the lock; it
-is not an error to re-board an intent this session already owns. A failed arm raises with
-a message naming the resolving `plastic-lock` verb (`status`, `reclaim`, or `fix`): follow
-that message, never delete a lock file by hand.
-
-## Confirm delivery state
-
-Read `savepoint.md` and classify from the **last line** alone, then verify ONLY that line's
-artifact is real (sentinel-aware via `Bridge.stage_file_present?`). On drift (the last line
-disagrees with files on disk), rebuild the ledger from disk and note the correction. Do not
-inline the rebuild; the `plastic-intent-savepoint` skill owns it:
-```bash
-ruby -r ~/.plastic/scripts/lib/bridge -e 'Bridge.rebuild_savepoint("<intent_dir>")'
-```
-
-## Report + ask "auto or guided?" ONCE
-
-Report: the intent, the station it lands at (the matrix below), what is delivered, the next
-step. Then ask the user **"auto or guided?"** — exactly ONCE, whatever station it lands at.
-Never re-ask at a later station.
-
-- **guided** → `arm_guided` (lock only); continue step by step with the user through the
-  station's work below.
-- **auto** → `arm_auto` (lock + auto), then hand off to `plastic-auto`. The auto branch's
-  only remaining job is the handoff; `plastic-auto` runs the cycle from here.
-
-Read `../plastic-conventions/references/tiers-and-dispatch.md` for tier sizing and the
-stage-to-agent dispatch rules behind the auto branch above.
-
-## Board at the latest delivered station
-
-The station is derived from `savepoint.md` last line + real artifacts on disk. See
-`references/boarding-matrix.md` for the full table (last line → latest delivered → boards at →
-continue with) and the per-station notes. Summary of what "continue" means per station:
-
-Read `../plastic-conventions/references/gates-and-enforcement.md` for the transition-gate
-mechanics, the audited escape, and gate logging that govern moving between the stations below.
-
-- **What** → do what What requires (106-expanded), then brainstorm → `spec.md`.
-- **Why** → continue brainstorming → `spec.md`.
-- **How** → continue `plan.md` + `actions/` + `checklist.md`.
-- **Exec** → verify what has been delivered, then continue (or restart) the delivery /
-  research; tick the checklist.
-- **ready to complete** (`Exec outcome.md created`) → exit at Done.
-- **Done** → report only, ask what is next, never reopen.
-
-## Disarm / release on done
-
-When delivery finishes, disarm and release per the `plastic-auto` disarm/release prose (do
-not duplicate it here). The guided branch releases the lock via `disarm_auto`, which is
-mode-agnostic (it sets `auto = false` and calls `Worktree.release`), so it releases a guided
-lock too. When the work ships through a release, the release path merges the branch before the
-worktree is removed; the plain disarm remove is only for the no-release case.
-
-## References
-
-- `references/boarding-matrix.md` — the full boarding table and per-station behaviour.

package/skills/intent-starting/evals/evals.json

@@ -1,117 +0,0 @@
-{
-  "skill_name": "plastic-intent-starting",
-  "notes": "Intent 96. Scopes: description triggering (1-5) and behavior (6-10: lock-first spine, ask-mode-once, terminal report-only, mode->arm mapping, boarding matrix). The lock-first and gate behaviors are also proven by Ruby tests (test/bridge_guided_test.rb, test/lock_gate_test.rb, test/lock_gate_hook_test.rb).",
-  "evals": [
-    {
-      "id": 1,
-      "scope": "triggering",
-      "set": "train",
-      "prompt": "start work on intent 96",
-      "expected_output": "Activates plastic-intent-starting (board a session onto the named intent).",
-      "files": [],
-      "assertions": [
-        { "type": "code", "check": "router CHOICE == plastic-intent-starting", "result": "expect-pass" }
-      ]
-    },
-    {
-      "id": 2,
-      "scope": "triggering",
-      "set": "train",
-      "prompt": "continuing --intent 96",
-      "expected_output": "Activates plastic-intent-starting (the --intent form boards a specific intent).",
-      "files": [],
-      "assertions": [
-        { "type": "code", "check": "router CHOICE == plastic-intent-starting", "result": "expect-pass" }
-      ]
-    },
-    {
-      "id": 3,
-      "scope": "triggering",
-      "set": "validation",
-      "prompt": "work this intent",
-      "expected_output": "Activates plastic-intent-starting when an intent is in context to be worked.",
-      "files": [],
-      "assertions": [
-        { "type": "code", "check": "router CHOICE == plastic-intent-starting", "result": "expect-pass" }
-      ]
-    },
-    {
-      "id": 4,
-      "scope": "triggering",
-      "set": "validation",
-      "prompt": "continue",
-      "expected_output": "Does NOT activate plastic-intent-starting; bare 'continue' is plastic-continuing (the router, no specific intent named).",
-      "files": [],
-      "assertions": [
-        { "type": "code", "check": "router CHOICE != plastic-intent-starting", "result": "expect-pass" }
-      ]
-    },
-    {
-      "id": 5,
-      "scope": "triggering",
-      "set": "validation",
-      "prompt": "create a new intent for the uploader retry policy",
-      "expected_output": "Does NOT activate plastic-intent-starting; activates plastic-intent-creating.",
-      "files": [],
-      "assertions": [
-        { "type": "code", "check": "router CHOICE != plastic-intent-starting", "result": "expect-pass" }
-      ]
-    },
-    {
-      "id": 6,
-      "scope": "behavior",
-      "set": "train",
-      "prompt": "Active intent X exists at the Why station. Start work on it (guided).",
-      "expected_output": "Takes the lock FIRST via Bridge.arm_guided (auto stays false) before any mutating work, confirms savepoint, then boards at Why and continues brainstorming toward spec.md.",
-      "files": [],
-      "assertions": [
-        { "type": "human", "check": "lock acquired before any mutating write; SKILL.md 'Lock FIRST' section precedes station work", "result": "expect-pass" },
-        { "type": "code", "check": "Bridge.arm_guided stamps the lock with auto=false (test/bridge_guided_test.rb green); lock-gate denies a no-lock write to the active intent dir (test/lock_gate_hook_test.rb green)", "result": "pass" }
-      ]
-    },
-    {
-      "id": 7,
-      "scope": "behavior",
-      "set": "train",
-      "prompt": "Start work on an active intent without saying auto or guided.",
-      "expected_output": "Asks 'auto or guided?' exactly once after reporting the station; never re-asks at later stations.",
-      "files": [],
-      "assertions": [
-        { "type": "human", "check": "SKILL.md asks the mode exactly once and states 'never re-asked at a later station'", "result": "expect-pass" }
-      ]
-    },
-    {
-      "id": 8,
-      "scope": "behavior",
-      "set": "train",
-      "prompt": "Start work on an intent that is Done in INDEX.",
-      "expected_output": "Reports only: no lock, no resume, no reopen. Summarizes the outcome and asks what is next.",
-      "files": [],
-      "assertions": [
-        { "type": "human", "check": "terminal intent -> report only, no arm call", "result": "expect-pass" }
-      ]
-    },
-    {
-      "id": 9,
-      "scope": "behavior",
-      "set": "validation",
-      "prompt": "Start work and choose auto.",
-      "expected_output": "guided -> Bridge.arm_guided; auto -> Bridge.arm_auto then hand off to plastic-auto (auto branch's only remaining job is the handoff).",
-      "files": [],
-      "assertions": [
-        { "type": "human", "check": "SKILL.md maps guided->arm_guided and auto->arm_auto+handoff to plastic-auto", "result": "expect-pass" }
-      ]
-    },
-    {
-      "id": 10,
-      "scope": "behavior",
-      "set": "validation",
-      "prompt": "Start an intent whose savepoint last line is 'How  checklist.md created'.",
-      "expected_output": "Boards at Exec (verify plan + checklist real), per references/boarding-matrix.md, and continues delivery/ticks the checklist.",
-      "files": [],
-      "assertions": [
-        { "type": "human", "check": "boarding matrix lands 'How checklist.md created' / 'Exec started' at Exec", "result": "expect-pass" }
-      ]
-    }
-  ]
-}