task-pipeline-skill 1.79.1 → 1.80.0

package/CHANGELOG.md

@@ -1,5 +1,84 @@
 # Changelog
 
+## v1.80.0 — the doctrine pack: one home per rule, and the boundaries said out loud
+
+The largest doctrine reconciliation since the corpus was audited whole. The
+wave-2/3 audit read all ~717KB of shipped doctrine against itself and this
+release closes its deferred pack: every contradiction between a short-form
+gate and its long form, every count restated where a list already was the
+count, and the two closure protocols that had no boundary sentence between
+them.
+
+**Two closure protocols, one boundary.** A work-graph node closes through the
+three blind tiers and `graph.py certify` (ceiling 3); a prose-plan task closes
+through `build.md` §4.4's single reviewer (five-round cap). Both were true and
+nothing said which applied — a run could pick whichever was cheaper at the
+moment of closing. The boundary sentence now lives in `SKILL.md`'s routing
+row, `certification.md` and `build.md`: the artifact the queue is decides.
+
+**The COPY/VISUAL track doctrine moved into `spec.md` whole** — its one home —
+and `stages.md`'s stage 3 keeps a routed summary; the example config's stage-3
+check now demands the tracks and their convergence record. `references/
+probing.md` is new: the four probe-authoring sections extracted from
+`gates.md` (plant/run/restore, how a probe rots, the neighbour probe, the
+landed-mutation rule), routed from the gate doctrine they prove; the guards
+and plants that read those sections moved with them, and the bundle's
+reference-file counts were re-derived to 38 by the registry that refuses a
+stale one.
+
+**The `judgment` gate type reaches every surface that taught `auto`/`manual`**
+— SKILL.md (three places), stages.md, the command, the Cursor rule, README,
+plugin.json — and a new cross-surface guard compares the schema's enum against
+the sentence that teaches it, so the next type cannot sit seven releases in
+the schema alone. The browser gate cells say when the look binds and what the
+weaker claim is; brainstorm's GATE names the queue-artifact and loop-arming
+criteria; the loop arms where `run.loop.arm` says, not unconditionally at
+preflight; stage-0 seeding covers the three gate scripts stages 5–10 run;
+the template board's State vocabulary admits `parked`/`waived`; project-audit
+prices with the board header's declared formula and never effort, and its
+disambiguation table gains the fifth audit (`/seo-aeo-audit`). Four domain
+companions (sheleg-dev, agent-stack, telegram-dev, seo-aeo-audit) enter the
+matrix, the preflight block and the stages they bind — recommended, never a
+gate. `model-tiering.md` gains the per-generation stress-test rule and the
+judgment gate the rubric-steering note, both with dated sources.
+
+**Mechanics: the PR gate now runs what `npm test` documents.** `graph_test.py`
+and `project_audit_test.py` reached CI only at tag time; a PR breaking
+`graph.py` merged green. The blind rule covers every prose field of a tier
+report — a cross-tier citation hiding in `scope` or a finding's `what`/`fix`
+is refused, fixtured, and mutation-proven (17/17 noticed, control 22).
+`gate-observer.sh` reads the documented `tool_response` payload with
+`tool_output` as fallback — the exit-code branch had been dead on the
+documented shape — with fixtures on both shapes, each watched red against the
+reverted hook. The upstream strict validation is its own CI job, so an npm
+outage and a house failure stop masking each other.
+
+**Ledgers: the board re-ranks on real ages.** Every open row's Age and Prio
+re-derived against its Source date — rows filed 08-17/08-20 still said Age 0
+on 08-29 under a header claiming re-derivation. The verification ledger's
+`Shipped state` header is gated against `package.json` (it had sat six
+releases stale), the two 2026-08-22 run stamps stop claiming retro entries
+that do not exist, the two rows frozen at `unreleased` gain superseding rows
+naming v1.72.0, and v1.76.0's absence from the ledger is stated beside the
+08-20 note. Five board rows filed from the harness-engineering articles
+(B-114…B-117) and from this release's own probes (B-118).
+
+**Evals: three blind runs, one per model.** evidence-docs and project-audit
+gain behavioural suites with near-miss negatives («аудит модуля» one word
+from «аудит проекта»); `evals/run.py` discovers every suite instead of the
+one filename it shipped pinned to; and 147 fresh-subagent probes (49 queries
+× haiku/sonnet/opus) produced the first dated blind rows in both RESULTS
+files — opus 42/42, sonnet 40/42, haiku 39/42, with haiku's three misses
+sharing one shape that is now B-118. Method and limits stated in the ledgers,
+INSTR cases recorded as not reproducible rather than guessed.
+
+`compatibility` frontmatter on task-pipeline and project-audit; a 3-line
+Degradation block in SKILL.md paid for by the model blockquote it displaced;
+`$schema` in both manifests.
+
+Guards: 417 → **419** — the gate-type vocabulary plant and the stale
+shipped-state-header plant, both watched red locally before shipping.
+
 ## v1.79.1 — the probe that a healthy release disarmed
 
 The first round of `v1.79.0` failed in the release job on the

package/README.md

@@ -587,7 +587,7 @@ must say so.
 ### Held to Anthropic's own Skill authoring guidance
 
 Audited against the four Agent Skills pages. Most of it already held — `name`
-13/64 chars, `description` inside 1024, `SKILL.md` 334/500 lines, all 37 references
+13/64 chars, `description` inside 1024, `SKILL.md` 334/500 lines, all 38 references
 linked **directly** from `SKILL.md`, 436 KB against a 30 MB ceiling. What did not,
 now does:
 
@@ -787,7 +787,7 @@ Stages 0→10 above are the plugin's **example** flow. It is a machine-readable
 written against a universal contract
 ([`pipeline.schema.json`](plugins/task-pipeline/skills/task-pipeline/pipeline.schema.json)):
 copy the example to `pipeline.json` in your repo and rewrite it with your own stages
-(any count), your own `skills[]`, and your own `auto`/`manual` gate types. The
+(any count), your own `skills[]`, and your own `auto`/`judgment`/`manual` gate types. The
 framework bakes in no fixed stage count and no opinion on which gates are manual.
 
 ```jsonc
@@ -932,7 +932,8 @@ recommendation, so you arm the whole run in one exchange. Detail:
 | [`references/artifacts.md`](plugins/task-pipeline/skills/task-pipeline/references/artifacts.md) | the canonical document layout each stage writes to |
 | [`references/conventions.md`](plugins/task-pipeline/skills/task-pipeline/references/conventions.md) | how stages 6–10 read the host project's `CLAUDE.md`, and how the documentation regime is detected |
 | [`references/documentation.md`](plugins/task-pipeline/skills/task-pipeline/references/documentation.md) | the doc system: the inventory, registers and ids, SSOT, the Doc Loop, supersede semantics, the propagation matrix, intent vs as-built |
-| [`references/gates.md`](plugins/task-pipeline/skills/task-pipeline/references/gates.md) | the three axes, the promotion ladder, gate anatomy, the probe recipe, ratchet floors, where a gate runs |
+| [`references/gates.md`](plugins/task-pipeline/skills/task-pipeline/references/gates.md) | the three axes, the promotion ladder, gate anatomy, ratchet floors, where a gate runs |
+| [`references/probing.md`](plugins/task-pipeline/skills/task-pipeline/references/probing.md) | the probe recipe — plant, run, restore; how a probe rots; the neighbour probe; the landed-mutation rule |
 | [`references/deploy-targets.md`](plugins/task-pipeline/skills/task-pipeline/references/deploy-targets.md) | stages 7–8: writing the runbook when there is none, the template, per-platform deploy and log verbs, the verification trio |
 | [`references/hooks.md`](plugins/task-pipeline/skills/task-pipeline/references/hooks.md) | the `PreToolUse` contract, the fail-open hazard, placement, and the Claude-Code-only limit |
 | [`references/knowledge-graph.md`](plugins/task-pipeline/skills/task-pipeline/references/knowledge-graph.md) | the code graph: install line, stage-0 reach queries, the stage-9 refresh, the graph↔docs divergence check |

package/SKILL-CARD.md

@@ -12,7 +12,7 @@ harmless.
 |---|---|
 | **Purpose** | Runs a substantial task through ten gated delivery stages — intake grill, docs study, brainstorm, spec, plan, subagent build, tests, lint/deploy, post-deploy, docs+registers, acceptance — refusing to advance until each gate passes |
 | **Owner** | ssheleg ([github.com/ssheleg/task-pipeline](https://github.com/ssheleg/task-pipeline)) |
-| **Version** | 1.79.1 |
+| **Version** | 1.80.0 |
 | **Surface** | Claude Code (filesystem skill + plugin) and the vercel `skills` CLI. **Not** uploaded to the Skills API; custom Skills do not sync across surfaces |
 | **Dependencies** | None required. Optional: `context7` (MCP), `figma` (MCP), super-ux, agent-sync, graphify, obsidian-wiki, and **one of two browser channels** — `playwright` (CLI or MCP) or `chrome-devtools` (MCP); either satisfies the browser step and neither is required. Every stage's doctrine ships in-repo; the one conditional requirement is super-ux for the stage-3 UX track on a user-facing task |
 | **Evaluation status** | Suite authored, 5 categories. One recorded run, **self-observed by the author**; **zero blind runs on zero of three models** — the split, and the numbers, live in [`evals/RESULTS.md`](evals/RESULTS.md) and are computed by `evals/run.py` |

package/cursor/rules/task-pipeline.mdc

@@ -499,7 +499,9 @@ type the run produced, then run the documentation gate and print its ratchet cou
 ## Gates: three axes, and how to build one that cannot lie
 
 **Axis A — the stage gate type.** `auto` = verify the check yourself and stop on
-fail; `manual` = wait for an explicit operator go. An auto gate never substitutes
+fail; `judgment` = a named judge rules where no deterministic check exists, and the
+ruling is recorded as judgement, never as a measurement; `manual` = wait for an
+explicit operator go. Neither of the first two ever substitutes
 for a required manual approval.
 
 **Axis B — where the rule is actually enforced**, and a rule climbs this ladder

package/evals/RESULTS.md

@@ -1,9 +1,10 @@
 # Evaluation results — task-pipeline
 
-**Status: the suite is authored. One run is recorded and it was self-observed by the
-author; no blind run has been made on any model.** Recorded this way rather than left
-blank, because an empty results file and an unrun suite look identical, and this
-repository's own doctrine calls that the failure — a skip is not a pass.
+**Status: three suites authored (task-pipeline, evidence-docs, project-audit);
+one self-observed run and, since 2026-08-31, three blind trigger runs — one per
+model (haiku, sonnet, opus).** The instruction-following cases remain unexecuted
+and say so per run, because they need a full interactive session — a skip is not
+a pass, and a guessed verdict is worse than a vacant row.
 
 **The numbers below are computed, not asserted.** `python3 evals/run.py` counts the
 suite and the dated run headings in this file. A value typed here that disagrees with
@@ -39,11 +40,11 @@ or it belongs in a check.
 
 | Metric | Value | Computed by | As of |
 |---|---|---|---|
-| Evals authored | 15 | `python3 evals/run.py` → `suite: N evals` | 2026-08-08 |
-| Categories covered | 5 of 5 | the suite's own `category` fields | 2026-08-08 |
-| Dated runs recorded | **1** | `python3 evals/run.py` → `recorded runs: N` | 2026-08-08 |
-| …of those, **blind** | **0** | run headings not marked `self-observed` | 2026-08-08 |
-| Models exercised blind | **0 of 3** | distinct models across blind runs | 2026-08-08 |
+| Evals authored | 46 (three suites: task-pipeline 28, evidence-docs 9, project-audit 9) | `python3 evals/run.py` → `suite: N evals` | 2026-08-31 |
+| Categories covered | 5 of 5, per suite | the suite's own `category` fields | 2026-08-31 |
+| Dated runs recorded | **4** | `python3 evals/run.py` → `recorded runs: N` | 2026-08-31 |
+| …of those, **blind** | **3** | run headings not marked `self-observed` | 2026-08-31 |
+| Models exercised blind | **3 of 3** | distinct models across blind runs | 2026-08-31 |
 
 **The last three rows are the honest state of this skill's behavioural evidence**, and
 the split matters more than the total: a run the author watched, knowing the expected
@@ -67,6 +68,208 @@ green structural suite is never read as "the skill is known to work".
 Newest first. Each entry states the model, the task, and how the evidence was
 obtained — a self-observed run and a blind one are not the same claim.
 
+**Method (wave-3 subagent protocol, and its limits).** One FRESH general-purpose
+subagent per query per model, launched from a Claude Code harness with the model
+pinned. Each received: the query verbatim; the family's 28 skill
+names-with-descriptions (built once from the members' `SKILL.md` frontmatters,
+including evidence-docs and project-audit from this plugin); the instruction to
+answer with one skill name from that list, or `none`. Blind: no expected answer
+was named. Limits, stated rather than implied: the harness's OWN installed-skill
+inventory is also visible to a subagent's system prompt — a real coexistence
+environment rather than a cleanroom, and four early sonnet probes answered from
+it without opening the provided list (one chose `build-dashboard`, a skill
+outside the family; recorded as the miss it is, and the remaining prompts were
+tightened to "choose only from that file's list"). A trigger `pass` means the
+model NAMED the skill; it does not prove a full session loaded and obeyed the
+doctrine — the INSTR cases need exactly that and are recorded as **not
+reproducible from this harness**, not guessed.
+
+## 2026-08-31 · haiku · blind trigger probes, subagent protocol
+
+**39 of 42 scored cases passed** across the three suites' trigger-shaped
+categories (should_trigger, should_not_trigger; ambiguous and coexistence
+recorded unscored). Three misses, one shape: checkup/setup/prod-check phrasings («что у нас накопилось непроверенного?», «проверь документацию проекта…», «проверь, всё ли живо в проде…») routed to `project-audit` instead of task-pipeline's own checkup/setup modes — the two skills now share the "what is unverified/true" ground and the cheaper model takes the newer, narrower description.
+
+task-pipeline suite:
+
+| id | verdict | what happened |
+|---|---|---|
+| TRIG-01 | pass | named `task-pipeline` |
+| TRIG-02 | pass | named `task-pipeline` |
+| TRIG-03 | pass | named `task-pipeline` |
+| NOTRIG-01 | pass | answered `none` — did not route to the excluded skill |
+| NOTRIG-02 | pass | answered `none` — did not route to the excluded skill |
+| NOTRIG-03 | pass | answered `none` — did not route to the excluded skill |
+| AMB-01 | observed | answered `task-pipeline` (ambiguous/coexistence — recorded, not scored) |
+| AMB-02 | observed | answered `task-pipeline` (ambiguous/coexistence — recorded, not scored) |
+| COEX-01 | observed | answered `ux-flows` (ambiguous/coexistence — recorded, not scored) |
+| TRIG-04 | pass | named `task-pipeline` |
+| NOTRIG-04 | pass | answered `none` — did not route to the excluded skill |
+| TRIG-05 | fail | answered `project-audit` |
+| TRIG-06 | fail | answered `project-audit` |
+| NOTRIG-05 | pass | answered `none` — did not route to the excluded skill |
+| TRIG-07 | pass | named `task-pipeline` |
+| TRIG-08 | pass | named `task-pipeline` |
+| TRIG-09 | fail | answered `project-audit` |
+| TRIG-10 | pass | named `task-pipeline` |
+| NOTRIG-06 | pass | answered `seo-aeo-audit` — did not route to the excluded skill |
+| NOTRIG-07 | pass | answered `ux-audit` — did not route to the excluded skill |
+| NOTRIG-08 | pass | answered `make-skill` — did not route to the excluded skill |
+
+evidence-docs suite:
+
+| id | verdict | what happened |
+|---|---|---|
+| TRIG-01 | pass | named `evidence-docs` |
+| TRIG-02 | pass | named `evidence-docs` |
+| TRIG-03 | pass | named `evidence-docs` |
+| NOTRIG-01 | pass | answered `none` — did not route to the excluded skill |
+| NOTRIG-02 | pass | answered `none` — did not route to the excluded skill |
+| NOTRIG-03 | pass | answered `none` — did not route to the excluded skill |
+| AMB-01 | observed | answered `evidence-docs` (ambiguous/coexistence — recorded, not scored) |
+| COEX-01 | observed | answered `task-pipeline` (ambiguous/coexistence — recorded, not scored) |
+
+project-audit suite:
+
+| id | verdict | what happened |
+|---|---|---|
+| TRIG-01 | pass | named `project-audit` |
+| TRIG-02 | pass | named `project-audit` |
+| TRIG-03 | pass | named `project-audit` |
+| NOTRIG-01 | pass | answered `task-pipeline` — did not route to the excluded skill |
+| NOTRIG-02 | pass | answered `task-pipeline` — did not route to the excluded skill |
+| NOTRIG-03 | pass | answered `make-skill` — did not route to the excluded skill |
+| AMB-01 | observed | answered `project-audit` (ambiguous/coexistence — recorded, not scored) |
+| COEX-01 | observed | answered `task-pipeline` (ambiguous/coexistence — recorded, not scored) |
+
+INSTR-01…07 (task-pipeline) and INSTR-01 (evidence-docs, project-audit): **not
+reproducible from this harness** — each needs a full interactive pipeline run,
+and a guessed verdict would be the exact substitution this file exists to refuse.
+
+## 2026-08-31 · sonnet · blind trigger probes, subagent protocol
+
+**40 of 42 scored cases passed** across the three suites' trigger-shaped
+categories (should_trigger, should_not_trigger; ambiguous and coexistence
+recorded unscored). Two misses: TRIG-03 (`build a support-agent dashboard…`) answered `build-dashboard` — a skill OUTSIDE the offered list, from the harness's own inventory, before the choose-only-from-list tightening; TRIG-10 («посмотри PR #24 и скажи, что там не так») answered `none` — the PR-review findings class did not reach sonnet from the description alone.
+
+task-pipeline suite:
+
+| id | verdict | what happened |
+|---|---|---|
+| TRIG-01 | pass | named `task-pipeline:task-pipeline` |
+| TRIG-02 | pass | named `task-pipeline` |
+| TRIG-03 | fail | answered `build-dashboard` |
+| NOTRIG-01 | pass | answered `none` — did not route to the excluded skill |
+| NOTRIG-02 | pass | answered `none` — did not route to the excluded skill |
+| NOTRIG-03 | pass | answered `none` — did not route to the excluded skill |
+| AMB-01 | observed | answered `task-pipeline` (ambiguous/coexistence — recorded, not scored) |
+| AMB-02 | observed | answered `task-pipeline` (ambiguous/coexistence — recorded, not scored) |
+| COEX-01 | observed | answered `ux-flows` (ambiguous/coexistence — recorded, not scored) |
+| TRIG-04 | pass | named `task-pipeline` |
+| NOTRIG-04 | pass | answered `none` — did not route to the excluded skill |
+| TRIG-05 | pass | named `task-pipeline` |
+| TRIG-06 | pass | named `task-pipeline` |
+| NOTRIG-05 | pass | answered `none` — did not route to the excluded skill |
+| TRIG-07 | pass | named `task-pipeline` |
+| TRIG-08 | pass | named `task-pipeline` |
+| TRIG-09 | pass | named `task-pipeline` |
+| TRIG-10 | fail | answered `none` |
+| NOTRIG-06 | pass | answered `none` — did not route to the excluded skill |
+| NOTRIG-07 | pass | answered `super-ux:ux-audit` — did not route to the excluded skill |
+| NOTRIG-08 | pass | answered `make-skill:skill-audit` — did not route to the excluded skill |
+
+evidence-docs suite:
+
+| id | verdict | what happened |
+|---|---|---|
+| TRIG-01 | pass | named `evidence-docs` |
+| TRIG-02 | pass | named `evidence-docs` |
+| TRIG-03 | pass | named `evidence-docs` |
+| NOTRIG-01 | pass | answered `none` — did not route to the excluded skill |
+| NOTRIG-02 | pass | answered `none` — did not route to the excluded skill |
+| NOTRIG-03 | pass | answered `none` — did not route to the excluded skill |
+| AMB-01 | observed | answered `evidence-docs` (ambiguous/coexistence — recorded, not scored) |
+| COEX-01 | observed | answered `task-pipeline` (ambiguous/coexistence — recorded, not scored) |
+
+project-audit suite:
+
+| id | verdict | what happened |
+|---|---|---|
+| TRIG-01 | pass | named `task-pipeline:project-audit` |
+| TRIG-02 | pass | named `task-pipeline:project-audit` |
+| TRIG-03 | pass | named `project-audit` |
+| NOTRIG-01 | pass | answered `task-pipeline` — did not route to the excluded skill |
+| NOTRIG-02 | pass | answered `task-pipeline` — did not route to the excluded skill |
+| NOTRIG-03 | pass | answered `make-skill:skill-audit` — did not route to the excluded skill |
+| AMB-01 | observed | answered `task-pipeline:project-audit` (ambiguous/coexistence — recorded, not scored) |
+| COEX-01 | observed | answered `task-pipeline` (ambiguous/coexistence — recorded, not scored) |
+
+INSTR-01…07 (task-pipeline) and INSTR-01 (evidence-docs, project-audit): **not
+reproducible from this harness** — each needs a full interactive pipeline run,
+and a guessed verdict would be the exact substitution this file exists to refuse.
+
+## 2026-08-31 · opus · blind trigger probes, subagent protocol
+
+**42 of 42 scored cases passed** across the three suites' trigger-shaped
+categories (should_trigger, should_not_trigger; ambiguous and coexistence
+recorded unscored). No misses. All four audit near-misses routed away correctly (module audit → task-pipeline, skill standard → make-skill, landing-page traffic → seo-aeo-audit, UX conformance → ux-audit).
+
+task-pipeline suite:
+
+| id | verdict | what happened |
+|---|---|---|
+| TRIG-01 | pass | named `task-pipeline` |
+| TRIG-02 | pass | named `task-pipeline` |
+| TRIG-03 | pass | named `task-pipeline` |
+| NOTRIG-01 | pass | answered `none` — did not route to the excluded skill |
+| NOTRIG-02 | pass | answered `none` — did not route to the excluded skill |
+| NOTRIG-03 | pass | answered `none` — did not route to the excluded skill |
+| AMB-01 | observed | answered `task-pipeline` (ambiguous/coexistence — recorded, not scored) |
+| AMB-02 | observed | answered `task-pipeline` (ambiguous/coexistence — recorded, not scored) |
+| COEX-01 | observed | answered `ux-flows` (ambiguous/coexistence — recorded, not scored) |
+| TRIG-04 | pass | named `task-pipeline` |
+| NOTRIG-04 | pass | answered `none` — did not route to the excluded skill |
+| TRIG-05 | pass | named `task-pipeline` |
+| TRIG-06 | pass | named `task-pipeline` |
+| NOTRIG-05 | pass | answered `none` — did not route to the excluded skill |
+| TRIG-07 | pass | named `task-pipeline` |
+| TRIG-08 | pass | named `task-pipeline` |
+| TRIG-09 | pass | named `task-pipeline` |
+| TRIG-10 | pass | named `task-pipeline` |
+| NOTRIG-06 | pass | answered `seo-aeo-audit` — did not route to the excluded skill |
+| NOTRIG-07 | pass | answered `ux-audit` — did not route to the excluded skill |
+| NOTRIG-08 | pass | answered `make-skill` — did not route to the excluded skill |
+
+evidence-docs suite:
+
+| id | verdict | what happened |
+|---|---|---|
+| TRIG-01 | pass | named `evidence-docs` |
+| TRIG-02 | pass | named `evidence-docs` |
+| TRIG-03 | pass | named `evidence-docs` |
+| NOTRIG-01 | pass | answered `none` — did not route to the excluded skill |
+| NOTRIG-02 | pass | answered `none` — did not route to the excluded skill |
+| NOTRIG-03 | pass | answered `none` — did not route to the excluded skill |
+| AMB-01 | observed | answered `evidence-docs` (ambiguous/coexistence — recorded, not scored) |
+| COEX-01 | observed | answered `task-pipeline` (ambiguous/coexistence — recorded, not scored) |
+
+project-audit suite:
+
+| id | verdict | what happened |
+|---|---|---|
+| TRIG-01 | pass | named `project-audit` |
+| TRIG-02 | pass | named `project-audit` |
+| TRIG-03 | pass | named `project-audit` |
+| NOTRIG-01 | pass | answered `task-pipeline` — did not route to the excluded skill |
+| NOTRIG-02 | pass | answered `task-pipeline` — did not route to the excluded skill |
+| NOTRIG-03 | pass | answered `make-skill` — did not route to the excluded skill |
+| AMB-01 | observed | answered `project-audit` (ambiguous/coexistence — recorded, not scored) |
+| COEX-01 | observed | answered `project-audit` (ambiguous/coexistence — recorded, not scored) |
+
+INSTR-01…07 (task-pipeline) and INSTR-01 (evidence-docs, project-audit): **not
+reproducible from this harness** — each needs a full interactive pipeline run,
+and a guessed verdict would be the exact substitution this file exists to refuse.
+
 ## 2026-08-03 · opus · self-observed, not a blind run
 
 **Scope of this evidence.** The author ran the skill on a real task

package/evals/evidence-docs.evals.json

@@ -0,0 +1,109 @@
+{
+  "_note": "Behavioural evaluations for the evidence-docs skill — the ten-canon navigator that ships in this plugin. Same format and dimensions as task-pipeline.evals.json; the negatives are NEAR MISSES on purpose (a commit message and a code comment are the excluded surfaces closest to the trigger ground), because a control that shares no words with the trigger proves nothing about the boundary.",
+  "skill": "evidence-docs",
+  "models": ["haiku", "sonnet", "opus"],
+  "evals": [
+    {
+      "id": "TRIG-01",
+      "category": "should_trigger",
+      "skills": ["evidence-docs"],
+      "query": "запиши решение: внутренние сервисы переходят с REST на gRPC, обратной дороги нет",
+      "expected_behavior": [
+        "Invokes the evidence-docs skill (or its routed documentation doctrine), not a freehand note",
+        "The decision lands in the project's one decision register, append-only, with an id",
+        "The record carries its evidence and its date rather than only the conclusion"
+      ],
+      "why": "«записать решение» is a declared Russian trigger; the failure it guards is a decision written into chat instead of the register."
+    },
+    {
+      "id": "TRIG-02",
+      "category": "should_trigger",
+      "skills": ["evidence-docs"],
+      "query": "Write the acceptance report for the export migration — and make sure every claim in it is actually backed",
+      "expected_behavior": [
+        "Invokes the evidence-docs skill for the canon layer (a claim carries its address; numbers computed, never restated)",
+        "Each verified claim names the check that was seen deciding it; unverified ones are marked as such rather than dropped"
+      ],
+      "why": "An acceptance report is the archetypal will-be-read-as-true document; the canons are its standard."
+    },
+    {
+      "id": "TRIG-03",
+      "category": "should_trigger",
+      "skills": ["evidence-docs"],
+      "query": "Is this verified? The README claims the importer handles 10k rows per second.",
+      "expected_behavior": [
+        "Invokes the evidence-docs skill — the question is whether a claim is documentation or an assertion",
+        "Answers with the claim's evidence condition: what observable signal would license the number, and whether one exists",
+        "Does not re-assert the number without an address"
+      ],
+      "why": "'is this verified' is a declared trigger; the failure is grading the claim by plausibility instead of by evidence."
+    },
+    {
+      "id": "NOTRIG-01",
+      "category": "should_not_trigger",
+      "skills": ["evidence-docs"],
+      "query": "Write a commit message for this diff — it renames the exporter and fixes the retry backoff",
+      "expected_behavior": [
+        "Writes the commit message directly",
+        "Does NOT invoke the evidence-docs skill or demand file:line receipts for a commit message"
+      ],
+      "why": "Near miss by design: a commit message describes a change truthfully but is an excluded surface — demanding canons here teaches routing around them."
+    },
+    {
+      "id": "NOTRIG-02",
+      "category": "should_not_trigger",
+      "skills": ["evidence-docs"],
+      "query": "добавь комментарий в код, почему в этом месте ретрай с экспоненциальной задержкой",
+      "expected_behavior": [
+        "Writes the code comment directly",
+        "Does NOT invoke the evidence-docs skill — a code comment is an excluded surface by the skill's own Not-for list"
+      ],
+      "why": "Near miss: 'почему' invites an evidence reflex, and the boundary says a code comment is not documentation-read-as-true."
+    },
+    {
+      "id": "NOTRIG-03",
+      "category": "should_not_trigger",
+      "skills": ["evidence-docs"],
+      "query": "Draft some rough notes on how we might approach caching — just thinking out loud, no docs",
+      "expected_behavior": [
+        "Produces the draft directly",
+        "Does NOT apply the canons — 'без доков'/'no docs' is the declared opt-out, and a draft is outside the boundary anyway"
+      ],
+      "why": "The refusal phrase plus the draft exclusion; the failure is refusing exploratory writing for want of receipts."
+    },
+    {
+      "id": "AMB-01",
+      "category": "ambiguous",
+      "skills": ["evidence-docs"],
+      "query": "Update the README",
+      "expected_behavior": [
+        "Names the route: a developer README section is direct work, while a claim a reader will take as true (a benchmark, a guarantee) passes the canons",
+        "Does not silently pick one reading of the request"
+      ],
+      "why": "A README holds both excluded and covered content; the observable is naming the split, not the choice itself."
+    },
+    {
+      "id": "COEX-01",
+      "category": "coexistence",
+      "skills": ["evidence-docs", "task-pipeline"],
+      "query": "прогони миграцию через конвейер и запиши архитектурное решение в реестр",
+      "expected_behavior": [
+        "task-pipeline carries the change; the decision record goes through the documentation doctrine evidence-docs routes",
+        "One register entry with an id — not a second decision home invented for the run"
+      ],
+      "why": "The two skills share a plugin and a boundary: the pipeline owns delivery, evidence-docs owns what is written as true."
+    },
+    {
+      "id": "INSTR-01",
+      "category": "instruction_following",
+      "skills": ["evidence-docs"],
+      "query": "Record the decision that we drop Python 3.8 support, and note it was discussed in Slack",
+      "expected_behavior": [
+        "The record is appended to the existing register, never a new file beside it",
+        "A correction or later reversal would be appended, not edited over",
+        "The Slack discussion is cited as the decision's source, not pasted as its evidence"
+      ],
+      "why": "Append-only and one-home are the canons most often broken by a helpful rewrite."
+    }
+  ]
+}

package/evals/project-audit.evals.json

@@ -0,0 +1,108 @@
+{
+  "_note": "Behavioural evaluations for the project-audit skill. Same format and dimensions as task-pipeline.evals.json. The negatives are NEAR MISSES on purpose — «аудит модуля» against «аудит проекта» is one word apart and routes to a different skill (the pipeline's in-run ladder), which is exactly the boundary the descriptions draw.",
+  "skill": "project-audit",
+  "models": ["haiku", "sonnet", "opus"],
+  "evals": [
+    {
+      "id": "TRIG-01",
+      "category": "should_trigger",
+      "skills": ["project-audit"],
+      "query": "сделай аудит проекта — что реально готово, что наполовину, что сломано?",
+      "expected_behavior": [
+        "Invokes the project-audit skill, not the pipeline's in-run audit ladder",
+        "Starts with discovery (what the project IS) before choosing probes",
+        "Leaves the HTML report and the JSON sidecar; proposes board rows and commits nothing"
+      ],
+      "why": "«аудит проекта» is the declared trigger; the failure is running a fixed checklist or treating it as a change-task."
+    },
+    {
+      "id": "TRIG-02",
+      "category": "should_trigger",
+      "skills": ["project-audit"],
+      "query": "What is actually true of this project right now — what is finished, what is half-built, what has nobody looked at?",
+      "expected_behavior": [
+        "Invokes the project-audit skill — the subject is the whole project, not one change",
+        "Reads production evidence (published artefact vs source, CI history, telemetry presence), not only the working tree"
+      ],
+      "why": "The skill's own opening sentence as a user query; the failure is answering from the README."
+    },
+    {
+      "id": "TRIG-03",
+      "category": "should_trigger",
+      "skills": ["project-audit"],
+      "query": "Run a project health check on this repository and leave me the report",
+      "expected_behavior": [
+        "Invokes the project-audit skill",
+        "Blind probes are rendered as their own section with reasons — a probe that could not look is not a probe that found nothing"
+      ],
+      "why": "'project health check' is a declared trigger; the blind verdict is the design worth probing for."
+    },
+    {
+      "id": "NOTRIG-01",
+      "category": "should_not_trigger",
+      "skills": ["project-audit"],
+      "query": "сделай аудит модуля оплат",
+      "expected_behavior": [
+        "Routes to the pipeline's audit path (a finding that lands in the repository), not to project-audit",
+        "Does NOT start a cold whole-project discovery for a one-module question"
+      ],
+      "why": "Near miss by one word: «аудит проекта» is this skill, «аудит модуля» is one deliverable inside a run — the pipeline's own ladder."
+    },
+    {
+      "id": "NOTRIG-02",
+      "category": "should_not_trigger",
+      "skills": ["project-audit"],
+      "query": "Review PR #24 and tell me what is wrong with it",
+      "expected_behavior": [
+        "Routes to the pipeline's PR-review findings path or answers directly",
+        "Does NOT invoke project-audit — reviewing a diff is its declared Not-for"
+      ],
+      "why": "A diff has a change as its subject; project-audit's subject is the project."
+    },
+    {
+      "id": "NOTRIG-03",
+      "category": "should_not_trigger",
+      "skills": ["project-audit"],
+      "query": "проверь, соответствует ли этот скил стандарту Agent Skills",
+      "expected_behavior": [
+        "Routes to make-skill's audit (/skill-audit), not to project-audit",
+        "Does NOT run whole-project probes over a skill-construction question"
+      ],
+      "why": "The disambiguation table's own row: a skill's construction belongs to make-skill even when the word 'audit' appears."
+    },
+    {
+      "id": "AMB-01",
+      "category": "ambiguous",
+      "skills": ["project-audit"],
+      "query": "проверь проект",
+      "expected_behavior": [
+        "Names the route it is taking in one line — whole-project diagnosis (project-audit) versus a specific check the operator may mean",
+        "Does not silently start either the full audit or a random spot-check"
+      ],
+      "why": "Two words with no object; the observable is the named route, not the choice."
+    },
+    {
+      "id": "COEX-01",
+      "category": "coexistence",
+      "skills": ["project-audit", "task-pipeline"],
+      "query": "Audit the whole project, then fix the three worst things you find",
+      "expected_behavior": [
+        "project-audit produces the findings as proposed board rows, read-only",
+        "The fixes are carried by task-pipeline runs off those rows — the audit itself commits nothing"
+      ],
+      "why": "The seam the two skills share: diagnosis is read-only, delivery is the pipeline's; collapsing them makes the audit unrepeatable."
+    },
+    {
+      "id": "INSTR-01",
+      "category": "instruction_following",
+      "skills": ["project-audit"],
+      "query": "Audit this project",
+      "expected_behavior": [
+        "Discovery runs first and the probes are chosen from the profile, not from a fixed list",
+        "The three-verdict vocabulary is kept: clean, finding, blind — with blind reasons on the page",
+        "Findings leave priced with the board header's declared formula; effort never ranks"
+      ],
+      "why": "The procedure's own load-bearing steps, each of which a helpful shortcut would skip."
+    }
+  ]
+}