task-pipeline-skill 1.15.0 → 1.16.1

package/CHANGELOG.md

@@ -1,5 +1,49 @@
 # Changelog
 
+## v1.16.1 — 2026-08-06
+
+### Fixed — frontmatter that a regex called valid and a YAML parser silently dropped
+
+`evidence-docs`'s description contained *"read as true: a decision record"*. A
+colon-space inside a plain YAML scalar makes the value a nested mapping, so the official
+plugin validator reported the skill **loads with empty metadata — every frontmatter field
+silently dropped**, which for a skill means it never triggers. v1.16.0 published in that
+state.
+
+The guard that was supposed to catch it checked the frontmatter with a regular
+expression and passed: a check proving less than it claims, shipped in the release that
+publishes canon 6. It now rejects a plain scalar carrying a colon-space, across **every**
+`SKILL.md` in the plugin rather than only the new one — the class, not the instance.
+Guards 112 → 113.
+
+## v1.16.0 — 2026-08-06
+
+### Added — `evidence-docs`: a second skill in this plugin, and the router row it fills
+
+The canons landed in v1.15.0 with no way to reach them except through the pipeline. The
+global router already reserved a name for the question *"what is this proved by?"* —
+`evidence-docs` — and nothing resolved it. A routed name that resolves to nothing is the
+shape `learned.md` rule 14 forbids, in the routing table itself.
+
+`skills/evidence-docs/SKILL.md` is a **navigator, not a second copy**: the ten canons as
+a one-line index, a pointer to their one home in `documentation.md` → *The canons*, and a
+table of where to go next — set docs up from nothing, record a decision, avoid orphaning
+docs on a change, build a check that cannot lie, trust a mechanism that reports success,
+audit docs a project already has, seed a gate. It states its own boundary ("it will be
+read as true"), what is explicitly out (drafts, chat, commit messages, code comments) and
+its refusal phrase.
+
+Shipping it as a second skill **in the same plugin** rather than a separate repository is
+what keeps SSOT: one set of files, one release, and no copy to drift. `super-ux` already
+ships six skills from one plugin, so the shape is the family's own.
+
+### Guards — 108 → 112
+
+The index is held to the doctrine's own canon list, the pointer to the one home is
+required, the frontmatter is checked against the Agent Skills spec, and every relative
+link is resolved **from the navigator's own directory** — it sits one level over from
+everything it names, which is canon 4 enforced in the file that publishes canon 4.
+
 ## v1.15.0 — 2026-08-06
 
 ### Added — the ten canons: what makes a document evidence

package/CONTRIBUTING.md

@@ -235,7 +235,15 @@ commands and all three signal states — with a state missing, a graph that coul
 be measured prints like a fresh one.
 *(guard: `never requires it — a run passes intake quoting a`)*
 
-**31. Every invariant above names the guard that enforces it, and that guard exists.**
+**31. The evidence-docs navigator indexes the canons and never copies them.**
+`skills/evidence-docs/SKILL.md` is a second skill in the same plugin: the ten canons as
+a one-line index, a pointer to their one home, and a table of where to go next. The
+guard holds the index to the doctrine's own list, requires the pointer, and resolves
+every relative link **from the navigator's directory** — it sits one level over from
+everything it names, which is canon 4 in the file that publishes canon 4.
+*(guard: `index that has drifted from its doctrine`)*
+
+**32. Every invariant above names the guard that enforces it, and that guard exists.**
 This list claims to be *what the validator enforces*; it was eight guards behind when
 an audit measured it. A claim of enforcement is now checked like any other claim.
 *(guard: `whose message does not appear in`)* — and a cited literal must lie inside

package/README.md

@@ -116,6 +116,7 @@ until it is installed.
 
 | Stage | Built-in doctrine |
 |---|---|
+| **any claim read as true** | [`evidence-docs`](plugins/task-pipeline/skills/evidence-docs/SKILL.md) — **a second skill in this plugin**: the ten canons as an index, and where each is defined, enforced and seeded |
 | 0 Knowledge harvest | [`knowledge-sources.md`](plugins/task-pipeline/skills/task-pipeline/references/knowledge-sources.md) — source list, the wiki, the ledger, the stage-9 loop-back |
 | 0 Intake grill | [`grill.md`](plugins/task-pipeline/skills/task-pipeline/references/grill.md) — interview loop, domain awareness, autonomy sweep |
 | 2 Brainstorm | [`brainstorm.md`](plugins/task-pipeline/skills/task-pipeline/references/brainstorm.md) — approaches, YAGNI, the no-code-before-approval gate |

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** | 1.15.0 |
+| **Version** | 1.16.1 |
 | **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. 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 (15 evals, 5 categories). **Never executed** — see [`evals/RESULTS.md`](evals/RESULTS.md) |

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "task-pipeline-skill",
-  "version": "1.15.0",
+  "version": "1.16.1",
   "description": "Full-cycle delivery pipeline for coding agents: a mandatory built-in intake grill, then 10 gated stages (docs, brainstorm+decompose, spec, plan, build, tests, lint/deploy, post-deploy, docs/wiki, acceptance). Every stage's doctrine ships inside the skill — no companion plugin required. This package is the installer CLI.",
   "bin": {
     "task-pipeline": "bin/task-pipeline.js"

package/plugins/task-pipeline/.claude-plugin/plugin.json

@@ -2,7 +2,7 @@
   "name": "task-pipeline",
   "displayName": "Task Pipeline",
   "description": "Runs a substantial task through a mandatory built-in intake grill, then 10 gated stages (docs, brainstorm+decompose, spec, plan, subagent build, tests, lint/deploy, post-deploy, docs/wiki, acceptance). Every stage's doctrine is built into the skill — no companion plugin required — with typed auto/manual gates, a frozen requirement spine that must close with evidence, a loop guard that breaks churn, one provider-agnostic model confirmed up front, and an optional super-ux UX track for user-facing work.",
-  "version": "1.15.0",
+  "version": "1.16.1",
   "author": {
     "name": "ssheleg",
     "url": "https://x.com/sshlg93"

package/plugins/task-pipeline/skills/evidence-docs/SKILL.md

@@ -0,0 +1,68 @@
+---
+name: evidence-docs
+description: Applies the ten canons of evidence-backed documentation — what makes a claim documentation rather than an assertion — and routes to the doctrine that enforces each one. Use when writing or reviewing anything that will be read as true — a decision record, a README, an acceptance report, a runbook, a changelog entry, an audit finding, or any claim that something was verified. Also use when a project needs a documentation gate, a decision register, a propagation matrix, or a retrospective that outlives its author. Not for drafts, chat answers, commit messages or code comments.
+---
+
+# Evidence-backed documentation
+
+**A claim is documentation only when it carries the means to check it.** This skill is
+the standard and the map: ten canons, and where each is defined, enforced and seeded.
+
+It is a **navigator, not a second copy**. Every law below has exactly one home — that is
+canon 3, and a navigator that restated the doctrine would break the rule it is indexing.
+The full statement of each canon, its rationale and its enforcement live in
+[`documentation.md`](../task-pipeline/references/documentation.md) → *The canons*.
+
+## The ten canons
+
+1. **A claim carries its address** — `file:line`, a command with its output, a test name; a lesson names its commit.
+2. **Numbers are computed, never restated.**
+3. **Every fact has exactly one home** — others link, never restate.
+4. **A reference resolves from where the document is read** — not from where it lives.
+5. **Green nobody watched turn red is not evidence.**
+6. **A check proves its scope and nothing beyond it.**
+7. **Silence is not a pass** — ask what a mechanism prints when it did not look.
+8. **An estimate is never announced as a measurement** — a rule states its evidence condition.
+9. **What was not checked is printed beside what was.**
+10. **The document ships in the change that made it true** — and a correction is appended, never written over.
+
+They are **epistemic**: what makes a claim documentation. The operational layer — what to
+do at a given trigger, with a check and an exit criterion — is
+[`learned.md`](../task-pipeline/references/learned.md). When the two seem to say the same
+thing, the canon is the *why* and the rule is the *how*.
+
+## Where next
+
+| You are about to… | Read | Because |
+|---|---|---|
+| set a project's documentation up from nothing | [`documentation.md`](../task-pipeline/references/documentation.md) → *The inventory* | four questions answered before the first line of work |
+| record a decision so it survives its author | *Registers and ids* + [`templates/decisions.md`](../task-pipeline/templates/decisions.md) | append-only ids, edge markers, one decision home |
+| change something and not orphan the docs | *The Doc Loop* + *The propagation matrix* | which documents a change owes, starting with the meta-row |
+| decide where a fact belongs | *Single source of truth* | two homes disagree the day one of them is updated |
+| build a check that cannot lie | [`gates.md`](../task-pipeline/references/gates.md) | three axes, the enforcement ladder, progressive arming, probing |
+| trust a mechanism that reports success | [`gates.md`](../task-pipeline/references/gates.md) → *False success* | the failure that removes the reason to look |
+| wire a check into the agent's own tooling | [`hooks.md`](../task-pipeline/references/hooks.md) | the hook contract, and why a crashed guard **allows** the action |
+| audit documentation a project already has | [`setup.md`](../task-pipeline/references/setup.md) | seven passes, cheapest first, output is a fix plan |
+| carry a lesson to the next run | [`retrospective.md`](../task-pipeline/references/retrospective.md) | prune first, cap of ten, every lesson names its commit |
+| seed a gate into a host project | [`templates/docgate.sh`](../task-pipeline/templates/docgate.sh) | it seeds **green**: dormant where there is no input yet |
+| take a whole change through to acceptance | [`task-pipeline`](../task-pipeline/SKILL.md) | this skill is the standard; that one is how a change reaches the repository |
+
+## When this applies
+
+**The boundary is "it will be read as true."** A decision record, a README, an acceptance
+report, a runbook, a changelog for users, an audit finding, a claim that something was
+verified.
+
+**Not through this skill:** a draft, thinking out loud, an answer in chat, a commit
+message, a code comment. Demanding a `file:line` for "let me check that" is the fastest
+way to teach an agent to route around the rule where it actually protects something.
+
+**Refusal phrase — "без доков" / "on my word".** It works on a task that would otherwise
+pass through here: do it directly and **say out loud** that the claim is unbacked, rather
+than presenting an estimate as a measurement (canon 8).
+
+## The one test
+
+Before a document ships, read it for the sentence that would embarrass you if someone
+asked *"how do you know?"* — and either give that sentence its address, or delete it.
+Everything above is that question, made mechanical.

package/plugins/task-pipeline/skills/task-pipeline/SKILL.md

@@ -47,6 +47,7 @@ gate stops until it is installed.
 | Stage | Built-in doctrine |
 |---|---|
 | 0 + 9 + any settled decision · The documentation system | [`references/documentation.md`](references/documentation.md) |
+| any claim that will be read as true · The canons, and where each is enforced | [`evidence-docs`](../evidence-docs/SKILL.md) — the sibling skill in this plugin |
 | 6–10 + any check you write · Gates | [`references/gates.md`](references/gates.md) |
 | any agent-time enforcement · Hooks | [`references/hooks.md`](references/hooks.md) |
 | 0 Knowledge harvest (pre-grill) | [`references/knowledge-sources.md`](references/knowledge-sources.md) |

package/plugins/task-pipeline/skills/task-pipeline/references/portability.md

@@ -67,6 +67,7 @@ a row pointing outside the bundle is the defect this file exists to catch.
 | Workspace isolation, the subagent loop, who may write the register | `references/build.md` |
 | The review rubric, diff packages, the three verdicts | `references/review.md` |
 | **False success** — the class, its known shapes and its two rules | `references/gates.md` |
+| **The canons** — what makes a claim documentation, and the index that routes to each | `references/documentation.md`, `../evidence-docs/SKILL.md` |
 | **Effect verification** — the `verified-by:` contract and the rubric item that blocks | `references/build.md`, `references/review.md` |
 | The TDD iron law and the suite gate | `references/tdd.md` |
 | The REQ coverage table, evidence rules, the closing question | `references/acceptance.md` |