task-pipeline-skill 1.85.2 → 1.86.3

package/evals/cases/task-pipeline.json

@@ -0,0 +1,191 @@
+{
+ "contract": "outcome-case/1 (schemas/outcome-case.schema.json + test/outcome_harness.py in ssheleg/sshlg-skills)",
+ "note": "Outcome corpus for task-pipeline (FIX-EV-01.11). Judged on ARTIFACTS via the family harness: the runner records the actual output oracle verdict AND the raw result per case; with/without-skill arms are the harness's baseline contract. Nothing in the production skill was changed for grader convenience.",
+ "arms": {
+  "baseline": "same prompts, skill absent",
+  "current": "same prompts, skill installed"
+ },
+ "cases": [
+  {
+   "schema_version": "outcome-case/1",
+   "id": "TP-OUT-001-full-brief-no-extra-questions",
+   "skill": "task-pipeline",
+   "prompt": {
+    "text": "Given a fully specified brief (exact file, exact change, acceptance stated), run the pipeline and record in run-log.md that it asked ZERO clarifying questions and went straight to the plan (TP-01)."
+   },
+   "environment": {
+    "model": "inherit",
+    "host": "any",
+    "case_digest": "b69415f8f9515946adf5cacfe4e1e735885351d81f352444a8ab9885bc46eb96"
+   },
+   "checks": {
+    "tool": [
+     {
+      "name": "python3 present",
+      "command": "python3 -c 'pass'"
+     }
+    ],
+    "load_trace": {
+     "expect_loaded": [
+      "task-pipeline"
+     ],
+     "expect_not_loaded": []
+    },
+    "outcome": [
+     {
+      "name": "run-log exists",
+      "kind": "artifact-exists",
+      "target": "run-log.md"
+     },
+     {
+      "name": "a full brief triggers no extra questions (TP-01)",
+      "kind": "artifact-contains",
+      "target": "run-log.md",
+      "expect": "0 questions"
+     }
+    ]
+   }
+  },
+  {
+   "schema_version": "outcome-case/1",
+   "id": "TP-OUT-002-negative-routing",
+   "skill": "task-pipeline",
+   "prompt": {
+    "text": "Explain in two sentences what a webhook is."
+   },
+   "environment": {
+    "model": "inherit",
+    "host": "any",
+    "case_digest": "a5da94aa03520bb6226ea88328a75ab6d7e3985c73a0e90a1379bf168fead57e"
+   },
+   "checks": {
+    "tool": [
+     {
+      "name": "python3 present",
+      "command": "python3 -c 'pass'"
+     }
+    ],
+    "load_trace": {
+     "expect_loaded": [],
+     "expect_not_loaded": [
+      "task-pipeline"
+     ]
+    },
+    "outcome": [
+     {
+      "name": "no pipeline artifact appears",
+      "kind": "command-exit-0",
+      "target": "test ! -f run-log.md"
+     }
+    ]
+   }
+  },
+  {
+   "schema_version": "outcome-case/1",
+   "id": "TP-OUT-003-custom-profile-no-forced-stages",
+   "skill": "task-pipeline",
+   "prompt": {
+    "text": "Validate a three-stage custom pipeline profile — it must pass without gaining forced stage 0/7/10, while the kernel invariants are still checked; write profile-check.md (TP-03)."
+   },
+   "environment": {
+    "model": "inherit",
+    "host": "any",
+    "case_digest": "5b1b98d485c4dc61cf6f1acf7bd071cb01ef512c5c802eafd6b6f450cb7dd38c"
+   },
+   "checks": {
+    "tool": [
+     {
+      "name": "python3 present",
+      "command": "python3 -c 'pass'"
+     }
+    ],
+    "load_trace": {
+     "expect_loaded": [
+      "task-pipeline"
+     ],
+     "expect_not_loaded": []
+    },
+    "outcome": [
+     {
+      "name": "a custom profile keeps its stages (TP-03)",
+      "kind": "artifact-contains",
+      "target": "profile-check.md",
+      "expect": "three-stage"
+     }
+    ]
+   }
+  },
+  {
+   "schema_version": "outcome-case/1",
+   "id": "TP-OUT-004-unused-rule-not-auto-removed",
+   "skill": "task-pipeline",
+   "prompt": {
+    "text": "Five runs happened with no payments. Do NOT remove the payment-safety rule for being unused; explain every removal you do make; write pruning.md (TP-04)."
+   },
+   "environment": {
+    "model": "inherit",
+    "host": "any",
+    "case_digest": "1e8f20941ef80ebc9a1a6c399b042c7a683564c30419b5bae1f585a9a3671123"
+   },
+   "checks": {
+    "tool": [
+     {
+      "name": "python3 present",
+      "command": "python3 -c 'pass'"
+     }
+    ],
+    "load_trace": {
+     "expect_loaded": [
+      "task-pipeline"
+     ],
+     "expect_not_loaded": []
+    },
+    "outcome": [
+     {
+      "name": "an unused rule is not auto-removed (TP-04)",
+      "kind": "artifact-contains",
+      "target": "pruning.md",
+      "expect": "not removed"
+     }
+    ]
+   }
+  },
+  {
+   "schema_version": "outcome-case/1",
+   "id": "TP-OUT-005-scenarios-without-super-ux",
+   "skill": "task-pipeline",
+   "prompt": {
+    "text": "With valid docs/ux/scenarios.md present but super-ux NOT installed, run the pipeline; it should honour the scenarios contract and complete; write scenario-check.md (TP-02)."
+   },
+   "environment": {
+    "model": "inherit",
+    "host": "any",
+    "case_digest": "d28ba54adac84d3234566b3eeb566a527b75aeb337fc4328a3455cf3448f328a"
+   },
+   "checks": {
+    "tool": [
+     {
+      "name": "python3 present",
+      "command": "python3 -c 'pass'"
+     }
+    ],
+    "load_trace": {
+     "expect_loaded": [
+      "task-pipeline"
+     ],
+     "expect_not_loaded": [
+      "super-ux"
+     ]
+    },
+    "outcome": [
+     {
+      "name": "valid scenarios satisfy the contract without super-ux (TP-02)",
+      "kind": "artifact-contains",
+      "target": "scenario-check.md",
+      "expect": "scenarios"
+     }
+    ]
+   }
+  }
+ ]
+}

package/package.json

@@ -1,13 +1,13 @@
 {
   "name": "task-pipeline-skill",
-  "version": "1.85.2",
+  "version": "1.86.3",
   "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"
   },
   "scripts": {
-    "test": "python3 test/validate.py && python3 test/graph_test.py && python3 test/project_audit_test.py",
-    "test:all": "python3 test/validate.py && python3 test/graph_test.py && python3 test/project_audit_test.py && python3 test/negatives.py && npm run test:certify && npm run test:exposure && npm run test:probe && npm run test:anchors && npm run test:runner && npm run test:hooks && npm run test:artifacts && npm run test:docs",
+    "test": "python3 test/validate.py && python3 test/graph_test.py && python3 test/project_audit_test.py && python3 test/packet_schema_test.py && python3 test/browser_claims_test.py && npm run test:audit-regressions",
+    "test:all": "python3 test/validate.py && python3 test/graph_test.py && python3 test/project_audit_test.py && python3 test/packet_schema_test.py && python3 test/browser_claims_test.py && python3 test/negatives.py && npm run test:certify && npm run test:exposure && npm run test:probe && npm run test:anchors && npm run test:runner && npm run test:hooks && npm run test:artifacts && npm run test:docs && npm run test:audit-regressions",
     "test:negatives": "python3 test/negatives.py",
     "test:exposure": "python3 test/exposure_test.py",
     "test:probe": "python3 test/probe.py --self-test",
@@ -17,7 +17,8 @@
     "test:artifacts": "python3 test/artifact_root_test.py && python3 test/migrate_artifacts_test.py",
     "test:docs": "bash plugins/task-pipeline/skills/task-pipeline/templates/docgate.sh",
     "test:certify": "python3 test/certify_mutations.py",
-    "test:audit": "python3 test/project_audit_test.py"
+    "test:audit": "python3 test/project_audit_test.py",
+    "test:audit-regressions": "for t in test/audit_regressions/*.py; do python3 \"$t\" || exit 1; done"
   },
   "files": [
     "bin",

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

@@ -3,7 +3,7 @@
   "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/judgment/manual gates, a frozen requirement spine that closes with evidence, a work board and a verification ledger that outlive a run, an exposure line naming what shipped unconfirmed, a progress rail computed from the project's own config, a loop guard whose review ceiling measures rather than stops, and stage-3 tracks for what a product does, how it sounds and how it looks. Two modes need no task: `checkup` (what is unverified) and `setup` (audit existing docs). Retro insights can publish upstream as issues, opt-in and redacted.",
-  "version": "1.85.2",
+  "version": "1.86.3",
   "author": {
     "name": "ssheleg",
     "url": "https://x.com/sshlg93"

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

@@ -13,7 +13,7 @@ the standard and the map: ten canons, and where each is defined, enforced and se
 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*.
+[`documentation.md`](references/documentation.md) → *The canons*.
 
 ## The ten canons
 
@@ -34,25 +34,25 @@ The full statement of each canon, its rationale and its enforcement live in
 
 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
+[`learned.md`](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 |
+| set a project's documentation up from nothing | [`documentation.md`](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`](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) | stamp first (the cold trigger reads it), then prune to a 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 |
+| build a check that cannot lie | [`gates.md`](references/gates.md) | three axes, the enforcement ladder, progressive arming, probing |
+| trust a mechanism that reports success | [`gates.md`](references/gates.md) → *False success* | the failure that removes the reason to look |
+| wire a check into the agent's own tooling | [`hooks.md`](references/hooks.md) | the hook contract, and why a crashed guard **allows** the action |
+| audit documentation a project already has | [`setup.md`](references/setup.md) | seven passes, cheapest first, output is a fix plan |
+| carry a lesson to the next run | [`retrospective.md`](references/retrospective.md) | stamp first (the cold trigger reads it), then prune to a cap of ten; every lesson names its commit |
+| seed a gate into a host project | [`templates/docgate.sh`](templates/docgate.sh) | it seeds **green**: dormant where there is no input yet |
 | claim that an **agent** behaves | `tdd.md` → *When the thing under test is an agent* — named rather than linked, because this navigator's out-of-directory links break wherever a packager ships this skill alone | the address is a trace id and the assertion that ran (canon 1); a judge nobody watched disagree is a green nobody watched turn red (canon 5) |
-| 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 |
+| take a whole change through to acceptance | the `task-pipeline` skill (install it separately) | this skill is the standard; that one is how a change reaches the repository |
 
 ## When this applies
 
@@ -103,3 +103,8 @@ address, delete it, or **mark it as an unbacked claim the operator chose to make
 it**. The third option is not a loophole; it is the reason the other two are worth
 anything. A rule with no way to proceed under it becomes a rule people route around, and
 then nothing carries an address.
+
+**Editing these references.** The files under `references/` and `templates/` here are
+GENERATED copies, so a single-skill install of this skill resolves every link without a
+neighbouring checkout. Edit the source home, never the copy — which file is generated,
+from where, and how to re-sync: [`GENERATED.md`](references/GENERATED.md).

package/plugins/task-pipeline/skills/evidence-docs/references/GENERATED.md

@@ -0,0 +1,8 @@
+# Generated copies — do not edit here
+
+The files in this directory (and `../templates/`) are GENERATED (a deterministic transform: in-set links stay relative, out-of-set links point at the source home’s canonical URL) from the
+source home `skills/task-pipeline/references/` and `skills/task-pipeline/templates/`
+so an isolated single-skill install of evidence-docs resolves every required
+link without a neighbouring checkout (FIX-ED-01.01). Edit the source home and
+re-run `python3 test/audit_regressions/fix-ed-01.01.py --sync`;
+`test/validate.py`'s regression stage fails when a copy drifts.