harnessed 3.5.0 → 3.6.0

package/dist/index.mjs

@@ -1,6 +1,6 @@
 // package.json
 var package_default = {
-  version: "3.5.0"};
+  version: "3.6.0"};
 
 // src/index.ts
 var VERSION = package_default.version;

package/dist/index.mjs.map

@@ -1 +1 @@
-{"version":3,"sources":["../package.json","../src/index.ts"],"names":[],"mappings":";AAAA,IAAA,eAAA,GAAA;AAAA,EAEE,OAAA,EAAW,OA8Fb,CAAA;;;AC3FO,IAAM,UAAU,eAAA,CAAI","file":"index.mjs","sourcesContent":["{\n  \"name\": \"harnessed\",\n  \"version\": \"3.5.0\",\n  \"description\": \"AI coding harness package manager + composition orchestrator\",\n  \"type\": \"module\",\n  \"license\": \"Apache-2.0\",\n  \"author\": \"easyinplay\",\n  \"repository\": {\n    \"type\": \"git\",\n    \"url\": \"https://github.com/easyinplay/harnessed.git\"\n  },\n  \"homepage\": \"https://github.com/easyinplay/harnessed#readme\",\n  \"bugs\": \"https://github.com/easyinplay/harnessed/issues\",\n  \"keywords\": [\n    \"claude-code\",\n    \"ai-harness\",\n    \"package-manager\",\n    \"composition\",\n    \"skill-pack\",\n    \"mcp\",\n    \"orchestrator\"\n  ],\n  \"engines\": {\n    \"node\": \">=22.0.0\"\n  },\n  \"packageManager\": \"pnpm@10.12.0\",\n  \"bin\": {\n    \"harnessed\": \"./dist/cli.mjs\"\n  },\n  \"main\": \"./dist/index.mjs\",\n  \"types\": \"./dist/index.d.ts\",\n  \"exports\": {\n    \".\": {\n      \"types\": \"./dist/index.d.ts\",\n      \"import\": \"./dist/index.mjs\",\n      \"default\": \"./dist/index.mjs\"\n    },\n    \"./schemas\": {\n      \"types\": \"./dist/schemas/index.d.ts\",\n      \"import\": \"./dist/schemas/index.mjs\"\n    },\n    \"./package.json\": \"./package.json\"\n  },\n  \"files\": [\n    \"dist\",\n    \"manifests\",\n    \"workflows\",\n    \"routing\",\n    \"config-templates\",\n    \"schemas\",\n    \"README.md\",\n    \"LICENSE\",\n    \"NOTICE\"\n  ],\n  \"scripts\": {\n    \"dev\": \"tsup --watch\",\n    \"build\": \"tsc --noEmit && tsup\",\n    \"build:schema\": \"node ./scripts/build-schema.mjs\",\n    \"validate:schema\": \"node ./scripts/validate-schema.mjs\",\n    \"typecheck\": \"tsc --noEmit\",\n    \"test\": \"vitest run --passWithNoTests\",\n    \"test:watch\": \"vitest\",\n    \"test:coverage\": \"vitest run --coverage --passWithNoTests\",\n    \"bench\": \"vitest bench --run\",\n    \"lint\": \"biome check .\",\n    \"lint:fix\": \"biome check --write .\",\n    \"format\": \"biome format --write .\"\n  },\n  \"dependencies\": {\n    \"@anthropic-ai/claude-agent-sdk\": \"0.3.142\",\n    \"@clack/prompts\": \"^0.10.1\",\n    \"@sinclair/typebox\": \"^0.34.49\",\n    \"ajv\": \"^8.20.0\",\n    \"ajv-errors\": \"^3.0.0\",\n    \"ajv-formats\": \"^3.0.1\",\n    \"commander\": \"^13.0.0\",\n    \"diff\": \"^9.0.0\",\n    \"expr-eval\": \"^2.0.2\",\n    \"picocolors\": \"^1.1.1\",\n    \"proper-lockfile\": \"^4.1.2\",\n    \"yaml\": \"^2.9.0\"\n  },\n  \"devDependencies\": {\n    \"@biomejs/biome\": \"^2.0.0\",\n    \"@types/node\": \"^22.10.0\",\n    \"@types/proper-lockfile\": \"^4.1.4\",\n    \"@vitest/coverage-v8\": \"^4.0.0\",\n    \"tsup\": \"^8.3.0\",\n    \"typescript\": \"^5.6.0\",\n    \"vitest\": \"^4.0.0\"\n  },\n  \"pnpm\": {\n    \"onlyBuiltDependencies\": [\n      \"esbuild\"\n    ]\n  }\n}\n","// Main library entry — re-exports public APIs.\n// phase 1.1 batch 1: skeleton only; schema validator wired in batch 2 (T3+).\n\nimport pkg from '../package.json' with { type: 'json' }\n\nexport const VERSION = pkg.version\n"]}
+{"version":3,"sources":["../package.json","../src/index.ts"],"names":[],"mappings":";AAAA,IAAA,eAAA,GAAA;AAAA,EAEE,OAAA,EAAW,OA+Fb,CAAA;;;AC5FO,IAAM,UAAU,eAAA,CAAI","file":"index.mjs","sourcesContent":["{\n  \"name\": \"harnessed\",\n  \"version\": \"3.6.0\",\n  \"description\": \"AI coding harness package manager + composition orchestrator\",\n  \"type\": \"module\",\n  \"license\": \"Apache-2.0\",\n  \"author\": \"easyinplay\",\n  \"repository\": {\n    \"type\": \"git\",\n    \"url\": \"https://github.com/easyinplay/harnessed.git\"\n  },\n  \"homepage\": \"https://github.com/easyinplay/harnessed#readme\",\n  \"bugs\": \"https://github.com/easyinplay/harnessed/issues\",\n  \"keywords\": [\n    \"claude-code\",\n    \"ai-harness\",\n    \"package-manager\",\n    \"composition\",\n    \"skill-pack\",\n    \"mcp\",\n    \"orchestrator\"\n  ],\n  \"engines\": {\n    \"node\": \">=22.0.0\"\n  },\n  \"packageManager\": \"pnpm@10.12.0\",\n  \"bin\": {\n    \"harnessed\": \"./dist/cli.mjs\"\n  },\n  \"main\": \"./dist/index.mjs\",\n  \"types\": \"./dist/index.d.ts\",\n  \"exports\": {\n    \".\": {\n      \"types\": \"./dist/index.d.ts\",\n      \"import\": \"./dist/index.mjs\",\n      \"default\": \"./dist/index.mjs\"\n    },\n    \"./schemas\": {\n      \"types\": \"./dist/schemas/index.d.ts\",\n      \"import\": \"./dist/schemas/index.mjs\"\n    },\n    \"./package.json\": \"./package.json\"\n  },\n  \"files\": [\n    \"dist\",\n    \"manifests\",\n    \"workflows\",\n    \"routing\",\n    \"config-templates\",\n    \"schemas\",\n    \"README.md\",\n    \"LICENSE\",\n    \"NOTICE\",\n    \"THIRD-PARTY-NOTICES.md\"\n  ],\n  \"scripts\": {\n    \"dev\": \"tsup --watch\",\n    \"build\": \"tsc --noEmit && tsup\",\n    \"build:schema\": \"node ./scripts/build-schema.mjs\",\n    \"validate:schema\": \"node ./scripts/validate-schema.mjs\",\n    \"typecheck\": \"tsc --noEmit\",\n    \"test\": \"vitest run --passWithNoTests\",\n    \"test:watch\": \"vitest\",\n    \"test:coverage\": \"vitest run --coverage --passWithNoTests\",\n    \"bench\": \"vitest bench --run\",\n    \"lint\": \"biome check .\",\n    \"lint:fix\": \"biome check --write .\",\n    \"format\": \"biome format --write .\"\n  },\n  \"dependencies\": {\n    \"@anthropic-ai/claude-agent-sdk\": \"0.3.142\",\n    \"@clack/prompts\": \"^0.10.1\",\n    \"@sinclair/typebox\": \"^0.34.49\",\n    \"ajv\": \"^8.20.0\",\n    \"ajv-errors\": \"^3.0.0\",\n    \"ajv-formats\": \"^3.0.1\",\n    \"commander\": \"^13.0.0\",\n    \"diff\": \"^9.0.0\",\n    \"expr-eval\": \"^2.0.2\",\n    \"picocolors\": \"^1.1.1\",\n    \"proper-lockfile\": \"^4.1.2\",\n    \"yaml\": \"^2.9.0\"\n  },\n  \"devDependencies\": {\n    \"@biomejs/biome\": \"^2.0.0\",\n    \"@types/node\": \"^22.10.0\",\n    \"@types/proper-lockfile\": \"^4.1.4\",\n    \"@vitest/coverage-v8\": \"^4.0.0\",\n    \"tsup\": \"^8.3.0\",\n    \"typescript\": \"^5.6.0\",\n    \"vitest\": \"^4.0.0\"\n  },\n  \"pnpm\": {\n    \"onlyBuiltDependencies\": [\n      \"esbuild\"\n    ]\n  }\n}\n","// Main library entry — re-exports public APIs.\n// phase 1.1 batch 1: skeleton only; schema validator wired in batch 2 (T3+).\n\nimport pkg from '../package.json' with { type: 'json' }\n\nexport const VERSION = pkg.version\n"]}

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "harnessed",
-  "version": "3.5.0",
+  "version": "3.6.0",
   "description": "AI coding harness package manager + composition orchestrator",
   "type": "module",
   "license": "Apache-2.0",
@@ -50,7 +50,8 @@
     "schemas",
     "README.md",
     "LICENSE",
-    "NOTICE"
+    "NOTICE",
+    "THIRD-PARTY-NOTICES.md"
   ],
   "scripts": {
     "dev": "tsup --watch",

package/workflows/disciplines/operational.yaml

@@ -59,3 +59,21 @@ rules:
     enforcement: warn
     trigger: cmd.requires_approval == true AND session.has_prior_approval == true
     check_method: heuristic
+
+  # v3.6.0 Phase 3 — transparent-skip discipline (P0b 下半,Audit § fallback
+  # 三条铁律 "拿不准 → 倾向跳过 + 透明声明"). prompt-inject method delivered
+  # via src/workflow/run.ts TRANSPARENT_SKIP_RULES const appended to
+  # criticalSystemReminder_EXPERIMENTAL alongside ESCALATION_RULES (v3.5.0
+  # Phase 2 sister). Spawned subagent reads the rule + emits the verbatim
+  # skip message when gate context is ambiguous instead of silent execution.
+  - id: transparent-skip-on-low-confidence
+    description: |
+      When a phase gate condition cannot be confidently evaluated (e.g.
+      expected context fields missing, default-valued, or contradictory),
+      prefer skip + transparent explanation over silent execution.
+      Verbatim format: "这次跳过了 <phase>, 因为 <reason>. 如果你认为
+      需要请明说" / English: "Skipped <phase> because <reason>. Tell me
+      if you actually need it."
+    enforcement: warn
+    trigger: gate_evaluation_low_confidence
+    check_method: prompt-inject

package/workflows/judgments/user-overrides.yaml

@@ -0,0 +1,82 @@
+# workflows/judgments/user-overrides.yaml
+# v3.6.0 Phase 3 — user-override keyword → trigger gate refs lookup
+# (P0b 上半,Audit § fallback 三条铁律 "用户明示 → 覆盖判据" mechanism)
+#
+# Runtime: CLI extracts keywords from user task description, matches against
+# `keywords` substring patterns, collects matched `triggers[]` into
+# gateContext.user_overrides[]. judgmentResolver pre-checks user_overrides[]
+# before expression evaluation — if gateRef in user_overrides → fires=true bypass.
+#
+# Cross-validation status (Wave 1 灰区 #1/#2/#3 resolved per user ack 2026-05-25):
+#   - arch-review.triggers[0] points to stage-routing.plan-architecture-delegate
+#     (no architecture-gate.yaml exists; semantically nearest existing entry per
+#     灰区 #2 Option C — no scope creep)
+#   - phase-discuss.triggers[0] points to phase-gate.gsd-discuss-phase (no
+#     `gray-areas` entry exists in phase-gate.yaml; renamed per 灰区 #1/#3
+#     Option A — naming drift fix, semantic equivalent)
+
+schema_version: harnessed.user-overrides.v1
+
+overrides:
+  - id: brainstorm
+    keywords:
+      - "先 brainstorm"
+      - "brainstorm 一下"
+      - "讨论一下"
+      - "先想想"
+      - "先讨论"
+      - "brainstorm first"
+      - "let's brainstorm"
+    triggers:
+      - judgments.subtask-gate.brainstorming.fires
+      - judgments.stage-routing.discuss-subtask-delegate.fires
+
+  - id: strategic-review
+    keywords:
+      - "跑 office-hours"
+      - "office-hours"
+      - "找 CEO"
+      - "战略层"
+      - "战略评估"
+      - "plan-ceo-review"
+    triggers:
+      - judgments.strategic-gate.office-hours.fires
+      - judgments.strategic-gate.plan-ceo-review.fires
+      - judgments.stage-routing.discuss-strategic-delegate.fires
+
+  - id: arch-review
+    keywords:
+      - "架构审查"
+      - "plan-eng-review"
+      - "复杂架构"
+      - "engineering review"
+    triggers:
+      - judgments.stage-routing.plan-architecture-delegate.fires
+
+  - id: phase-discuss
+    keywords:
+      - "phase 澄清"
+      - "灰色澄清"
+      - "discuss-phase"
+      - "gsd-discuss-phase"
+    triggers:
+      - judgments.phase-gate.gsd-discuss-phase.fires
+      - judgments.stage-routing.discuss-phase-delegate.fires
+
+  - id: paranoid-review
+    keywords:
+      - "关键模块"
+      - "paranoid review"
+      - "/review"
+      - "staff engineer review"
+    triggers:
+      - judgments.stage-routing.verify-paranoid-critical.fires
+
+  - id: tdd
+    keywords:
+      - "强制 TDD"
+      - "TDD first"
+      - "red-green-refactor"
+      - "test first"
+    triggers:
+      - judgments.tdd-gate.tdd-strongly-suggested.fires

package/workflows/role-prompts.yaml

@@ -17,6 +17,14 @@
 #   description:    YAML frontmatter `description` for <claude-home>/commands/<x>.md.
 #
 # Karpathy simplicity: 1 small yaml beats 23 hardcoded strings in TS.
+#
+# Upstream attributions (v3.6.0 Phase 1):
+#   Portions of the `task-clarify` / `task-code` / `discuss-subtask` entries
+#   below are paraphrased from https://github.com/mattpocock/skills
+#   (MIT License, commit b8be62ffacb0118fa3eaa29a0923c87c8c11985c). The full
+#   upstream license is preserved at
+#   .planning/v3.6.0/mattpocock-source/LICENSE and a project-wide attribution
+#   summary is in THIRD-PARTY-NOTICES.md at the repo root.
 
 schema_version: harnessed.role-prompts.v1
 
@@ -177,6 +185,16 @@ prompts:
       Generate ≥2 implementation approaches for a single subtask and compare
       tradeoffs. Fires when core algorithm / data structure / API contract /
       high error-cost. Skip pure CRUD or single-obvious-path tasks.
+
+      # grill-me methodology paraphrased from mattpocock/skills (MIT, b8be62f)
+      # Source: skills/productivity/grill-me/SKILL.md
+      # When the user wants to stress-test a plan or asks to be grilled,
+      # interview them relentlessly about every aspect until shared
+      # understanding is reached. Walk down each branch of the decision tree,
+      # resolving dependencies between decisions one at a time. For each
+      # question, provide your recommended answer. Ask questions ONE at a
+      # time. If a question can be answered by exploring the codebase,
+      # explore the codebase instead of asking.
     checklist:
       - "State the subtask in one sentence; confirm scope with user if ambiguous"
       - "Produce 2-4 distinct approaches (not just '2 flavors of the same idea')"
@@ -184,8 +202,11 @@ prompts:
       - "Recommend one with 1-2 line reason; flag risks of the chosen path"
       - "Output a `findings.md` block the implementer can paste into the task"
       - "If options collapse to one (others clearly bad), say so and exit fast"
+      # grill-me additional checklist (paraphrased from mattpocock/skills)
+      - "Grill mode: walk the decision tree branch-by-branch, ONE question at a time, with your recommended answer"
+      - "Prefer codebase exploration over asking when a question can be answered from code"
     severity: "recommended / acceptable / rejected"
-    description: "Generate 2-4 subtask approaches with tradeoffs and recommend one (brainstorming)."
+    description: "Generate 2-4 subtask approaches with tradeoffs and recommend one (brainstorming + grill-me on stress-test requests)."
 
   # ============================================================================
   # plan-* (2 subs)
@@ -239,6 +260,16 @@ prompts:
       Surface ambiguity in a single subtask spec by asking ONE focused
       question at a time. Fires when ≥2 approaches / core algorithm / API
       contract / high error-cost. Skip if subtask is CRUD or already obvious.
+
+      # grill-with-docs methodology paraphrased from mattpocock/skills (MIT, b8be62f)
+      # Source: skills/engineering/grill-with-docs/SKILL.md
+      # When ambiguity overlaps with existing project docs / ADRs, run a
+      # grill-with-docs cycle: pressure-test the plan against the project's
+      # domain language (CONTEXT.md), sharpen terminology mismatches inline,
+      # and update ADRs as decisions crystallise. Challenge term conflicts
+      # immediately; sharpen vague/overloaded terms by proposing a canonical
+      # name; cross-reference user claims with code and surface contradictions.
+      # Output is BOTH a refined spec AND a doc-diff (CONTEXT.md / docs/adr/*.md).
     checklist:
       - "Read the subtask description; restate it in your own words to confirm"
       - "List every assumption you would make; flag the ones the user must confirm"
@@ -246,6 +277,11 @@ prompts:
       - "Stop asking when you have enough to write 80% of the code without guessing"
       - "Record the resolved spec at the top of the subtask file before implementing"
       - "If `phase.spec_ambiguous == true AND phase.no_docs == true`, request grill-me"
+      # grill-with-docs additional checklist (paraphrased from mattpocock/skills)
+      - "Cross-reference each assumption against CONTEXT.md domain language; flag terminology drift immediately"
+      - "Sharpen vague/overloaded terms (e.g. 'account' → Customer vs User) by proposing a canonical name"
+      - "If a decision crystallises mid-grill, draft the ADR delta inline (don't defer)"
+      - "Output BOTH the refined spec AND any doc-diff (CONTEXT.md / docs/adr/*.md)"
     severity: "blocking-question / nice-to-know / resolved"
     description: "Clarify subtask spec one question at a time (brainstorming + grill-with-docs on ambiguity)."
 
@@ -267,8 +303,17 @@ prompts:
       - "No speculative abstractions (no 'just in case' generics)"
       - "Edit with surgical precision: full path, exact selectors, no broad rewrites"
       - "Update progress.md before declaring done (planning-with-files `/plan`)"
+      # zoom-out methodology paraphrased from mattpocock/skills (MIT, b8be62f)
+      # Source: skills/engineering/zoom-out/SKILL.md
+      - "zoom-out: when unfamiliar with an area, go up a layer of abstraction and map the relevant modules and callers using the project's CONTEXT.md domain glossary vocabulary"
+      # improve-codebase-architecture methodology paraphrased from mattpocock/skills (MIT, b8be62f)
+      # Source: skills/engineering/improve-codebase-architecture/SKILL.md
+      - "improve-arch: hunt deepening opportunities — modules whose interface is nearly as complex as their implementation are shallow; deep modules hide a lot of behaviour behind a small interface"
+      - "improve-arch deletion test: imagine deleting the module — if complexity vanishes it was a pass-through (delete it); if complexity reappears across N callers it was earning its keep (keep / deepen)"
+      - "improve-arch: name candidates using CONTEXT.md domain vocabulary (e.g. 'the Order intake module', not 'FooBarHandler'); if a candidate contradicts an existing ADR, only surface it when the friction is real enough to revisit the ADR"
+      - "improve-arch: present candidates as a before/after report and let the user pick which to explore before designing interfaces"
     severity: "needs-fix / done / blocked"
-    description: "Implement a subtask under karpathy 4 心法 (Think Before Coding, Simplicity First, Surgical Changes, Goal-Driven); ≤200 LOC per file."
+    description: "Implement a subtask under karpathy 4 心法 (Think Before Coding, Simplicity First, Surgical Changes, Goal-Driven); ≤200 LOC per file. zoom-out for unfamiliar areas; improve-codebase-architecture for shallow-module deepening audits."
 
   task-test:
     primary_cap: "tdd"