create-harness-vibe-coding 0.8.0 → 0.8.2

package/templates/common/.claude/skills/wf-auto/SKILL.md

@@ -0,0 +1,107 @@
+---
+name: wf-auto
+description: Perpetual auto-optimization mode. Never stops — continuously improves code until 8-angle exhaustion. Adaptive checkpoints, external spark search, evidence ledger. Use for Claude /wf-auto, Codex $wf-auto, auto mode, or when the user wants unbounded self-directed optimization.
+---
+
+# WF Auto — Perpetual Auto-Optimization
+
+## Load (authoritative specs)
+
+- `Harness/WF-AUTO.md` — full spec: perpetual loop, state machine, 8-angle exhaustion gate, cross-model oracle, spark candidate provider, Value Gate scoring, evidence ledger, Intent Checkpoints, anti-patterns, safety controls
+- `Harness/subagents.md` — agent roster, controller role, efficiency ladder
+- `Harness/dispatch.md` — handoff format, File claim, Concurrency group fields
+- `Harness/agent-workflow.md` — build/review/test loop, cohesion rule, completion gate
+- `.claude/skills/wf-review/SKILL.md` — cross-model invocation pattern (used by the oracle step)
+
+## Trigger & When NOT to Use
+
+- **Trigger**: Claude `/wf-auto`, Codex `$wf-auto`, `wf auto`, `auto mode`, or user wants continuous self-directed improvement
+- **Do NOT use**: user has a specific bounded task (use `/wf`), task needs maximum parallelism (use `/wf-max`), production hotfix needed urgently, codebase <100 lines
+
+## State Machine
+
+```
+auto.internal → auto.spark → auto.checkpoint → auto.exhausted → paused
+```
+
+CEO tracks state in `Harness/tasks/auto/PROGRESS.md`. Transitions are CEO-owned.
+
+## Hard Constraints
+
+1. **NEVER STOP except A-GATE.** No "task complete" early exit. The Angle Exhaustion Gate (internal + oracle + spark all empty, 3 confirm rounds) is the ONLY permitted stop.
+2. **CEO never writes production code.** CEO uses Task, Read, Grep/Glob. No Edit/Write/Bash on source files. Exception: CEO MAY write to `Harness/tasks/auto/PROGRESS.md` and `Harness/tasks/auto/PLAN.md`.
+3. **ALL sources in ONE message per cycle.** 8 angles + oracle + spark searchers. Batching is mandatory.
+4. **ONE finding per cycle.** One change, ≤3 files, ≤50 lines diff. Big ideas (>50 lines) escalate to /wf or /wf-max then return.
+5. **Two-gate review every cycle.** Spec review before code-quality review. No skipping.
+6. **A-GATE has 3 tiers.** All 8 exhausted → Cross-Model Oracle → Spark search → 2 confirmation rounds → STOP.
+7. **Value Gate is scored, not binary.** 5 dimensions (Impact, Evidence, Fit, Timing, Cost/Risk), 1-5 each. Pass: ≥18/25 AND no dimension <3.
+8. **Intent Checkpoint is adaptive.** 2→5→10 cycles. Exactly 2 questions: "Still aligned?" + "What should change?" Early on drift signals.
+9. **Evidence ledger per cycle.** Source, evidence type, expected impact, verification method, measured result, verdict. Track weak spark count.
+
+## The 8 Angles (quick reference)
+
+| # | Angle | Finds |
+|---|-------|-------|
+| 1 | Correctness | Bugs, edge cases, null safety, race conditions |
+| 2 | Performance | Slow paths, memory, algorithmic complexity |
+| 3 | Security | Injection, auth, secrets, dependency CVEs |
+| 4 | Maintainability | Clarity, DRY, coupling, naming, dead code |
+| 5 | Test Coverage | Missing tests, weak assertions, flaky tests |
+| 6 | Architecture | Boundaries, dependency direction, layer discipline |
+| 7 | UX / DX | Error messages, API ergonomics, documentation |
+| 8 | Robustness | Resilience, retry, observability, recovery |
+
+## Spark Sources (when internal + oracle empty)
+
+| # | Source | Evidence Weight |
+|---|--------|-----------------|
+| 1 | Official Docs & Advisories | HIGH |
+| 2 | Ecosystem Pulse | MEDIUM |
+| 3 | GitHub Trending (same stack) | LOW-MEDIUM |
+| 4 | Best Practices (latest) | MEDIUM |
+| 5 | Competitor/Peer Projects | LOW |
+| 6 | Real-world Issues | MEDIUM |
+| 7 | Architecture Trends | LOW |
+| 8 | Performance Benchmarks | MEDIUM |
+
+Source-quality: official docs > blog posts. Trending ≠ correct. Competitor behavior is hypothesis only. Every spark MUST cite source with URL and date.
+
+## Perpetual Loop
+
+```
+W0: SENSE (8 angles + oracle + 8 spark sources, all parallel)
+A-GATE [findings? → W1 | all empty? → oracle → spark → confirm ×2 → STOP]
+CHECKPOINT [every 2→5→10 cycles, 2 questions]
+W1: PRIORITIZE (across internal + oracle + spark)
+W2: IMPLEMENT → W3: REVIEW → W4: DEBUG → W5: VERIFY
+RECORD + EVIDENCE LEDGER → LOOP W0
+```
+
+## Cycle Recording
+
+Every cycle writes to `Harness/tasks/auto/PROGRESS.md`:
+- Cycle number, timestamp, state
+- Source (internal/oracle/spark-*), source citation
+- Finding, change description, files changed
+- Value Gate scores (if spark candidate)
+- Review result, verification evidence
+- Evidence Ledger: evidence type, expected impact, verification method, measured result, verdict
+
+## Safety
+
+- ≤3 files, ≤50 lines per cycle
+- Big ideas (>50 lines) escalate to /wf or /wf-max, then return to auto
+- Destructive changes flagged with rollback plan
+- IDLE alarm after 5 empty cycles → re-scope → A-GATE candidate
+- Spark stop: 5 failed Value Gates OR 3 weak measured impacts OR 2 repeated source families empty
+- User can interrupt at any time
+
+## Return Format
+
+- Total cycles run
+- Findings addressed per source (internal / oracle / spark)
+- Evidence ledger with measured impacts
+- Exhaustion evidence (3-round confirmation)
+- Weak spark count
+- Final codebase state
+- Residual risk assessment

package/templates/common/.claude/skills/wf-auto-spark/SKILL.md

@@ -0,0 +1,39 @@
+---
+name: wf-auto-spark
+description: Use for /wf-auto-spark in Claude Code, $wf-auto-spark or /skills wf-auto-spark in Codex, or perpetual inspiration mode that never stops — external spark search, long-term roadmap with staged milestones, ≤50% deviation guard.
+---
+
+# WF-AUTO-SPARK Adapter
+
+This skill is a thin tool adapter. The authoritative workflow lives in
+`Harness/WF-AUTO-SPARK.md`; do not duplicate or override it here.
+
+## Invocation
+
+- Claude Code: use `/wf-auto-spark` or select the `wf-auto-spark` skill.
+- Codex CLI or IDE: use `$wf-auto-spark` or `/skills` then choose `wf-auto-spark`.
+
+## Load
+
+1. `CLAUDE.md`
+2. `Harness/MEMORY.md`
+3. `Harness/README.md`
+4. `Harness/WF-AUTO-SPARK.md`
+5. `Harness/WF-AUTO.md`
+6. `Harness/subagents.md`
+7. `Harness/dispatch.md`
+
+## Rules
+
+WF-AUTO-SPARK is perpetual inspiration mode with roadmap anchoring:
+1. **Roadmap first**: Declare North Star + staged milestones before any spark cycle.
+2. **Never auto-stop**: Only user can stop. "No sparks found" → expand search.
+3. **Deviation guard (≤50%)**: Every spark checked against North Star. Cumulative 10-cycle average ≥65%. Below → force Re-Anchor Gate.
+4. **Milestones flexible within 50%**: Can reorder/split/merge/replace, but North Star changes need user confirmation.
+5. **Value reflection every cycle**: CEO writes what was done, why it matters, deviation score, milestone progress.
+6. **Re-Anchor Gate every 10 cycles**: User confirms direction or adjusts roadmap.
+
+## Roadmap Location
+
+Active roadmap lives at `Harness/tasks/auto/SPARK-ROADMAP.md`. Created at startup.
+Per-cycle evidence at `Harness/tasks/auto/PROGRESS.md`.

package/templates/common/.claude/skills/wf-max/SKILL.md

@@ -26,8 +26,16 @@ This skill is a thin tool adapter. The authoritative workflow lives in
 
 ## Rules
 
-- Treat yourself as CEO, not implementer.
-- Do not edit production/source files directly while WF-MAX is active.
+WF-MAX is a three-layer architecture:
+1. Global mode (`wf-max`)
+2. Agent role (`ceo` | `manager` | `worker` | `reviewer`)
+3. Dispatch permission (`writeSet`, `forbidden`, `verification`)
+
+- Top-level orchestrator is CEO (reads, plans, dispatches). Delegated Workers follow dispatch packet with explicit writeSet. Global mode ≠ every agent is CEO.
+- CEO: never edit source files directly. Spawn Workers with writeSet.
+- Worker: edit only files in dispatch writeSet. Outside writeSet → blocked.
+- Manager: scope, review, coordinate. No source edits by default.
+- Reviewer: read and report only. No edits.
 - Use the D-GATE in `Harness/WF-MAX.md` before any implementation wave:
   dispatch table, self-audit, disjoint file claims, and reviewer plan.
 - Use real subagents when the runtime supports them; otherwise record a

package/templates/common/.claude/skills/wf-remove/SKILL.md

@@ -17,14 +17,21 @@ description: Use for /wf-remove in Claude Code, $wf-remove or /skills wf-remove
 
 ## Flow
 
-1. Run `node Harness/scripts/wf-remove.mjs` for a dry-run plan.
+1. Run `node Harness/scripts/wf-remove.mjs --json` for the machine-readable
+   plan.
 2. Auto-remove only SAFE files that still match stored checksums.
 3. Ask the user before every MODIFIED or uncertain file.
-4. Never remove USER DATA files.
-5. Run `node Harness/scripts/wf-remove.mjs --apply` only after the plan is
-   understood and modified-file decisions are clear.
+4. Preserve USER DATA by default. For an explicit thorough uninstall, use
+   `--purge-user-data` (alias `--purge`); add `--keep-tasks` when the user wants task records
+   retained while project-fact Harness docs are removed.
+5. Run the script, not manual deletes:
+   - safe default: `node Harness/scripts/wf-remove.mjs --apply --yes`
+   - thorough but keep tasks: `node Harness/scripts/wf-remove.mjs --apply --yes --purge-user-data --keep-tasks`
+   - exact modified decisions: add `--delete-modified <path>` for each
+     user-approved MODIFIED file.
 
 ## Return
 
 Report SAFE removals, MODIFIED keep/delete decisions, preserved USER DATA,
-directory cleanup, CLAUDE/AGENTS status, and `git status` guidance.
+PURGE removals, directory cleanup, CLAUDE/AGENTS status, `.harness-version`
+status, and `git status` guidance.

package/templates/common/.claude/skills/wf-update/SKILL.md

@@ -19,14 +19,21 @@ description: Use for /wf-update in Claude Code, $wf-update or /skills wf-update
 
 ## Flow
 
-1. Run `node Harness/scripts/wf-update-check.mjs` first.
+1. Run `node Harness/scripts/wf-update-check.mjs --json` first and use the
+   `agent` block as the action plan.
 2. Preserve all PRESERVE files. Never overwrite user task, memory, research,
    README, package, or architecture files.
-3. Apply SAFE and NEW files through the script.
-4. Ask the user before every CONFLICT file: merge, overwrite, or keep.
-5. After update, run the validator and then scan-clean.
+3. If `agent.safeApplyCommand` is present, run it to apply SAFE and NEW files
+   before spending AI time on conflicts. Default command:
+   `node Harness/scripts/wf-update-check.mjs --apply-safe`.
+4. For every `agent.aiMergeRequired` entry, compare the local file with
+   `templateHint` or `remoteUrl`, then choose merge, keep-local, or
+   overwrite-from-template. Ask the user only when the intent is ambiguous.
+5. Use strict `--apply` only when the JSON plan has zero conflicts.
+6. After update, run the validator and then scan-clean.
 
 ## Return
 
 Report version, SAFE/NEW updates, conflicts and decisions, preserved files,
-validation output, scan-clean result, and remaining risks.
+partialUpdate status if any, validation output, scan-clean result, and
+remaining risks.

package/templates/common/.codex/hooks.json

@@ -1,37 +1,59 @@
-{
-  "hooks": {
-    "SessionStart": [
-      {
-        "matcher": "",
-        "hooks": [
-          {
-            "type": "command",
-            "command": "node Harness/scripts/wf-mode-hook.mjs"
-          }
-        ]
-      }
-    ],
-    "UserPromptSubmit": [
-      {
-        "matcher": "",
-        "hooks": [
-          {
-            "type": "command",
-            "command": "node Harness/scripts/wf-mode-hook.mjs"
-          }
-        ]
-      }
-    ],
-    "PreToolUse": [
-      {
-        "matcher": "Edit|Write|MultiEdit|Bash",
-        "hooks": [
-          {
-            "type": "command",
-            "command": "node Harness/scripts/wf-mode-hook.mjs"
-          }
-        ]
-      }
-    ]
-  }
-}
+{
+  "hooks": {
+    "SessionStart": [
+      {
+        "matcher": "",
+        "hooks": [
+          {
+            "type": "command",
+            "command": "node Harness/scripts/wf-mode-hook.mjs"
+          }
+        ]
+      }
+    ],
+    "UserPromptSubmit": [
+      {
+        "matcher": "",
+        "hooks": [
+          {
+            "type": "command",
+            "command": "node Harness/scripts/wf-mode-hook.mjs"
+          }
+        ]
+      }
+    ],
+    "PreToolUse": [
+      {
+        "matcher": "Edit|Write|MultiEdit|Bash",
+        "hooks": [
+          {
+            "type": "command",
+            "command": "node Harness/scripts/wf-mode-hook.mjs"
+          }
+        ]
+      }
+    ],
+    "PostToolUse": [
+      {
+        "matcher": "",
+        "hooks": [
+          {
+            "type": "command",
+            "command": "node Harness/scripts/wf-mode-hook.mjs"
+          }
+        ]
+      }
+    ],
+    "Stop": [
+      {
+        "matcher": "",
+        "hooks": [
+          {
+            "type": "command",
+            "command": "node Harness/scripts/wf-mode-hook.mjs"
+          }
+        ]
+      }
+    ]
+  }
+}

package/templates/common/.harness-version

@@ -1,17 +1,20 @@
 {
-  "generator": "0.8.0",
-  "generated": "2026-07-01T04:31:49.043Z",
+  "generator": "0.8.2",
+  "generated": "2026-07-02T04:28:22.774Z",
   "options": [],
   "autoCheck": true,
   "source": "https://raw.githubusercontent.com/zingspark/create-harness-vibe-coding/main/templates/common/",
   "checksums": {
     ".agents/skills/subagent-orchestrator/SKILL.md": "sha256-d17b1e49aa8e3125b17621242f620ac89c10692fac853bf0a682a87f660d86da",
+    ".agents/skills/tdd/SKILL.md": "sha256-2a86f45b3685670f5f214fdcc8d21ecc3d04f42af4f7cae2a38e994ab24bfb1e",
+    ".agents/skills/wf-auto-spark/SKILL.md": "sha256-b07a3570e232cf47b179b9774daed4c00d7756ccce9e2339556d3544f92cf02b",
+    ".agents/skills/wf-auto/SKILL.md": "sha256-ac3177dc7c5f40f99017b79dbb71722325f75c2e608f20aca780fd874c9755ee",
     ".agents/skills/wf-learn/SKILL.md": "sha256-7f3e1ee0aa83cbb76707698d0c26b703ad5c74b2df95a7dc4d751939a4ba05b2",
-    ".agents/skills/wf-max/SKILL.md": "sha256-5463c4ac6a34848639c176000ef3f1989c54e7cb795e47251ef465782118a18d",
+    ".agents/skills/wf-max/SKILL.md": "sha256-9b37cc3385f6d1a285b617169e91fbf71ffec76135b7b46ec1de2fe94ca220da",
     ".agents/skills/wf-readme/SKILL.md": "sha256-4d34ee3b6b305fa2581f5d8cb31e9152759f3df8bf8fa08efbb43782f128bdcd",
-    ".agents/skills/wf-remove/SKILL.md": "sha256-34888c78feade04e8b6d1f22e366c04e3daefc8c0f9e6ea39f52cf0a7f3ec01f",
+    ".agents/skills/wf-remove/SKILL.md": "sha256-f27aee81d4d6988186f468ccc5dfd02c7605967636a5aea93d92443e030dbcc2",
     ".agents/skills/wf-review/SKILL.md": "sha256-cc6d536ec6de25546a0ba96e686f195da50ed11bc03763a76ef46d77243d3537",
-    ".agents/skills/wf-update/SKILL.md": "sha256-c58d1238d2a5f47dda9c8bea2ccd95d350e39ef0985c9c69d8111e7e84a3a4b6",
+    ".agents/skills/wf-update/SKILL.md": "sha256-d57cd89e271b2af63b6a1264af552a30f8d44959cf4782b42f0ab082a90be9cf",
     ".agents/skills/wf/SKILL.md": "sha256-70766bd2cb02bc489b5cc021797af62596a005d444a026abb511054a1a820a67",
     ".claude/agents/architect-manager.md": "sha256-d98c3a2d044d5216d9bcde217b4359b1c33f5be152416e242807652ddcd2868b",
     ".claude/agents/architect.md": "sha256-61cea40c8c3e01bd53f3ad642ef734850fdb931497e7ee20552ea7a8b4e7b70c",
@@ -26,44 +29,55 @@
     ".claude/agents/researcher.md": "sha256-402fef14dee8f495dc9ddfad5af3ad233d254326b49b831f604014a8cb6d0beb",
     ".claude/agents/review-manager.md": "sha256-fb8fbd6c6624279cc97aa3dbd50ec20c150ff4a2d195788bc8537d98699cc41b",
     ".claude/agents/reviewer.md": "sha256-2913b7799fcd8e162f01ae0de09a41ec7083de5f0cae3abcd4ecc62acc675a6b",
+    ".claude/agents/tdd-guide.md": "sha256-c1663ffba6e48c7c19b0de1bb3eae674b3e85386fc959b15dd30d696aef6433c",
     ".claude/agents/test-writer.md": "sha256-9018a9f65f1861a9bade999790e945d258781c1d846eb30a9de23ec3ce5f1d82",
     ".claude/agents/verifier.md": "sha256-6d8ca8bd13d7bb7680423875269e407c06aca60334df44d9230a015aabd0a8d0",
     ".claude/rules/ecc/common.md": "sha256-157c300e3b47049998d1bca867da6f9b54efb5de6efbabbb64a22af4cb2b84e8",
-    ".claude/settings.json": "sha256-3ee53515a829b85267b7330fad9e90d797f1bd16964ec9f876fdd630a0d2c093",
+    ".claude/settings.json": "sha256-4a2bdeb15d9911c8fa624e90ef977e857790981017ff10f44de36a343249ce25",
     ".claude/skills/subagent-orchestrator/SKILL.md": "sha256-d17b1e49aa8e3125b17621242f620ac89c10692fac853bf0a682a87f660d86da",
+    ".claude/skills/tdd/SKILL.md": "sha256-2a86f45b3685670f5f214fdcc8d21ecc3d04f42af4f7cae2a38e994ab24bfb1e",
+    ".claude/skills/wf-auto-spark/SKILL.md": "sha256-b07a3570e232cf47b179b9774daed4c00d7756ccce9e2339556d3544f92cf02b",
+    ".claude/skills/wf-auto/SKILL.md": "sha256-ac3177dc7c5f40f99017b79dbb71722325f75c2e608f20aca780fd874c9755ee",
     ".claude/skills/wf-learn/SKILL.md": "sha256-7f3e1ee0aa83cbb76707698d0c26b703ad5c74b2df95a7dc4d751939a4ba05b2",
-    ".claude/skills/wf-max/SKILL.md": "sha256-5463c4ac6a34848639c176000ef3f1989c54e7cb795e47251ef465782118a18d",
+    ".claude/skills/wf-max/SKILL.md": "sha256-9b37cc3385f6d1a285b617169e91fbf71ffec76135b7b46ec1de2fe94ca220da",
     ".claude/skills/wf-readme/SKILL.md": "sha256-4d34ee3b6b305fa2581f5d8cb31e9152759f3df8bf8fa08efbb43782f128bdcd",
-    ".claude/skills/wf-remove/SKILL.md": "sha256-34888c78feade04e8b6d1f22e366c04e3daefc8c0f9e6ea39f52cf0a7f3ec01f",
+    ".claude/skills/wf-remove/SKILL.md": "sha256-f27aee81d4d6988186f468ccc5dfd02c7605967636a5aea93d92443e030dbcc2",
     ".claude/skills/wf-review/SKILL.md": "sha256-cc6d536ec6de25546a0ba96e686f195da50ed11bc03763a76ef46d77243d3537",
-    ".claude/skills/wf-update/SKILL.md": "sha256-c58d1238d2a5f47dda9c8bea2ccd95d350e39ef0985c9c69d8111e7e84a3a4b6",
+    ".claude/skills/wf-update/SKILL.md": "sha256-d57cd89e271b2af63b6a1264af552a30f8d44959cf4782b42f0ab082a90be9cf",
     ".claude/skills/wf/SKILL.md": "sha256-70766bd2cb02bc489b5cc021797af62596a005d444a026abb511054a1a820a67",
     ".codex/config.toml": "sha256-d37497c3278121598a663564ab38b53f658969717f78decb661ddd11c66551ea",
-    ".codex/hooks.json": "sha256-6d8d237b4a038a48fbadbdd087d9a68dba024bcfd748f59968252ebae7cc2e96",
-    "AGENTS.md": "sha256-bbc17b119ff579e500dcd36e78f9cf600ccda27fa7b32903f233ad96a97058ff",
-    "CLAUDE.md": "sha256-432bd4dc9bdf9958d79ae697f72d1c9723be23fb156d43889ede84e305ed5e70",
-    "Harness/MEMORY.md": "sha256-68b3e2b68880814bad11aa6d444d6b736848ac14c2a758ec3225c688a2c1882e",
-    "Harness/README.md": "sha256-6608f74400dbae1e73b838d6b74f02e73a0b0e54404e899628dde6ccfbf06cf4",
-    "Harness/SETUP.md": "sha256-742d37c31ed6caccd39db499dc316528ec293396fe9a1ac84c47e408f6ab9839",
-    "Harness/WF-MAX.md": "sha256-81c788ac56a0c1673a9e6bdf619efbcfa9c961ca7c5065c15b98760775f963a6",
+    ".codex/hooks.json": "sha256-ec2322e080b96b1c0cb86161476ff75a4ed00312b57eed979d7d4a379365d0b7",
+    "AGENTS.md": "sha256-c6e6f08195c41b49b682291c7b83f55acd9750767a7eef3811bf5bbdaa66f76a",
+    "CLAUDE.md": "sha256-b62a1bc5410280ed17f87ba591f571a0917f438589627fc50e9a53b9e9d0bb75",
+    "Harness/ECC-GUIDE.md": "sha256-48924c4c0e17dc47be53d616a6690415307688f971ec872d8860c5bbe64c90d7",
+    "Harness/MEMORY.md": "sha256-6e01795e787eb809f856cce8d90a15a118f8fac1ebbb71dd746a868f207a9457",
+    "Harness/README.md": "sha256-3f33274b01d100f20694efdf6c4633a01a79dcef9c9b8974ad5e8796ef928dc6",
+    "Harness/SETUP.md": "sha256-2a59db4e5053faf5f82ceb402491df016fee93bd59449202d4c9e1e7388df977",
+    "Harness/TDD-GUIDE.md": "sha256-a038f0aea67c72220684d6854536ad7b2d59ab52342374d4710f2c94828f88c4",
+    "Harness/WF-AUTO-SPARK.md": "sha256-48cc08e1a78cd4abb2ae9c2807ef1ac9a09544eb954220b9087b2032fabbd690",
+    "Harness/WF-AUTO.md": "sha256-ac0ab13e11ca658cd2c5b6ce73f3d267bea6391a04e850c9f9a24d642f1ad350",
+    "Harness/WF-MAX.md": "sha256-98a4a918eb8e97c40422c7e133a0bc33184faf7771ca9645f4161d82a5cac8cb",
     "Harness/WF.md": "sha256-7cce2568444295cb387fa958cd4ef9711a19697b60ce9cba0e142484e0a165ae",
     "Harness/agent-workflow.md": "sha256-1aff5e7dc1e082c559cb0a9086c4f93f6702905aff00ebb957300f463ea80b31",
-    "Harness/context-loading.md": "sha256-0d97d6ec2325063f7158511f3462ca9cbdf3b6db177a79dac8ee7d2cb7930264",
-    "Harness/dispatch.md": "sha256-e0c6a3a46acc8899574c9b6d6bb4da119adb9e9ed1ce91acc9f7a688ed3aea15",
+    "Harness/context-loading.md": "sha256-a2e71435e127c2ff5b70ebfddb1a8bbaa64dfd584505fbd6e14dc059e18cc6a1",
+    "Harness/dispatch.md": "sha256-e823b905bbdcae396d759f281bbd413693904c80b6c18f7993718e63a961b2a6",
     "Harness/extension.md": "sha256-686f76d83e91750c20d4f5aa8e614f5003baeb5a703d0451f469ca7eeab75e37",
     "Harness/lifecycle.md": "sha256-5979c37e66e35940cb707f8cd71e97d53bb05399c3281c714f69499abdee59a4",
     "Harness/research/README.md": "sha256-956c154df01cb9376972eb8b88bb3be0fe4e2dda802a72457c0126e3476fa755",
     "Harness/scripts/scan-clean.mjs": "sha256-7f693faf762c9c8e7657143d651f7c8369ed4823f18babe21daec58a55025593",
-    "Harness/scripts/validate-harness.mjs": "sha256-f3211c2149918b1cfc83648ea2e992b80c45b0c00f9a5b9f02a6f6094e7791d6",
-    "Harness/scripts/wf-mode-hook.mjs": "sha256-289f0df4155dd8523507f59add5eac72c0aa92efc85a78d5a46350b9c9bb4f80",
-    "Harness/scripts/wf-remove.mjs": "sha256-2ae2687c63cd3aea3b36713d67ce78811df6541a19904b153d17518b6268938b",
-    "Harness/scripts/wf-statusline.ps1": "sha256-53c2e0178e9a0826516731b1145f96f55ff6c57fb1f31bf6f1a7210a8502ca65",
-    "Harness/scripts/wf-statusline.sh": "sha256-053908cd4d53dea162252077c6cc5544ccd164455739f6edfbf254945f06ea2f",
-    "Harness/scripts/wf-update-check.mjs": "sha256-8c3fa219e902056c20c55b2abfa5152349d9e00f4faa5bef646f78bfb71c486f",
-    "Harness/subagents.md": "sha256-e66f4bef8ce6c118cf0ec8c511f727a8c2c40bce25dcf5b754489d89915a47ba"
+    "Harness/scripts/validate-harness.mjs": "sha256-fd904202f99cd30ad7ce69f5343c4adca94ab30b7a5f8eab37004d748e0779ab",
+    "Harness/scripts/wf-mode-hook.mjs": "sha256-fbf2c398bfe21374fc5d0230133dfa16feff6afe79598bd185aae49643075545",
+    "Harness/scripts/wf-remove.mjs": "sha256-ae941d34d7d263f2b65751d177673a3c4fb11c326885ca413245e3f93e99a006",
+    "Harness/scripts/wf-statusline.ps1": "sha256-49effdea8b0980e762a9440f4be9011543ede3533f6df1b2008368d78c427fcc",
+    "Harness/scripts/wf-statusline.sh": "sha256-6fa034fab9abe9361daae14cdb802f69825ce20d4bf6a9c18f58c04e971693ac",
+    "Harness/scripts/wf-update-check.mjs": "sha256-d14ce08f4c05ba118362a56a4b7d5965b114bc2b15a023c08e21d57f32b2cf93",
+    "Harness/subagents.md": "sha256-31818b96f4e834087d8ce8887758f303114b3fd67fb9819fd661f78170fb39d3"
   },
   "sources": {
     ".agents/skills/subagent-orchestrator/SKILL.md": ".claude/skills/subagent-orchestrator/SKILL.md",
+    ".agents/skills/tdd/SKILL.md": ".claude/skills/tdd/SKILL.md",
+    ".agents/skills/wf-auto-spark/SKILL.md": ".claude/skills/wf-auto-spark/SKILL.md",
+    ".agents/skills/wf-auto/SKILL.md": ".claude/skills/wf-auto/SKILL.md",
     ".agents/skills/wf-learn/SKILL.md": ".claude/skills/wf-learn/SKILL.md",
     ".agents/skills/wf-max/SKILL.md": ".claude/skills/wf-max/SKILL.md",
     ".agents/skills/wf-readme/SKILL.md": ".claude/skills/wf-readme/SKILL.md",
@@ -84,11 +98,15 @@
     ".claude/agents/researcher.md": ".claude/agents/researcher.md",
     ".claude/agents/review-manager.md": ".claude/agents/review-manager.md",
     ".claude/agents/reviewer.md": ".claude/agents/reviewer.md",
+    ".claude/agents/tdd-guide.md": ".claude/agents/tdd-guide.md",
     ".claude/agents/test-writer.md": ".claude/agents/test-writer.md",
     ".claude/agents/verifier.md": ".claude/agents/verifier.md",
     ".claude/rules/ecc/common.md": ".claude/rules/ecc/common.md",
     ".claude/settings.json": ".claude/settings.json",
     ".claude/skills/subagent-orchestrator/SKILL.md": ".claude/skills/subagent-orchestrator/SKILL.md",
+    ".claude/skills/tdd/SKILL.md": ".claude/skills/tdd/SKILL.md",
+    ".claude/skills/wf-auto-spark/SKILL.md": ".claude/skills/wf-auto-spark/SKILL.md",
+    ".claude/skills/wf-auto/SKILL.md": ".claude/skills/wf-auto/SKILL.md",
     ".claude/skills/wf-learn/SKILL.md": ".claude/skills/wf-learn/SKILL.md",
     ".claude/skills/wf-max/SKILL.md": ".claude/skills/wf-max/SKILL.md",
     ".claude/skills/wf-readme/SKILL.md": ".claude/skills/wf-readme/SKILL.md",
@@ -102,10 +120,14 @@
     "AGENTS.md": "AGENTS.md",
     "CLAUDE.md": "CLAUDE.md",
     "Harness/.harness-version": ".harness-version",
+    "Harness/ECC-GUIDE.md": "Harness/ECC-GUIDE.md",
     "Harness/MEMORY.md": "MEMORY.md",
     "Harness/PROGRESS.md": "Harness/PROGRESS.md",
     "Harness/README.md": "Harness/README.md",
     "Harness/SETUP.md": "SETUP.md",
+    "Harness/TDD-GUIDE.md": "Harness/TDD-GUIDE.md",
+    "Harness/WF-AUTO-SPARK.md": "Harness/WF-AUTO-SPARK.md",
+    "Harness/WF-AUTO.md": "Harness/WF-AUTO.md",
     "Harness/WF-MAX.md": "Harness/WF-MAX.md",
     "Harness/WF.md": "Harness/WF.md",
     "Harness/agent-workflow.md": "Harness/agent-workflow.md",
@@ -129,6 +151,7 @@
     "Harness/scripts/wf-update-check.mjs": "scripts/wf-update-check.mjs",
     "Harness/subagents.md": "Harness/subagents.md",
     "Harness/tasks/_template/ARTIFACTS.md": "Harness/tasks/_template/ARTIFACTS.md",
+    "Harness/tasks/_template/NAMING.md": "Harness/tasks/_template/NAMING.md",
     "Harness/tasks/_template/NOTES.md": "Harness/tasks/_template/NOTES.md",
     "Harness/tasks/_template/PLAN.md": "Harness/tasks/_template/PLAN.md",
     "Harness/tasks/_template/PROGRESS.md": "Harness/tasks/_template/PROGRESS.md",

package/templates/common/AGENTS.md

@@ -7,24 +7,24 @@ Entry point for coding agents. This project uses the Harness scaffold — a 0-1
 Read `CLAUDE.md` first, then `Harness/MEMORY.md`, then `Harness/README.md`.
 Do not bulk-read `Harness/`. Let `Harness/README.md#Load By Task` route you.
 
-## CEO Contract (READ FIRST)
+## WF-MAX Role Contract (READ FIRST)
 
-`/wf-max` active → you are **CEO, not implementer**.
+`/wf-max` activates WF-MAX global mode. Top-level orchestrator is **CEO** — reads, plans, dispatches. Delegated Workers follow dispatch packet (writeSet, forbidden, verification). **Global mode ≠ every agent is CEO.**
 
-| ALLOWED (W0) | FORBIDDEN (always on source) |
+| ALLOWED (W0 CEO) | FORBIDDEN (always on source) |
 |---|---|
 | Read Harness docs, CLAUDE.md | Edit / Write / MultiEdit |
 | Grep/Glob for scoping | Bash (except `ls`/`dir`/`tree`/`git`) |
 | Agent spawn (ONE message) | Deep source reads → delegate to Worker |
 | Write PLAN.md / PROGRESS.md | Sequential spawn (AP6) |
 
-**Tempted to edit source? STOP. Spawn a Worker.**
+**Tempted to edit source? STOP. Spawn a Worker with explicit writeSet.**
 
 ## Key Commands
 
 | Command | Purpose |
 |---------|---------|
-| `/wf-max [task]` | Maximum parallelism: CEO→Manager→Worker |
+| `/wf-max [task]` | Maximum parallelism: CEO→Manager→Worker hierarchy (three-layer architecture: mode / agent role / dispatch permission) |
 | `/wf-review [focus]` | Cross-model peer review (use OTHER CLI) |
 | `/wf <task>` | Standard workflow mode |
 | `/wf-auto` | Perpetual auto-optimization |

package/templates/common/CLAUDE.md

@@ -8,32 +8,26 @@ This repository dogfoods the generated Harness scaffold. Scaffold source files l
 - Every session: load `Harness/MEMORY.md` first, then `Harness/README.md`.
 - If `Harness/SETUP.md` exists, follow it before normal project work; it is the install/bootstrap contract and may be deleted after setup is complete.
 
-### 1a. CEO Contract (READ BEFORE ANY TOOL USE)
+### 1a. WF-MAX Role Contract (ACTIVE ONLY when /wf-max invoked)
 
-`/wf-max` active → you are **CEO, not implementer** (enforced by hooks + `.runtime/current-mode.json`).
+`/wf-max` active → top-level orchestrator is **CEO**. Delegated Workers follow dispatch packet, edit only assigned writeSet. **Global mode ≠ every agent is CEO.** (Enforced by hooks + `.runtime/current-mode.json`.)
 
-| ALLOWED (W0) | FORBIDDEN (always on source) |
+| ALLOWED (W0 CEO) | FORBIDDEN (always on source) |
 |---|---|
 | Read Harness docs, CLAUDE.md | Edit / Write / MultiEdit |
 | Grep/Glob for scoping | Bash (except `ls`/`dir`/`tree`/`git`) |
 | Agent spawn (ONE message) | Deep source reads → delegate to Worker |
 | Write PLAN.md / PROGRESS.md | Sequential spawn (AP6) |
 
-**Tempted to edit source? STOP. Spawn a Worker.**
+**Tempted to edit source? STOP. Spawn a Worker with explicit writeSet.**
 
 - `Harness/MEMORY.md` is the memory/resource router: agents, skills, durable memories, and cross-session lessons. Follow its registrations when selecting agents/skills or recording memory.
-- `Harness/README.md` is the task router. For every request, check `Harness/README.md#Load By Task`; if a row matches, read and follow those docs before acting.
+- `Harness/README.md` is the task router. For every request, check `Harness/README.md#Load By Task` and `Harness/README.md#Skill Commands`; invoke via `/wf-*` skills or `$wf-*` skills.
 - `Harness/PROGRESS.md` is the global task index. Load at session start to see active task and task history.
 - If work spans more than one step, create a task capsule from `Harness/tasks/_template/` and update `Harness/tasks/<task-id>/PROGRESS.md`.
-- Use `/wf <task>`, `/wf-review [focus]`, `wf mode`, `workflow mode`, or `wk mode` for long, difficult, uncertain, multi-file, or repeated-failure work.
-- Use `/wf-max [task]` for maximum parallelism — CEO→Manager→Worker hierarchy. CEO never writes code directly.
-- Use `/wf-auto` for perpetual self-directed optimization — never stops, continuously improves until 8-angle exhaustion.
-- Use `subagent-orchestrator` and `Harness/subagents.md` when coordinating multiple subagents.
-- Use `/wf-update` to check for and apply scaffold updates from GitHub. See `.claude/skills/wf-update/SKILL.md`.
 - Subagents are readers and reporters. Only the main agent writes to `Harness/tasks/<task-id>/PROGRESS.md` and `Harness/tasks/<task-id>/PLAN.md`.
-- For memory writing and consolidation (repeated failures, user corrections, closeout), dispatch `memory-master`.
-- For context analysis and compression alerts (~85% window), dispatch `context-master`.
-- Universal rules live in `.claude/rules/ecc/common.md`.
+- Invoke multi-agent work via `subagent-orchestrator` and `Harness/subagents.md`. Update harness via `/wf-update` (see `.claude/skills/wf-update/SKILL.md`).
+- For memory writing, dispatch `memory-master`. For context analysis, dispatch `context-master`.
 - Never bulk-read `Harness/`; route through `Harness/README.md` and `Harness/MEMORY.md`.
 - Scaffold source files live under `templates/common/` and `templates/optional/`; generated dogfood runtime files live under root `Harness/` and `.claude/`.
 
@@ -86,9 +80,10 @@ This repository dogfoods the generated Harness scaffold. Scaffold source files l
 - **Closeout trigger**: during WF closeout, dispatch `context-master` to extract durable knowledge, then `memory-master` to consolidate into `Harness/memory/*`.
 - Never record secrets, credentials, tokens, or private data in memory.
 
-## 7. CEO Constraints
+## 7. Mode Constraints
 
 - Never call `EnterPlanMode` — delegate planning to `planner` subagents (see `Harness/WF.md`).
-- Never write code directly in `/wf` or `/wf-max` mode — delegate all implementation to subagents (see `Harness/WF-MAX.md`).
-- **Enforcement**: `.claude/settings.json` denies `EnterPlanMode` via the `deny` list. CEO contract is in [Section 1a](#1a-ceo-contract-read-before-any-tool-use) — read it first.
-- WF-MAX hooks in `.claude/settings.json` block CEO Edit/Write/MultiEdit/Bash on source files. `Harness/.runtime/current-mode.json` persists mode state across sessions.
+- Never write code directly in `/wf` or `/wf-max` CEO mode — delegate all implementation to Workers via dispatch packets with explicit writeSet.
+- **WF-MAX three-layer architecture**: global mode (`wf-max`) ≠ agent role (`ceo|manager|worker|reviewer`). Workers follow dispatch packet (writeSet, forbidden, verification). Missing role/writeSet → source edits denied by default.
+- **Enforcement**: `.claude/settings.json` denies `EnterPlanMode` via the `deny` list. Role contract is in [Section 1a](#1a-wf-max-role-contract-read-before-any-tool-use) — read it first.
+- WF-MAX hooks in `.claude/settings.json` enforce per-agentRole + writeSet. `Harness/.runtime/current-mode.json` persists mode state; stale modes (>30 min) auto-clear.