create-harness-vibe-coding 0.8.7 → 0.8.9

package/templates/common/{MEMORY.md → Harness/MEMORY.md}

@@ -1,6 +1,6 @@
 # MEMORY.md - create-harness-vibe-coding Project Resource Index
 
-> The project fact source is reached via `CLAUDE.md -> Harness/README.md`. This file persists cross-session context: resource index, user preferences, tool usage standards.
+> `CLAUDE.md` is the session entry router; `Harness/README.md` is the Harness documentation index. This file persists cross-session context: resource index, user preferences, tool usage standards.
 > Detailed memory lives in `Harness/memory/`. Keep entries short, newest first, and free of secrets.
 
 ## Agents (Sub-agents)
@@ -16,6 +16,8 @@
 - [reviewer](../.claude/agents/reviewer.md) - read-only spec/AC and code/architecture/test review.
 - [verifier](../.claude/agents/verifier.md) - verification commands and AC evidence matrix.
 - [reflector](../.claude/agents/reflector.md) - closeout synthesis, contradiction check, and final acceptance gate verdict.
+- [task-scribe](../.claude/agents/task-scribe.md) - task state, heartbeat, dispatch ledger, evidence pointers — small-fast chore agent.
+- [codebase-explorer](../.claude/agents/codebase-explorer.md) - scoped read-only source exploration, file discovery, symbol tracing — small-fast.
 - [memory-master](../.claude/agents/memory-master.md) - memory writing, dedup, consolidation, and cross-project knowledge extraction.
 - [context-master](../.claude/agents/context-master.md) - context analysis, compression alerts, and session knowledge extraction for memory-master.
 - [explore-manager](../.claude/agents/explore-manager.md) - WF-MAX W0 exploration: spawn 5-10 read-only researchers, synthesize, report to CEO.
@@ -27,15 +29,15 @@ Stack-specific agents can be added after the product shape is known.
 
 ## Skills (Workflows)
 
-- [WF Mode](WF.md) - complete role chain: plan, research/docs, architecture, test, implement, validation, cross-review, reflector, acceptance.
+- [WF Mode](WF.md) - WF-KERNEL tiered orchestration: WF-Light (minimal roles), WF-Standard (adds review), WF-Full (complete role chain incl. reflector and cross-review).
 - [wf](../.claude/skills/wf/SKILL.md) - Claude Code WF skill command; mirrored for Codex at `../.agents/skills/wf/SKILL.md`.
 - [subagent-orchestrator](../.claude/skills/subagent-orchestrator/SKILL.md) - controller-led subagent orchestration, parallel read-only passes, review gates, and recovery handoffs.
 - [wf-readme](../.claude/skills/wf-readme/SKILL.md) - README preservation, append-only development sections, structured tables, and approved architecture diagrams.
 - [wf-review](../.claude/skills/wf-review/SKILL.md) - cross-model peer review: invoke the other agent CLI (Codex/Claude) for independent review.
 - [wf-update](../.claude/skills/wf-update/SKILL.md) - GitHub-based incremental harness update, checksum comparison, and safe in-place updates.
 - [wf-learn](../.claude/skills/wf-learn/SKILL.md) - force memory learning cycle: context-master -> memory-master -> project + global memory.
-- [wf-max](../.claude/skills/wf-max/SKILL.md) - WF strict superset: complete role chain plus maximum parallelism, current runtime subagents first, cross-CLI overflow when available.
-- [wf-auto](../.claude/skills/wf-auto/SKILL.md) - perpetual auto-optimization: bounded ticks, 8-angle internal scan, intent checkpoints, evidence ledger.
+- [wf-max](../.claude/skills/wf-max/SKILL.md) - WF kernel + maximum safe fan-out: WF-Max-Useful by default (fan out only where independent), WF-Max-Strict only on explicit strict request; current runtime subagents first, cross-CLI overflow when available.
+- [wf-auto](../.claude/skills/wf-auto/SKILL.md) - perpetual adaptive auto-optimization: evidence-selected probes, dynamic obligations, intent checkpoints, evidence ledger.
 - [wf-auto-spark](../.claude/skills/wf-auto-spark/SKILL.md) - perpetual inspiration mode: external spark search, long-term roadmap with staged milestones, <=50% deviation guard.
 - [tdd](../.claude/skills/tdd/SKILL.md) - acceptance-driven TDD: AC-linked RED tests, real UI clicks for browser-visible behavior, Playwright/CDP evidence, and configured coverage gate.
 - [wf-remove](../.claude/skills/wf-remove/SKILL.md) - safely remove Harness framework files (SAFE/MODIFIED/USER classes), auto-prune empty directories, backup option.
@@ -48,6 +50,8 @@ Codex repo-skill mirrors live under `../.agents/skills/` with the same skill nam
 
 Stack-specific skills can be added after the product shape is known.
 
+- [browser-e2e](workflows/browser-e2e.md)
+
 ## Rules (Harness Constraints)
 
 Located under `.claude/rules/ecc/`, auto-loaded by the CC engine:
@@ -65,6 +69,9 @@ Located under `.claude/rules/ecc/`, auto-loaded by the CC engine:
 - [Memory protocol](MEMORY_PROTOCOL.md)
 - [WF mode](WF.md)
 - [WF Max mode](WF-MAX.md)
+- [WF kernel contract](WF-KERNEL.md)
+- [WF state machine / resume](WF-STATE.md)
+- [Task archive mechanism](TASK_ARCHIVE.md)
 - [0-1 lifecycle](lifecycle.md)
 - [Research protocol](research/README.md)
 - [Context loading protocol](context-loading.md)
@@ -79,6 +86,12 @@ Located under `.claude/rules/ecc/`, auto-loaded by the CC engine:
 
 ## Memory Folder
 
+> L2 startup digest: `memory/startup-hints.md` — lightweight hints loaded at session start.
+> L3 route index: `memory/routes.md` — scenario hit-rules index (not detailed memory).
+> L3 detailed files: loaded only when scenario matches via routes.
+
+- [Startup hints](memory/startup-hints.md) - L2 lightweight startup digest (5-10 hints, no dates). Loaded at Harness session start; not a replacement for full router.
+- [Memory routes](memory/routes.md) - L3 route index with signals/scoring/avoid rules. Not detailed memory — hit-rules only.
 - [Tool usage/reflections](memory/tool-usage-reflections.md) - repeated tool failures, better command patterns, environment-specific fixes.
 - [User corrections/preferences](memory/user-corrections-preferences.md) - repeated user corrections, durable preferences, common-sense course corrections.
 - [Agent lessons/patterns](memory/agent-lessons-patterns.md) - reusable lessons from review, debugging, validation, and handoff loops.

package/templates/common/Harness/MEMORY_PROTOCOL.md

@@ -4,27 +4,35 @@ Purpose: record durable lessons from acceptance, validation, and debug work with
 
 Memory is downstream of evidence. It records reusable patterns, not raw transcripts.
 
+## L1/L2/L3 Memory Architecture
+
+- **L1 = File/Project Facts**: CLAUDE.md, Harness/README.md, PROGRESS/task capsules. Always loaded when relevant.
+- **L2 = Startup Digest**: `Harness/memory/startup-hints.md`. Lightweight hints loaded at session start. Not a replacement for full router.
+- **L3 = Detailed Durable Memory**: `Harness/memory/*.md` files. Loaded only when scenario matches via `routes.md`.
+
 ## When To Write Memory
 
 Write memory when any condition applies:
 
-- the same tool or command pattern fails 3+ times
-- the user corrects the same assumption or preference 2+ times
-- a review/debug loop reveals a reusable lesson
-- WF closeout extracts durable acceptance, validation, or debug knowledge
+- **Explicit user preference**: 用户显式说 remember/next time/never/always/记住/下次/不要再 时，清晰、安全、场景明确可立即写入 L3 (explicit user preference can be written immediately when safe and scoped)
+- **Repeated implicit correction**: 同一假设/模式被纠正 2+ 次 — user corrects the same assumption or preference 2+ times
+- **Tool/command pattern fails 3+ times**: 同类工具/命令失败 3+ 次 — same tool or command pattern fails 3+ times
+- **Review/debug/validation lesson**: 只有可复用、能防回归时才写
+- **WF closeout**: context-master 提取 durable knowledge 后写入
 
 ## What To Record
 
-Memory entries should be short, newest-first, and AC-aware when possible:
+Memory entries should be short and AC-aware when possible. Use **compact format** (default no date):
 
 ```markdown
-## 2026-07-02 - Playwright login validation needs network trace
-
-- Context: AC-003 passed visually but failed API payload validation.
-- Lesson: For login flows, require CDP/Playwright request assertions in addition to DOM checks.
-- Applies to: `ACCEPTANCE_PROTOCOL.md`, `HARNESS_BRIDGE.md`
+- When <scenario>: <rule>. Avoid <over-application>. Signals: <signals>.
 ```
 
+Only use date/timestamp headings when:
+- Entry supersedes prior conflicting guidance
+- Time-sensitive context (version, deprecation)
+- Conflict resolution needed
+
 Good memory:
 
 - failure mode
@@ -39,38 +47,61 @@ Bad memory:
 - full logs when a summary is enough
 - transient speculation
 - implementation summaries with no reusable lesson
+- task logs, process summaries, one-time emotions
 
-## Closeout Flow
+## Memory Candidate Detection
 
-For WF closeout:
+**Explicit trigger phrases** (中英文):
+- 英文: remember, next time, don't, do not, never, always, I prefer, I want you to
+- 中文: 记住, 下次, 以后, 不要再, 总是, 永远不要, 我偏好, 我希望你以后
 
-```text
-context-master
--> extract durable acceptance/debug/validation lessons
--> memory-master
--> deduplicate
--> write concise memory entry
+**Decision flow**:
+```
+detect candidate -> classify target file -> safety filter -> dedup -> write/update -> return concise summary
 ```
 
-Memory Master writes to:
+- **Explicit user preference**: can be written immediately when safe and scoped
+- **Repeated implicit correction**: still requires 2+ occurrences
+- **Tool failure**: 3+ same failures required
+- **Review/debug lesson**: only when reusable and regression-preventing
 
-- `Harness/memory/tool-usage-reflections.md`
-- `Harness/memory/user-corrections-preferences.md`
-- `Harness/memory/agent-lessons-patterns.md`
-- `Harness/MEMORY.md` only for routing/index updates
+## Memory Routing (L3)
 
-## Scenario Memory Hints
+Routes are defined in `Harness/memory/routes.md`. Not detailed memory, but hit-rules index.
+
+**Scenario pack**: intent / files / commands / signals / risk
+
+**Scoring**:
+- +4 exact file/path match
+- +3 explicit trigger phrase match
+- +3 command/error signature match
+- +2 workflow/mode match
+- +1 keyword overlap
+- -4 avoid match
+
+**Thresholds**:
+- score >= 5: load matching entry/file section
+- score 3-4: load route summary only
+- score < 3: load nothing
+
+**Hard triggers** (bypass scoring):
+- Explicit user memory statement → user-corrections-preferences.md
+- Same command fails 3x → tool-usage-reflections.md
+- Review/debug/validation reusable lesson → agent-lessons-patterns.md
+- Modifying hook-related files → load only-wf-auto hook lesson
+- /wf-learn → full learning cycle
 
-Controllers, context-master, or memory-master may load a compact memory hint
-when the current task matches a known scenario. Hints must be scenario-specific
-and must not dump full memory files into context.
+**Load logging**: always state `memory hints loaded: <id> because <signal>`
 
-Scenario hints are allowed when they help the current task avoid a known failure
-mode:
+No embedding; keep stable, explainable, token-efficient.
+
+## Scenario Memory Hints
+
+Controllers, context-master, or memory-master may load a compact memory hint when the current task matches a known scenario.
 
 | Scenario | Load Or Hint |
 | --- | --- |
-| new session / startup | `Harness/MEMORY.md` index only |
+| new session / startup | `Harness/memory/startup-hints.md` (L2 digest) |
 | same tool or command error repeats | matching entries from `memory/tool-usage-reflections.md` |
 | user repeats a correction or preference | matching entries from `memory/user-corrections-preferences.md` |
 | review/debug/validation failure | matching entries from `memory/agent-lessons-patterns.md` |
@@ -87,6 +118,25 @@ Hint rules:
 - never inject secrets, credentials, tokens, private data, or raw transcripts
 - memory-master owns writes; controller/context-master route context
 
+## Closeout Flow
+
+For WF closeout:
+
+```text
+context-master
+-> extract durable acceptance/debug/validation lessons
+-> memory-master
+-> deduplicate
+-> write concise entry
+```
+
+Memory Master writes to:
+
+- `Harness/memory/tool-usage-reflections.md`
+- `Harness/memory/user-corrections-preferences.md`
+- `Harness/memory/agent-lessons-patterns.md`
+- `Harness/MEMORY.md` only for routing/index updates
+
 ## Memory Write Flow
 
 Memory write triggers must never append raw logs directly to memory files.

package/templates/common/Harness/PROGRESS.md

@@ -1,17 +1,17 @@
-# PROGRESS.md
-
-Global task index. Load at session start to see what is active and what was done.
-
-## Active Task
-
-None — create a new task from `Harness/tasks/_template/` when work spans more than one step.
-
-## Task Index
-
-| ID | Goal | Phase | Closed |
-|----|------|-------|--------|
-
-## Cross-Task Decisions
-
-| Date | Decision | Reason |
-|------|----------|--------|
+# PROGRESS.md
+
+Global task index. Load at session start to see what is active and what was done.
+
+## Active Task
+
+None — create a new task from `Harness/tasks/_template/` when work spans more than one step.
+
+## Task Index
+
+| ID | Goal | Phase | Closed |
+|----|------|-------|--------|
+
+## Cross-Task Decisions
+
+| Date | Decision | Reason |
+|------|----------|--------|

package/templates/common/Harness/README.md

@@ -1,8 +1,43 @@
 # create-harness-vibe-coding - Harness Router
 
-Purpose: route humans and agents to the smallest useful context. `Harness/README.md` is the primary router.
+Purpose: route humans and agents to the smallest useful context. `CLAUDE.md` is the session entry router; `Harness/README.md` is the primary Harness documentation router.
 
-Default load: `CLAUDE.md`, `Harness/MEMORY.md`, this file, and `Harness/PROGRESS.md` when work is active. Do not read the whole `Harness/` tree.
+Default load: `CLAUDE.md`. For workflow commands (`/wf`, `/wf-max`, `/wf-auto`, `/wf-review`, `/wf-learn`, `/wf-readme`, `/wf-remove`, `/wf-browser`, `/wf-auto-spark`), also load `Harness/MEMORY.md` (index only per Memory Preflight), this file, and `Harness/PROGRESS.md` when work is active.
+
+`/wf-help` and `/wf-update` are **direct commands**: skip the router, do NOT load `Harness/MEMORY.md`, do NOT enter WF, execute immediately.
+
+Do not read the whole `Harness/` tree.
+
+## Resume Routing / Active Task Resume
+
+`Harness/PROGRESS.md` is the global active pointer. `Harness/tasks/<task-id>/STATE.json` is the machine-readable resume entry.
+
+On session start (new window, reopen, resume):
+1. If the user says "continue", "resume", "last task", "current task", "status", or the work is not a simple direct task, read `Harness/PROGRESS.md`.
+2. Find the Active Task, then read `Harness/tasks/<active-task>/STATE.json` first.
+3. From STATE.json, determine:
+   - Current phase — what was in progress
+   - activeQuestion — is a user answer needed before proceeding?
+   - ready queue — can work be dispatched immediately?
+   - running items — need result confirmation?
+   - blocked — what's blocking?
+   - nextAction — what to do next
+4. Do NOT discover context by reading all task directories. Use the active pointer.
+5. Direct simple tasks may skip STATE/PLAN/PROGRESS unless the user says "continue"/"resume".
+
+See `Harness/WF-STATE.md` for the full state machine contract and enums.
+
+## Direct Mode (Degradation Path)
+
+When the user does NOT explicitly invoke `/wf-*`, `$wf-*`, `/skills wf`, `/skills wf-max`, or say `wf` / `wf-max`, the request is handled in **direct mode**. Skip the router entirely. Execute the task. Do not load `Harness/MEMORY.md`, `Harness/README.md`, or `Harness/PROGRESS.md`.
+
+Complex work may use direct planning, task capsules, tests, and subagents without entering WF.
+
+Escalate to the router (next section) only when:
+- User explicitly invokes `/wf`, `/wf-max`, `$wf`, `$wf-max`, `/skills wf`, `/skills wf-max`, or says `wf` / `wf-max`
+- User invokes another workflow `/wf-*` command (NOT `/wf-help` or `/wf-update` — those are direct commands)
+
+`/wf-help` and `/wf-update` are direct commands executed immediately without router load.
 
 ## 0-1 Flow
 
@@ -55,37 +90,39 @@ Keywords are retrieval hints, not project facts.
 
 Load the matching row only. Add adjacent docs only when the loaded doc directly names them.
 
-Routing priority: if a request explicitly says `/wf <task>`, `$wf`, `wf mode`, `workflow mode`, or `wk mode`, or is long, difficult, uncertain, repeated-failure, migration, architecture-heavy, browser-visible, or broad multi-agent implementation work, choose the WF row first. Load `Harness/WF.md` directly, then delegate subagent coordination to `subagent-orchestrator`. If the request says `/wf-auto`, `$wf-auto`, `wf auto`, or `auto mode`, choose the WF-AUTO row and load `Harness/WF-AUTO.md`.
+Routing priority: **direct mode is the default** when no explicit WF token is present. Complex tasks may still plan, test, and use subagents without entering WF. If a request contains an explicit WF token (`/wf`, `$wf`, `/skills wf`, `/wf-max`, `$wf-max`, `/skills wf-max`), follow the WF contract. WF mode has three tiers: **WF-Light** (low-risk, explicit `/wf` — planner/test/verifier; no mandatory research/architecture/cross-review/reflector), **WF-Standard** (multi-file or behavior change — compact ACs, one implementer, one independent validation/review), **WF-Full** (high-risk, cross-layer, security/data-loss, browser/API, ambiguous architecture, or user asks for full role chain). `/wf-max` has two modes: **WF-Max-Useful** (default — fan-out only where write sets or review lenses are meaningfully independent) and **WF-Max-Strict** (explicit strict override preserving unconditional fan-out).
 
 | When to Read | Keywords | Load | Output |
 | --- | --- | --- | --- |
+| **Direct mode (default)** | simple, single-step, low-risk, commit, push, one-line, read, question, status, no /wf-* command | Nothing beyond CLAUDE.md | Direct execution; no router load |
 | Raw idea or vague product request | idea, vague, clarify, goal, non-goal, lifecycle | [lifecycle.md](lifecycle.md), [research/PRD.md](research/PRD.md) | clarified goal, non-goals, first questions |
 | Need market/tech direction | research, market, competitor, stack, library, pricing, policy | [research/README.md](research/README.md), [research/research-results.md](research/research-results.md) | research protocol, adopted/rejected choices |
 | Need MVP/spec | PRD, MVP, scope, requirement, acceptance, non-goal | [research/PRD.md](research/PRD.md), [ACCEPTANCE_PROTOCOL.md](ACCEPTANCE_PROTOCOL.md) | Mini PRD with AC IDs and verifiable acceptance criteria |
 | Need architecture or boundaries | architecture, boundary, layer, port, adapter, dependency | [architecture.md](architecture.md) | layer map, ports, constraints |
 | Need WF command help | /wf-help, wf help, command list, list wf commands | `.claude/commands/wf-help.md` | direct command table; no skill invocation |
-| Need WF mode | wf, /wf, $wf, wf mode, workflow mode, wk mode, long task, difficult, stuck, repeated failure | [WF.md](WF.md), [PROGRESS.md](PROGRESS.md), the current task `tasks/<id>/PROGRESS.md` and `tasks/<id>/PLAN.md` | complete role chain, heartbeat, recovery loop; explicit WF/WK loads subagent docs immediately |
-| Need perpetual auto-optimization | /wf-auto, $wf-auto, wf auto, auto mode, never stop, self-improve, continuous optimize | [WF-AUTO.md](WF-AUTO.md), [subagents.md](subagents.md), [dispatch.md](dispatch.md) | perpetual loop, bounded ticks, optional wf-auto-only hook exception, 8-angle scan, spark search, intent checkpoint, evidence ledger; CEO never writes code |
-| Need perpetual inspiration mode | /wf-auto-spark, $wf-auto-spark, wf auto spark, spark mode, external inspiration, discover mode, never stop | [WF-AUTO-SPARK.md](WF-AUTO-SPARK.md), [WF-AUTO.md](WF-AUTO.md), [subagents.md](subagents.md), [dispatch.md](dispatch.md) | roadmap-anchored: North Star + milestones; external spark search; <=50% deviation guard; never auto-stops |
-| Need WF-MAX mode | /wf-max, $wf-max, wf max, maximum parallelism, CEO, Manager, Worker, fan-out | [WF-MAX.md](WF-MAX.md), [subagents.md](subagents.md), [dispatch.md](dispatch.md) | WF strict superset: complete role chain plus maximum fan-out, current runtime subagents first, cross-CLI overflow when available |
+| Need WF mode (explicit only) | /wf, $wf, /skills wf (explicit user token only) | [WF.md](WF.md), [WF-KERNEL.md](WF-KERNEL.md), [PROGRESS.md](PROGRESS.md), the current task `tasks/<id>/PROGRESS.md` and `tasks/<id>/PLAN.md` | dynamic ready-queue orchestration, tier-gated acceptance |
+| Need perpetual auto-optimization | /wf-auto, $wf-auto, /skills wf-auto (explicit user token only) | [WF-AUTO.md](WF-AUTO.md), [WF-AUTO-ANGLES.md](WF-AUTO-ANGLES.md), [subagents.md](subagents.md), [dispatch.md](dispatch.md) | perpetual loop, adaptive probe selection, dynamic risk obligations, spark search, intent checkpoint, evidence ledger; CEO never writes code |
+| Need perpetual inspiration mode | /wf-auto-spark, $wf-auto-spark, /skills wf-auto-spark (explicit user token only) | [WF-AUTO-SPARK.md](WF-AUTO-SPARK.md), [WF-AUTO.md](WF-AUTO.md), [subagents.md](subagents.md), [dispatch.md](dispatch.md) | roadmap-anchored: North Star + milestones; external spark search; <=50% deviation guard; never auto-stops |
+| Need WF-MAX mode (explicit only) | /wf-max, $wf-max, /skills wf-max (explicit user token only) | [WF-MAX.md](WF-MAX.md), [WF-KERNEL.md](WF-KERNEL.md), [subagents.md](subagents.md), [dispatch.md](dispatch.md) | /wf kernel + max safe fan-out (WF-Max-Useful default, WF-Max-Strict override) |
 | Need peer review | /wf-review, $wf-review, peer review, second opinion, cross-check, stuck | `.claude/skills/wf-review/SKILL.md`, `.agents/skills/wf-review/SKILL.md`, `Harness/README.md` | cross-model multi-dimension review with severity classification |
 | Adding harness to existing project | existing project, onboarding, migrate, bootstrap, preserve, conflict | [extension.md](extension.md), [PROGRESS.md](PROGRESS.md), root `README.md` and package/CI files | discovered project facts, preserved config, manual registration plan |
 | README optimization | README, docs, quickstart, install docs, architecture diagram, command table, documentation polish | root `README.md`, `.claude/skills/wf-readme/SKILL.md`, [PROGRESS.md](PROGRESS.md), [architecture.md](architecture.md) as needed | approved README mode, preserved sections, proposed diff plan |
 | Need implementation plan | plan, task, write set, verify, milestone, progress | [PROGRESS.md](PROGRESS.md), the current task `tasks/<id>/PROGRESS.md` and `tasks/<id>/PLAN.md`, [agent-workflow.md](agent-workflow.md), [ACCEPTANCE_PROTOCOL.md](ACCEPTANCE_PROTOCOL.md) | tasks, AC IDs, write set, verification commands |
+| Browser E2E testing or automation | /wf-browser, browser, e2e, web automation, form fill, screenshot verify, page test, browser test, Playwright AI, Browser Use, CDP | browser-e2e workflow, [HARNESS_BRIDGE.md](HARNESS_BRIDGE.md), wf-browser skill, Browser Use skill | UI/API contract, CLI commands, screenshots, traces, validation matrix |
 | Optional workflow installed | workflow, optional, ui-ux-review, github-pr-review, python-backend, ts-react-frontend | matching `workflows/*.md` (if installed), [extension.md](extension.md) | workflow-specific evidence, commands, fallback path |
 | Need durable memory or reflection | memory, remember, preference, correction, tool failure, lesson, reflection, scenario memory | [MEMORY.md](MEMORY.md), [MEMORY_PROTOCOL.md](MEMORY_PROTOCOL.md), `Harness/memory/tool-usage-reflections.md`, `Harness/memory/user-corrections-preferences.md`, `Harness/memory/agent-lessons-patterns.md` | concise newest-first memory entry, scenario memory hint, or no-op rationale |
 | Need subagents | subagent, role pack, context, inject, return format, orchestrator, isolation | [subagents.md](subagents.md), [context-loading.md](context-loading.md), [dispatch.md](dispatch.md), [AGENT_ISOLATION.md](AGENT_ISOLATION.md) | controller plan, role-specific context pack, isolation-aware dispatch pack |
 | Need feature work | feature, implementation, TDD, test, review, closeout | [tasks/_template/PLAN.md](tasks/_template/PLAN.md), [agent-workflow.md](agent-workflow.md), [TDD-GUIDE.md](TDD-GUIDE.md), [ACCEPTANCE_PROTOCOL.md](ACCEPTANCE_PROTOCOL.md) | task plan, AC-linked RED tests, implementation loop |
 | Review or release check | review, release, finding, risk, evidence, verification | [agent-workflow.md](agent-workflow.md), current feature doc | findings, verification evidence |
 | Harness readiness check | validate, readiness, placeholder, missing file, release gate | `Harness/scripts/validate-harness.mjs`, `Harness/scripts/validate-harness.mjs --strict` | structural install check; strict bootstrap/release placeholder check |
-| Need harness update | /wf-update, $wf-update, update, check for updates, harness version | `.claude/skills/wf-update/SKILL.md`, `.agents/skills/wf-update/SKILL.md`, `Harness/.harness-version`, `Harness/scripts/wf-update-check.mjs` | script-driven comparison, SAFE/CONFLICT/PRESERVE classification, user decides conflicts |
+| Need harness update | /wf-update, $wf-update, update, check for updates, harness version | `.claude/commands/wf-update.md`, `.opencode/commands/wf-update.md`, `Harness/.harness-version`, `Harness/scripts/wf-update-check.mjs`; Codex fallback: `.claude/skills/wf-update/SKILL.md` | script-driven comparison, SAFE/CONFLICT/PRESERVE classification, user decides conflicts |
 | Need harness removal | /wf-remove, $wf-remove, wf remove, remove harness, uninstall harness | `.claude/skills/wf-remove/SKILL.md`, `.agents/skills/wf-remove/SKILL.md`, `Harness/scripts/wf-remove.mjs` | safe removal plan: auto-remove SAFE, confirm MODIFIED, never touch USER DATA |
 
 ## Gates
 
 - Move phases in order unless the user asks for a fast lane.
-- Use `/wf <task>` in Claude Code, `$wf` in Codex, `/wf-max [task]` or `$wf-max`, `wf mode`, `workflow mode`, or `wk mode` when a task is long, difficult, uncertain, multi-file, or repeatedly failing.
-- Use `/wf-auto` for perpetual self-directed optimization that never stops until 8-angle exhaustion.
+- Use `/wf <task>` in Claude Code or `$wf` in Codex, or `/wf-max [task]` / `$wf-max` for maximum-parallelism mode. WF mode is explicit only. WF-Light for low-risk, WF-Standard for multi-file, WF-Full for high-risk/cross-layer. `/wf-max` defaults to useful-fanout (WF-Max-Useful); use explicit `--strict` or "strict wf-max" for unconditional fan-out (WF-Max-Strict).
+- Use `/wf-auto` for perpetual self-directed optimization. It selects probes from project evidence and stops only after dynamic risk obligations and two different empty confirmation passes are recorded.
 - **WF-MAX Role Contract**: Three-layer architecture: global mode (`wf-max`), agent role (`ceo|manager|worker|verifier|reviewer|reflector`), dispatch permission (`writeSet`, `forbidden`, `verification`). CEO never writes source code. Workers edit only dispatch.writeSet. Compliance is checked through dispatch packets, independent review, validation evidence, and task capsules. See `CLAUDE.md#1a`.
 - **WF-REVIEW Anti-Self-Review**: Must invoke the OTHER CLI (Codex -> Claude, or Claude -> Codex). Same-model simulation is forbidden.
 - WF-MAX has no runtime hook state. The durable state is the task capsule, dispatch table, review findings, and validation evidence. The only runtime hook exception in Harness is the optional `/wf-auto` bounded tick hook described in `WF-AUTO.md`.
@@ -111,35 +148,37 @@ Routing priority: if a request explicitly says `/wf <task>`, `$wf`, `wf mode`, `
 | Category | Files |
 |----------|-------|
 | **Router + Index** | `README.md`, `MEMORY.md`, `PROGRESS.md` |
-| **Task Capsule** | `tasks/<id>/PROGRESS.md`, `tasks/<id>/PLAN.md`, `tasks/_template/` |
-| **Workflows** | `WF.md`, `WF-MAX.md`, `WF-AUTO.md`, `WF-AUTO-SPARK.md` |
+| **Task Capsule** | `tasks/<id>/PROGRESS.md`, `tasks/<id>/PLAN.md`, `tasks/<id>/STATE.json`, `tasks/_template/` |
+| **Workflows** | `WF.md`, `WF-KERNEL.md`, `WF-STATE.md`, `WF-MAX.md`, `WF-AUTO.md`, `WF-AUTO-SPARK.md` |
 | **Protocols** | `ACCEPTANCE_PROTOCOL.md`, `AGENT_ISOLATION.md`, `HARNESS_BRIDGE.md`, `DEBUG_PROTOCOL.md`, `MEMORY_PROTOCOL.md` |
-| **Guides** | `ECC-GUIDE.md`, `TDD-GUIDE.md`, `lifecycle.md`, `architecture.md` |
-| **Orchestration** | `subagents.md`, `context-loading.md`, `dispatch.md`, `agent-workflow.md`, `extension.md` |
+| **Guides** | `ECC-GUIDE.md`, `TDD-GUIDE.md`, `lifecycle.md`, `architecture.md`, `TASK_ARCHIVE.md` |
+| **Orchestration** | `subagents.md`, `context-loading.md`, `dispatch.md`, `agent-workflow.md`, `extension.md`, `WF-STATE.md` |
 | **Research** | `research/README.md`, `research/PRD.md`, `research/research-results.md` |
 | **Acceptance Templates** | `templates/PRD.template.md`, `templates/ACCEPTANCE.template.md`, `templates/UI_CONTRACT.template.md`, `templates/API_CONTRACT.template.md`, `templates/TEST_PLAN.template.md`, `templates/PLAYWRIGHT_SPEC.template.ts`, `templates/VALIDATION_REPORT.template.md` |
 | **Memory** | `memory/tool-usage-reflections.md`, `memory/user-corrections-preferences.md`, `memory/agent-lessons-patterns.md` |
-| **Scripts** | `scripts/validate-harness.mjs`, `scripts/wf-update-check.mjs`, `scripts/wf-remove.mjs` |
+| **Scripts** | `scripts/validate-harness.mjs`, `scripts/wf-update-check.mjs`, `scripts/wf-remove.mjs`, `scripts/archive-tasks.mjs` |
 | **Runtime** | `.harness-version` |
 | **Agents + Skills** | `.claude/agents/*`, `.claude/skills/*`, `.agents/skills/*` |
-| **Direct Commands** | `.claude/commands/wf-help.md` |
+| **Direct Commands** | `.claude/commands/wf-help.md`, `.claude/commands/wf-update.md`, `.opencode/commands/wf-help.md`, `.opencode/commands/wf-update.md` |
 
 ## Direct Commands
 
 | Command | Purpose |
 |---|---|
 | `/wf-help` | Directly returns a table of all Harness WF commands, usage, and purpose. It does not invoke a skill or start a workflow. |
+| `/wf-update` | Script-driven harness update: fetch + compare + apply. Direct command for Claude Code and OpenCode; skill path available for Codex compatibility. |
 
 ## Skill Commands
 
 | Claude Code | Codex | Purpose |
 |---|---|---|
-| `/wf <task>` | `$wf <task>` | Complete role chain: plan, research/docs, architecture, test, implement, validation, cross-review, reflector, acceptance |
-| `/wf-max [task]` | `$wf-max [task]` | WF strict superset with maximum parallelism: CEO -> Manager -> Worker, cross-CLI overflow |
-| `/wf-auto` | `$wf-auto` | Perpetual auto-optimization: never stops until 8-angle exhaustion |
+| `/wf <task>` | `$wf <task>` | Tiered WF: WF-Light (low-risk, planner/test/verifier), WF-Standard (multi-file, compact ACs), WF-Full (high-risk/cross-layer, full role chain) |
+| `/wf-max [task]` | `$wf-max [task]` | WF-Max-Useful default (fan-out only where independent), WF-Max-Strict override (unconditional fan-out) |
+| `/wf-auto` | `$wf-auto` | Perpetual adaptive auto-optimization: dynamic probes, risk obligations, evidence-based exhaustion |
 | `/wf-auto-spark` | `$wf-auto-spark` | Perpetual inspiration: spark search, roadmap-anchored, <=50% deviation guard, never auto-stops |
 | `/wf-review [focus]` | `$wf-review [focus]` | Cross-model peer review via Codex <-> Claude |
 | `/wf-learn` | `$wf-learn` | Force learning cycle: context-master -> memory-master |
+| `/wf-browser [task]` | `$wf-browser [task]` | AI-driven browser automation for E2E testing |
 | `/wf-readme [task]` | `$wf-readme [task]` | README preservation, merge, and documentation improvement workflow |
 | `/wf-update` | `$wf-update` | Script-driven harness update: fetch + compare + apply |
 | `/wf-remove` | `$wf-remove` | Safe harness removal: auto-delete SAFE, confirm MODIFIED, preserve USER DATA |