harness-everything 0.16.0 → 0.16.1

package/.claude-plugin/marketplace.json

@@ -10,7 +10,7 @@
       "name": "harness-everything",
       "source": "./",
       "description": "Harness OS: an orchestrated agent operating system — tier routing, circuit breaker guardrails, verification gates, WAL session memory, and self-evolving workspace rules.",
-      "version": "0.16.0",
+      "version": "0.16.1",
       "author": {
         "name": "Miya Daniel"
       },

package/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "harness-everything",
   "description": "Harness OS: an orchestrated agent operating system — tier routing, circuit breaker guardrails, verification gates, WAL session memory, and self-evolving workspace rules.",
-  "version": "0.16.0",
+  "version": "0.16.1",
   "author": {
     "name": "Miya Daniel"
   },

package/AGENTS.md

@@ -40,8 +40,8 @@ The retained [OpenCode evidence](benchmarks/results/live-host/opencode-2026-09-1
 7. **Runtime/workflow claims are generated facts.** `package.json`, `.nvmrc`, Dockerfile, and active workflows feed `scripts/repository-contract.js`; run `npm run docs:sync` after relevant changes.
 8. **CHANGELOG.md keeps pending human-authored notes under `[Unreleased]`.** Semantic-release owns stable headings/tags/release notes.
 9. **Conventional Commit type is release input.** Breaking→major; `feat`→minor; `fix`/`perf`/`refactor`/`build`/`revert`→patch; docs/test/ci/style/chore do not release by themselves.
-10. **Selected workflow is mandatory; reasoning inside it stays flexible.** Before omitting a suggested skill, read/evaluate its complete `SKILL.md` flow. Suggested skills may be `not-applicable` with a flow-grounded reason, but a selected topology must be executed to resolution. Do not bypass it because the task feels simple/routine/already clear. Escape is limited to genuinely uncovered workflow scope or host-capability loss and requires explicit scope + evidence. Do not turn this into one universal TODO/TDD/Fable sequence.
-11. **Major mutation requires Git worktree isolation.** Read-only discovery may stay in the bound repository. Tier 3 / Fable source and artifact changes must target a verified linked worktree belonging to that repository; creation failure means `blocked`. Worktree isolation is separate from durable multi-agent workspace state. Scoped escape never waives it. See [workflow-runtime.md](docs/workflow-runtime.md) for the tested boundary and limitations.
+10. **Selected workflow is planning guidance; reasoning and execution stay flexible.** Before omitting a suggested skill, read/evaluate its complete `SKILL.md` flow. Do not turn routing into a universal TODO/TDD/Fable sequence. Missing workflow evidence should produce a reminder, not a persistent Harness lock.
+11. **Prefer Git worktree isolation for major mutation.** Read-only discovery may stay in the bound repository. Tier 3 / Fable source and artifact changes should use a verified linked worktree when practical; failure to create one is a prominent risk reminder, not a Harness-owned deadlock. See [workflow-runtime.md](docs/workflow-runtime.md).
 
 ## Verification Before You Claim Done
 

package/CHANGELOG.md

@@ -2,6 +2,14 @@
 
 All notable changes to this project are documented in this file.
 
+## [0.16.1](https://github.com/dyphn1/Harness-everything/compare/v0.16.0...v0.16.1) (2026-09-20)
+
+### Bug Fixes
+
+* **runtime:** decouple recovery learning from rule reset ([7260e03](https://github.com/dyphn1/Harness-everything/commit/7260e031873eef03b895ffef76c490c8da18201b))
+* **runtime:** fail open advisory workflow hooks ([b0f8bec](https://github.com/dyphn1/Harness-everything/commit/b0f8bec15baaf1fa64a960f2a4890fd89fb22653))
+* **runtime:** preserve rule-of-3 failure evidence ([ce9fc6c](https://github.com/dyphn1/Harness-everything/commit/ce9fc6c97a231cae4fada49645506db54a56ecc8))
+
 ## [0.16.0](https://github.com/dyphn1/Harness-everything/compare/v0.15.0...v0.16.0) (2026-09-20)
 
 ### Features

package/README.md

@@ -19,7 +19,7 @@ AI coding agents are highly capable, but they struggle with self-regulation, env
 
 Harness acts as an automated system supervisor. It remains completely silent and out of the way, intervening only when execution boundaries are violated or failures are detected.
 
-Harness deliberately follows a **minimal rails, maximum freedom** design: the runtime enforces route-before-execution, verify-before-claim, and re-plan-after repeated identical failure. When routing emits skill suggestions, it adds one conditional rail: **evaluate before skip**. The agent must read each suggested skill's `SKILL.md` entry/basic flow before omitting it, but remains free to choose, combine, reorder, or skip execution after that evaluation.
+Harness deliberately follows a **minimal rails, maximum freedom** design: the runtime establishes routing context, observes verification evidence, and emits lightweight reminders. It does not hard-stop work on iteration/revision/replan/worker counts. The one cognitive hard boundary is Rule of 3: three matching failures pause mutation for a zoom-out reflection. When routing emits skill suggestions, it adds one conditional rail: **evaluate before skip**. The agent must read each suggested skill's `SKILL.md` entry/basic flow before omitting it, but remains free to choose, combine, reorder, or skip execution after that evaluation.
 
 ### Comparison: Prompt vs. Skill vs. Harness
 
@@ -148,7 +148,7 @@ The Tier changes the **recommendations**, not the required order. Tier 2 may sug
 Harness operates through six core cognitive concepts:
 
 1. **Kernel Router (`kernel-router.js` + `tier-router.js`):** `tier-router.js` remains the classifier, dynamic-skill detector, and knowledge-guide matcher. `kernel-router.js` is the public runtime boundary: it preserves the classifier result, removes legacy fixed-pipeline instructions, injects the baseline invariants, and adds `evaluate-suggestions-before-skip` whenever domain skills are suggested. Suggestions are mandatory to evaluate by reading their `SKILL.md` entry/basic flow, but advisory to execute after evaluation. This prevents host peer-skill selection or superficial routing summaries from bypassing Harness while preserving agent autonomy. If nothing matches at all — including nothing already kept from the open skills ecosystem — `find-skills` checks `npx skills list` live and, if still nothing, searches `skills.sh`/`npx skills` with explicit approval before installation.
-2. **Guard (`rule-of-3.js`):** The fail-safe circuit breaker. Tracks failure signatures across terminal runs on integration surfaces that package the required lifecycle hooks. If a test or command fails 3 times with the same signature, it locks mutating tools and forces a `zoom-out` reflection: re-verify every assumption with read-only tools, write a fact-checked report, then resume on a fresh diagnosis. A companion `Stop` gate (`stop-gate.js`) can bounce the end of a turn once per edit batch when edits were never followed by successful verification on hosts where that hook is installed.
+2. **Guard (`rule-of-3.js`):** The fail-safe circuit breaker. Tracks failure signatures across terminal runs on integration surfaces that package the required lifecycle hooks. If a test or command fails 3 times with the same signature, it locks mutating tools and forces a `zoom-out` reflection: re-verify every assumption with read-only tools, write a fact-checked report, then resume on a fresh diagnosis. A companion `Stop` hook (`stop-gate.js`) emits a non-blocking reminder when edits were never followed by successful verification on hosts where that hook is installed.
 3. **Memory (`state-persist.js`):** Session transaction logging for stateful hook/plugin integrations. Static skills/instructions alone do not create WAL state.
 4. **Reflection (`self-evolve`):** Long-term workspace immunization. Upon task completion, the agent reflects on the root cause of resolved issues, then judges whether the lesson is a simple rule or a reusable, complex pattern: simple rules are appended to local workspace rules (`RULES.md`); genuinely reusable patterns are instead packaged as a dynamic skill (via `skill-creator`'s Dynamic Skill Generation Contract) and registered in `manifest.json` so the Router picks it up in future sessions. Either path is validated by a hermetic self-regression suite before it's persisted.
 5. **Subagent Scope Guard (`subagent-scope-guard.js`):** Diffs the whole repo's `git status` before and after every supported subagent (`Task`) burst, not just the files it was briefed to touch. Catches a subagent that was told to only read/verify but edited files anyway — where that host/integration actually invokes the guard.
@@ -160,14 +160,14 @@ Harness operates through six core cognitive concepts:
 
 The authoritative current matrix is [docs/platform-capabilities.md](docs/platform-capabilities.md). The important distinction is that **one host can have multiple Harness installation surfaces**.
 
-[`opencode-plugin/`](opencode-plugin/) (`index.mjs`) implements a verification gate and a Rule of 3 breaker against OpenCode's real, source-verified plugin API (`tool.execute.before`/`.after`, the `session.idle` event). `ci/mechanism-2n-opencode-plugin.test.js` drives the exported hooks directly against a mock context matching that API. Retained evidence supports project-scope `.js` plugin loading and edit/verification state on OpenCode 1.18.31 (macOS): [live-host evidence](benchmarks/results/live-host/opencode-2026-09-16/README.md). The final snapshot is post-reset (`hardLock: false`, `count: 1`); hard lock is only an interactive observation with no retained blocked-tool trace. Reflection was operator-seeded, then agent-rewritten, not unaided. Agent-controlled state deletion resets the breaker, so this does not prove durable hard enforcement or behavioral effectiveness. Install with a **`.js`** destination name: this host silently ignores `.mjs` (issue #127, guarded by `test:opencode:loadability`). Global scope, npm-package installation, and other host versions remain unverified.
+[`opencode-plugin/`](opencode-plugin/) (`index.mjs`) implements verification observation/reminders and a Rule of 3 breaker against OpenCode's real, source-verified plugin API (`tool.execute.before`/`.after`, the `session.idle` event). `ci/mechanism-2n-opencode-plugin.test.js` drives the exported hooks directly against a mock context matching that API. Retained evidence supports project-scope `.js` plugin loading and edit/verification state on OpenCode 1.18.31 (macOS): [live-host evidence](benchmarks/results/live-host/opencode-2026-09-16/README.md). The retained snapshot predates #190's simplification and is historical evidence only: its final snapshot was post-reset; the old hard-lock was only an interactive observation, with no retained blocked-tool trace. Current OpenCode behavior keeps the third-failure reflection boundary but no permanent post-reflection hard lock. Reflection was operator-seeded, then agent-rewritten, not unaided; no behavioral-effectiveness claim is made. Install with a **`.js`** destination name: this host silently ignores `.mjs` (issue #127, guarded by `test:opencode:loadability`). Global scope, npm-package installation, and other host versions remain unverified.
 
 | AI Agent Tool / Surface | Integration Method | Local Target Location | Enforcement claim |
 |---|---|---|---|
-| **Claude Code** | Native lifecycle hooks (`PreToolUse`, `PostToolUse`, `SessionStart`, `UserPromptSubmit`, `Stop`) | `.claude/settings.json`, `.claude/skills/`, `.claude/agents/` | **Hard** for the supported verified hook gates |
-| **OpenCode** | Native plugin module ([`opencode-plugin/index.mjs`](opencode-plugin/index.mjs), install as `harness-enforcement.js`) | `.opencode/plugins/` | **Partial live-host evidence** — project-scope `.js` loading and edit/verification state on OpenCode 1.18.31 (macOS); hard lock reported only, no retained blocked-tool trace; not durable hard enforcement |
+| **Claude Code** | Native lifecycle hooks (`PreToolUse`, `PostToolUse`, `SessionStart`, `UserPromptSubmit`, `Stop`) | `.claude/settings.json`, `.claude/skills/`, `.claude/agents/` | Workflow/productivity guidance is reminder-oriented; Rule-of-3 reflection and explicit permission boundaries may block |
+| **OpenCode** | Native plugin module ([`opencode-plugin/index.mjs`](opencode-plugin/index.mjs), install as `harness-enforcement.js`) | `.opencode/plugins/` | **Partial live-host evidence** — project-scope `.js` loading and edit/verification state on OpenCode 1.18.31 (macOS); current workflow/verification behavior is reminder-oriented, with only the third-failure reflection boundary blocking edits |
 | **Codex — general installer path** | Skills + `AGENTS.md` guidance | `AGENTS.md` + repo-scoped `.agents/skills/` | **Advisory/instruction-oriented** where the host only consumes instructions |
-| **Codex / local OpenAI plugin** | `.codex-plugin` package with session, prompt, supported-tool, subagent, and stop hooks plus 26 canonical skills | `.agents/plugins/marketplace.json` → `plugins/harness-everything/` | **Mechanism-tested local enforcement** for the packaged mappings; live host loading remains unverified |
+| **Codex / local OpenAI plugin** | `.codex-plugin` package with session, prompt, supported-tool, subagent, and stop hooks plus 26 canonical skills | `.agents/plugins/marketplace.json` → `plugins/harness-everything/` | **Mechanism-tested local guidance plus explicit permission/Rule-of-3 boundaries** for the packaged mappings; live host loading remains unverified |
 | **Public OpenAI Skills-only plugin** | Public Skills-only bundle | Generated submission ZIP from `plugins/harness-everything/skills/` | **Skill/workflow behavior only**; no local `.codex-plugin` lifecycle hooks in the public artifact |
 | **Cursor** | Native Project Rules + project skills | `.cursorrules` + `.cursor/skills/` | Advisory only |
 | **GitHub Copilot agent surfaces** | Agent Skills + repository custom instructions | `.github/copilot-instructions.md` + `.github/skills/` | Agent Skills path is documented; no live Harness session or plugin install is verified |
@@ -255,7 +255,7 @@ For a deep dive into individual modules and the underlying philosophy, explore o
 
 * [Harness Philosophy](docs/philosophy.md): The core behavior-first, intervention-only design.
 * [Harness Architecture](docs/architecture.md): Lifecycle hooks, security model, and data locality.
-* [Enforcement and Lock Diagnostic Flows](docs/enforcement-locks.md): Identify which gate blocked progress, why it fired, and how to recover.
+* [Guidance and Safety Boundary Diagnostic Flows](docs/enforcement-locks.md): Distinguish reminders from the two intentional blocking boundaries and understand recovery.
 * [Platform Capability Matrix](docs/platform-capabilities.md): Canonical current enforcement/install/evidence boundary per surface.
 * [Repository Runtime & Workflow Contract](docs/repository-contract.md): Generated Node/action/workflow/gate state used by consistency CI.
 * [OpenAI / ChatGPT Plugin Packaging](docs/openai-plugin.md): Local Codex/OpenAI plugin packaging plus public Skills-only submission boundary.

package/VERIFICATION.md

@@ -129,7 +129,7 @@ npm run test:mechanism
 
 and inspect the OpenCode-specific mechanism suites (`ci/mechanism-2n-opencode-plugin.test.js` for hook behavior, `ci/mechanism-30-opencode-plugin-loadability.test.js` for install-filename loadability).
 
-**Current evidence boundary:** deterministic mechanism coverage plus partial live-host evidence for project-scope `.js` loading and edit/verification state on OpenCode 1.18.31 (macOS). See [retained evidence](benchmarks/results/live-host/opencode-2026-09-16/README.md). The final snapshot is post-reset (`hardLock: false`, `count: 1`), not a history of the enforcement sequence. Hard lock is only an interactive observation with no retained blocked-tool trace. Reflection was operator-seeded, then agent-rewritten; follow-up delivery is reported/state-consistent, without a retained transcript. Agent-controlled state deletion resets the breaker, so neither durable hard enforcement nor behavioral effectiveness is proven. `.mjs` auto-discovery is broken on this host version (issue #127). Global scope, npm-package installation, and other host versions remain unverified.
+**Current evidence boundary:** deterministic mechanism coverage plus partial live-host evidence for project-scope `.js` loading and edit/verification state on OpenCode 1.18.31 (macOS). See [retained evidence](benchmarks/results/live-host/opencode-2026-09-16/README.md). The retained snapshot predates #190's simplification and is historical evidence, not the current state machine: its final snapshot was post-reset; the old hard-lock was only an interactive observation, with no retained blocked-tool trace. Current OpenCode keeps the third-failure reflection boundary but removes the permanent post-reflection hard lock. Reflection was operator-seeded, then agent-rewritten; no behavioral-effectiveness claim is inferred. `.mjs` auto-discovery is broken on this host version (issue #127). Global scope, npm-package installation, and other host versions remain unverified.
 
 ---
 
@@ -205,7 +205,7 @@ If the agent chooses multi-agent execution, specialist scopes and merge/verifica
 
 The current architecture follows one rule:
 
-> **Do not enforce workflow order. Enforce workflow invariants.**
+> **Do not hard-enforce workflow order or numeric budgets. Observe, remind, and preserve evidence; only Rule of 3 and explicit permission boundaries may block.**
 
 Therefore conformance testing must not require a universal chain such as `TODO → TDD → verification-loop`, nor assert that every TDD task must auto-load a fixed set of companion skills.
 
@@ -213,7 +213,7 @@ For a task run, check these instead:
 
 1. **Route before execution** — software/project work receives a reasonable scope/tier classification before mutation.
 2. **Verify before claim** — completion claims are backed by objective evidence appropriate to the change.
-3. **Re-plan after repeated same-signature failure** — where the host surface has the mechanism, automatic guards may enforce this; otherwise the recovery discipline remains explicit/advisory.
+3. **Re-plan after repeated same-signature failure** — where the host surface has the mechanism, the Rule-of-3 guard may require a zoom-out at the third matching failure; other workflow guidance remains advisory.
 4. **Skill-local workflow conformance** — when a skill is actually selected, follow that skill's documented local lifecycle (for example RED/GREEN/REFACTOR inside `tdd`).
 5. **No false mechanism parity** — do not grade an advisory surface as mechanically broken simply because it lacks a hook that was never packaged there.
 

package/ci/invariant-routing.test.js

@@ -1,160 +1,60 @@
 #!/usr/bin/env node
-const fs = require('fs');
-const path = require('path');
-const { spawnSync } = require('child_process');
-
-const ROOT = path.resolve(__dirname, '..');
-let failed = 0;
-
-function check(condition, message) {
-  if (condition) console.log(`  PASS ${message}`);
-  else { console.error(`  FAIL ${message}`); failed++; }
-}
-
-function read(rel) {
-  return fs.readFileSync(path.join(ROOT, rel), 'utf8');
+'use strict';
+const fs=require('fs'),path=require('path'),{spawnSync}=require('child_process');
+const ROOT=path.resolve(__dirname,'..');let failed=0;
+function check(c,m){if(c)console.log('  PASS '+m);else{console.error('  FAIL '+m);failed++;}}
+function read(p){return fs.readFileSync(path.join(ROOT,p),'utf8');}
+console.log('=== Guidance-First Routing Contract ===');
+const kernel=path.join(ROOT,'harness-everything/scripts/kernel-router.js');
+const tier2=spawnSync(process.execPath,[kernel,'add a login endpoint with tests and update the implementation'],{cwd:ROOT,encoding:'utf8'});
+check(tier2.status===0,'kernel router exits successfully');
+check(/RECOMMENDED TIER:\s*Tier 2/i.test(tier2.stdout),'classifier result is preserved');
+check(tier2.stdout.includes('"strategy":"iterative-single"'),'Tier 2 selects iterative-single guidance');
+check(tier2.stdout.includes('loop-awareness:'),'iterative work exposes loop-awareness instead of a hard budget');
+check(tier2.stdout.includes('SELECTED WORKFLOW IS GUIDANCE'),'suggested workflow is explicitly guidance');
+check(tier2.stdout.includes('ORCHESTRATION POLICY: Selected topology is planning guidance'),'orchestration policy is guidance-first');
+check(tier2.stdout.includes('WORKFLOW GUIDANCE (ADVISORY WHEN SELECTED)'),'kernel emits advisory workflow guidance');
+check(tier2.stdout.includes('missing isolation is a strong reminder, not a Harness lock'),'worktree guidance is non-blocking');
+check(!tier2.stdout.includes('WORKFLOW EXECUTION CONTRACT (MANDATORY'),'old mandatory execution contract is absent');
+check(!tier2.stdout.includes('unavailable isolation means BLOCKED'),'old worktree hard-block wording is absent');
+check(tier2.stdout.includes('evaluate-suggestions-before-skip'),'skill suggestions still require evaluation before omission');
+
+const tier3=spawnSync(process.execPath,[kernel,'audit the entire repository architecture and coordinate multiple modules'],{cwd:ROOT,encoding:'utf8'});
+check(tier3.status===0,'Tier 3 routing exits successfully');
+check(/RECOMMENDED TIER:\s*Tier 3/i.test(tier3.stdout),'macro task remains Tier 3');
+check(tier3.stdout.includes('using-git-worktrees'),'Tier 3 still recommends worktree guidance');
+check(tier3.stdout.includes('WORKFLOW GUIDANCE (ADVISORY WHEN SELECTED)'),'Tier 3 workflow remains advisory');
+
+const hs=read('harness-everything/SKILL.md');
+check(/workflow state and numeric limits guide; they do not hard-stop execution/i.test(hs),'Harness skill states non-blocking workflow contract');
+check(/only Rule-of-3 reflection and explicit user\/host permission boundaries may block/i.test(hs),'Harness skill names the only intentional blocking boundaries');
+check(read('plugins/harness-everything/skills/harness-everything/SKILL.md')===hs,'Harness skill mirror matches');
+
+const wt=read('using-git-worktrees/SKILL.md');
+check(/safer in a linked worktree/i.test(wt),'worktree skill strongly recommends isolation');
+check(!/Creation\/entry failure => `BLOCKED`/i.test(wt),'worktree creation failure is not a cognitive blocked state');
+check(read('plugins/harness-everything/skills/using-git-worktrees/SKILL.md')===wt,'worktree skill mirror matches');
+
+const triage=read('harness-everything/references/triage-and-tiers.md');
+check(/Guidance-first workflow/i.test(triage),'triage reference uses guidance-first policy');
+check(read('plugins/harness-everything/skills/harness-everything/references/triage-and-tiers.md')===triage,'triage mirror matches');
+
+for(const p of ['docs/routing.md','docs/architecture.md','docs/philosophy.md','docs/mechanism-first-skill-mesh.md']){
+ const t=read(p); check(/guidance/i.test(t),'current doc '+p+' describes guidance');
 }
-
-console.log('=== Mandatory Workflow Routing Contract ===');
-
-const kernel = path.join(ROOT, 'harness-everything', 'scripts', 'kernel-router.js');
-const tier2 = spawnSync(process.execPath, [kernel, 'add a login endpoint with tests and update the implementation'], {
-  cwd: ROOT,
-  encoding: 'utf8',
-});
-
-check(tier2.status === 0, 'kernel router exits successfully');
-check(/RECOMMENDED TIER:\s*Tier 2/i.test(tier2.stdout), 'classifier result is preserved');
-check(tier2.stdout.includes('"strategy":"iterative-single"'), 'Tier 2 structured plan selects iterative-single');
-check(tier2.stdout.includes('REQUIRED HARNESS INVARIANTS'), 'kernel emits mandatory invariants');
-check(tier2.stdout.includes('Route before execution'), 'route-before-execution invariant is present');
-check(tier2.stdout.includes('Verify before claim'), 'verify-before-claim invariant is present');
-check(tier2.stdout.includes('after 3 same-signature failures'), 'failure escalation invariant is present');
-check(tier2.stdout.includes('loop-budget:'), 'iterative-single loop budget invariant is present');
-check(tier2.stdout.includes('evaluate-suggestions-before-skip'), 'non-empty suggestions inject evaluate-before-skip invariant');
-check(tier2.stdout.includes('WORKFLOW SKILLS (EVALUATE APPLICABILITY'), 'domain suggestions remain applicability inputs');
-check(tier2.stdout.includes('SELECTED WORKFLOW IS MANDATORY'), 'selected workflow execution is mandatory');
-check(tier2.stdout.includes('tdd:'), 'Tier 2 can still recommend TDD');
-check(!tier2.stdout.includes('BASE EXECUTION LOOP'), 'legacy fixed base-execution-loop output is suppressed');
-check(tier2.stdout.includes('Mandatory applicable workflow'), 'orchestration policy requires selected applicable workflow');
-check(tier2.stdout.includes('model controls HOW to satisfy it'), 'reasoning/implementation freedom remains inside workflow');
-check(tier2.stdout.includes('WORKFLOW EXECUTION CONTRACT (MANDATORY WHEN SELECTED)'), 'kernel emits workflow execution contract');
-check(tier2.stdout.includes('- State: unpersisted'), 'manual route without host session does not claim persisted lifecycle');
-check(tier2.stdout.includes('Generic simple/routine/already-clear reasons cannot waive'), 'model confidence cannot bypass workflow');
-check(tier2.stdout.includes('Escape is limited to workflow-uncovered-scope or host-capability-unavailable'), 'workflow escape is exception-only');
-check(!tier2.stdout.includes('execution remains advisory after evaluation'), 'old advisory execution wording is absent');
-check(!tier2.stdout.includes('isolated-worktree-before-mutation'), 'Tier 2 does not inherit the major-workflow worktree invariant');
-
-const tier2Checkpoints = tier2.stdout.match(/HARNESS ROUTING CHECKPOINT \(REQUIRED VISIBLE STATE\)/g) || [];
-check(tier2Checkpoints.length === 1, 'Tier 2 emits exactly one routing checkpoint');
-check(tier2.stdout.includes('- Tier: Tier 2'), 'checkpoint exposes Tier 2');
-check(tier2.stdout.includes('- Strategy: iterative-single'), 'checkpoint exposes selected strategy');
-check(/- Required invariants: .*verify-before-claim/.test(tier2.stdout), 'checkpoint exposes required invariants');
-check(/- Suggested skills: .*tdd/.test(tier2.stdout), 'checkpoint exposes suggestions');
-check(tier2.stdout.includes('Suggestion evaluation: MANDATORY'), 'checkpoint requires suggestion evaluation');
-check(tier2.stdout.includes('read its complete SKILL.md entry'), 'checkpoint requires reading skill entry');
-check(tier2.stdout.includes('name, description, router summary'), 'checkpoint rejects metadata-only omission');
-check(tier2.stdout.includes('routine/common task'), 'checkpoint rejects routine-task omission shortcut');
-check(tier2.stdout.includes('selected workflow is mandatory'), 'checkpoint distinguishes skill applicability from topology obligation');
-
-const tier3 = spawnSync(process.execPath, [kernel, 'audit the entire repository architecture and coordinate multiple modules'], {
-  cwd: ROOT,
-  encoding: 'utf8',
-});
-check(tier3.status === 0, 'Tier 3 kernel routing exits successfully');
-check(/RECOMMENDED TIER:\s*Tier 3/i.test(tier3.stdout), 'macro task remains Tier 3');
-check(tier3.stdout.includes('"strategy":"fable-staged"'), 'Tier 3 task selects fable-staged');
-check(tier3.stdout.includes('fable-mode / fable-discipline'), 'Tier 3 plan exposes Fable capabilities');
-check(tier3.stdout.includes('selected Fable topology must be entered and resolved before completion'), 'selected Fable topology is mandatory');
-check(tier3.stdout.includes('WORKFLOW EXECUTION CONTRACT (MANDATORY WHEN SELECTED)'), 'Tier 3 emits execution contract');
-check(tier3.stdout.includes('isolated-worktree-before-mutation'), 'Tier 3 structured plan carries the worktree isolation invariant');
-check(tier3.stdout.includes('using-git-worktrees'), 'Tier 3 structured plan surfaces the worktree workflow skill');
-check(tier3.stdout.includes('mutations require Git worktree isolation'), 'Tier 3 execution contract requires worktree isolation before mutation');
-check(tier3.stdout.includes('unavailable isolation means BLOCKED'), 'Tier 3 worktree failure blocks instead of falling back in place');
-
-const harnessSkill = read('harness-everything/SKILL.md');
-check(/Work that names or matches another skill/i.test(harnessSkill), 'named domain skills still pass through Harness routing');
-check(/selected topology is not advisory/i.test(harnessSkill), 'skill contract makes selected topology mandatory');
-check(/"Simple", "routine".*cannot justify omission/i.test(harnessSkill), 'skill contract rejects confidence/routine omission shortcuts');
-check(/explicit escape with uncovered scope \+ evidence/i.test(harnessSkill), 'skill contract defines evidence-backed escape');
-check(/Complete only after applicable workflow obligations and objective verification resolve/i.test(harnessSkill), 'skill contract gates completion on workflow resolution');
-check(/mandatory applicable workflow; flexible reasoning\/implementation/i.test(harnessSkill), 'skill entry states core policy');
-
-const pluginHarnessSkill = read('plugins/harness-everything/skills/harness-everything/SKILL.md');
-check(pluginHarnessSkill === harnessSkill, 'canonical/plugin Harness SKILL.md copies remain identical');
-check(read('plugins/harness-everything/skills/harness-everything/scripts/kernel-router.js') === read('harness-everything/scripts/kernel-router.js'), 'canonical/plugin kernel-router copies remain identical');
-check(read('plugins/harness-everything/skills/harness-everything/scripts/kernel-router-core.js') === read('harness-everything/scripts/kernel-router-core.js'), 'canonical/plugin kernel-router core copies remain identical');
-check(read('plugins/harness-everything/skills/harness-everything/references/triage-and-tiers.md') === read('harness-everything/references/triage-and-tiers.md'), 'canonical/plugin triage references remain identical');
-
-const worktreeSkill = read('using-git-worktrees/SKILL.md');
-check(/Major workflow mode/i.test(worktreeSkill), 'worktree skill defines mandatory major-workflow mode');
-check(/never fall back to the primary working tree/i.test(worktreeSkill), 'worktree skill blocks unsafe in-place fallback for major work');
-check(/Creation\/entry failure => `BLOCKED`/i.test(worktreeSkill), 'worktree skill makes isolation failure a blocked state');
-check(read('plugins/harness-everything/skills/using-git-worktrees/SKILL.md') === worktreeSkill, 'canonical/plugin worktree skill copies remain identical');
-
-const cognitiveSkill = read('install-cognitive-os/SKILL.md');
-check(/policy, not a required peer-skill selection/i.test(cognitiveSkill), 'Cognitive OS remains reasoning policy rather than peer dependency');
-
-const hooks = JSON.parse(read('hooks/hooks.json'));
-const promptHooks = hooks.hooks && hooks.hooks.UserPromptSubmit;
-const command = promptHooks && promptHooks[0] && promptHooks[0].hooks && promptHooks[0].hooks[0] && promptHooks[0].hooks[0].command;
-check(command === 'node "${CLAUDE_PLUGIN_ROOT}/harness-everything/scripts/kernel-router.js"', 'UserPromptSubmit anchors kernel to Claude plugin root');
-const preHooks = hooks.hooks && hooks.hooks.PreToolUse || [];
-const workflowHook = preHooks.find(entry => entry.id === 'harness:pre:workflow-gate');
-check(Boolean(workflowHook), 'Claude PreToolUse includes workflow gate');
-check(workflowHook && /Bash/.test(workflowHook.matcher) && /PowerShell/.test(workflowHook.matcher) && /Edit/.test(workflowHook.matcher) && /Write/.test(workflowHook.matcher), 'Claude workflow gate covers shell and artifact mutation');
-const stopHooks = hooks.hooks && hooks.hooks.Stop || [];
-check(stopHooks.some(entry => entry.id === 'harness:stop:workflow-completion-gate'), 'Claude Stop includes Fable workflow completion gate');
-
-const openaiHooks = JSON.parse(read('plugins/harness-everything/hooks/hooks.json'));
-const openaiWorkflowHook = (openaiHooks.hooks && openaiHooks.hooks.PreToolUse || []).find(entry =>
-  (entry.hooks || []).some(hook => String(hook.command || '').includes('workflow-gate.js'))
-);
-check(openaiWorkflowHook && /Bash/.test(openaiWorkflowHook.matcher) && /apply_patch/.test(openaiWorkflowHook.matcher), 'Codex/OpenAI packaged workflow gate covers Bash and apply_patch');
-
-const triageDoc = read('harness-everything/references/triage-and-tiers.md');
-check(/Mandatory applicable workflow/i.test(triageDoc), 'triage reference documents mandatory applicable workflow');
-check(/topology becomes the run's execution contract/i.test(triageDoc), 'triage reference makes topology a contract');
-check(/workflow-uncovered-scope/i.test(triageDoc), 'triage reference documents narrow escape policy');
-check(/A tier is \*\*not\*\* a fixed TODO\/TDD\/Fable pipeline/i.test(triageDoc), 'triage reference rejects universal tier pipeline');
-check(/```mermaid/.test(triageDoc), 'triage reference retains executable flowchart documentation');
-check(/cross-host live-enforcement claim/i.test(triageDoc), 'triage reference preserves host evidence boundary');
-
-const routingDoc = read('docs/routing.md');
-check(/Mandatory applicable workflow/i.test(routingDoc), 'routing docs use mandatory workflow policy');
-check(/workflow-gate\.js/.test(routingDoc), 'routing docs describe PreToolUse workflow gate');
-check(/workflow-stop-gate\.js/.test(routingDoc), 'routing docs describe completion gate');
-check(/workflow-disposition\.js/.test(routingDoc), 'routing docs describe explicit escape mechanism');
-check(!/mandatory to evaluate and advisory to execute/i.test(routingDoc), 'routing docs remove old advisory execution contract');
-
-const architectureDoc = read('docs/architecture.md');
-check(/topology becomes a lifecycle contract/i.test(architectureDoc), 'architecture makes selected topology lifecycle contract');
-check(/workflow-gate\.js/.test(architectureDoc), 'architecture includes workflow bypass gate');
-check(!/Mandatory evaluation, advisory execution/i.test(architectureDoc), 'architecture removes old advisory execution policy');
-
-const philosophyDoc = read('docs/philosophy.md');
-check(/Constrain Lifecycle, Not Reasoning/i.test(philosophyDoc), 'philosophy separates lifecycle constraint from reasoning freedom');
-check(/Applicable workflow is mandatory/i.test(philosophyDoc), 'philosophy states applicable workflow requirement');
-check(!/Mandatory Evaluation, Advisory Execution/i.test(philosophyDoc), 'philosophy removes old advisory execution policy');
-
-const meshDoc = read('docs/mechanism-first-skill-mesh.md');
-check(/mandatory applicable workflow \+ local skill autonomy/i.test(meshDoc), 'skill mesh documents mandatory outer workflow and local skill autonomy');
-check(/selected topology is mandatory for the run/i.test(meshDoc), 'skill mesh distinguishes selected topology from skill suggestions');
-
-const capabilitiesDoc = read('docs/platform-capabilities.md');
-check(capabilitiesDoc.includes('repository/agent contract'), 'platform docs distinguish contract from host enforcement evidence');
-check(capabilitiesDoc.includes('does not upgrade `platform-compatibility.json` live-host status values'), 'routing change does not inflate compatibility status');
-
-const advisory = read('scripts/lib/advisory-text.js');
-check(/For EVERY suggested skill/i.test(advisory), 'generated advisory instructions require per-suggestion applicability evaluation');
-check(/selected workflow topology is mandatory once applicable/i.test(advisory), 'advisory surfaces carry mandatory workflow semantics');
-check(/No universal skill pipeline/i.test(advisory), 'advisory surfaces reject universal skill pipeline');
-check(/workflow genuinely cannot cover part of the task/i.test(advisory), 'advisory surfaces constrain workflow escape');
-check(read('plugins/harness-everything/scripts/lib/advisory-text.js') === advisory, 'OpenAI plugin advisory mirror matches canonical source');
-
-const agents = read('AGENTS.md');
-check(/Selected workflow is mandatory; reasoning inside it stays flexible/i.test(agents), 'repository agent contract matches mandatory workflow policy');
-check(!/Router suggestions are mandatory to evaluate, advisory to execute/i.test(agents), 'repository agent contract removes old advisory execution rule');
-
-console.log(`\n${failed === 0 ? 'PASS' : 'FAIL'}: invariant routing contract (${failed} failure${failed === 1 ? '' : 's'})`);
-process.exit(failed === 0 ? 0 : 1);
+const advisory=read('scripts/lib/advisory-text.js');
+check(/selected workflow topology.*planning guidance/i.test(advisory),'installer advisory text keeps workflow non-blocking');
+check(/Rule of 3/i.test(advisory)&&/Permission boundaries are separate/i.test(advisory),'installer text preserves Rule-of-3 and permission boundaries');
+check(read('plugins/harness-everything/scripts/lib/advisory-text.js')===advisory,'OpenAI advisory mirror matches');
+
+const agents=read('AGENTS.md');
+check(/Selected workflow is planning guidance/i.test(agents),'repository agent contract is guidance-first');
+check(/Prefer Git worktree isolation/i.test(agents),'repository worktree rule is a recommendation');
+
+const hooks=JSON.parse(read('hooks/hooks.json'));
+check((hooks.hooks.PreToolUse||[]).some(e=>e.id==='harness:pre:workflow-gate'),'Claude packages workflow reminder hook');
+check((hooks.hooks.PreToolUse||[]).some(e=>e.id==='harness:pre:rule-of-3'),'Claude preserves Rule-of-3 boundary');
+check((hooks.hooks.PreToolUse||[]).some(e=>e.id==='harness:pre:action-gate'),'Claude preserves action permission gate');
+
+console.log('\n'+(failed===0?'PASS':'FAIL')+': guidance-first routing contract ('+failed+' failures)');
+process.exit(failed===0?0:1);