harness-everything 0.30.2 → 0.30.3

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": "0.30.2",
+      "version": "0.30.3",
       "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": "0.30.2",
+  "version": "0.30.3",
   "author": {
     "name": "Miya Daniel"
   },

package/CHANGELOG.md

@@ -2,6 +2,15 @@
 
 All notable changes to this project are documented in this file.
 
+## [0.30.3](https://github.com/dyphn1/Harness-everything/compare/v0.30.2...v0.30.3) (2026-10-01)
+
+### Bug Fixes
+
+* **router:** preserve structured A/B macro routing ([7184ec5](https://github.com/dyphn1/Harness-everything/commit/7184ec5742d12bca8abc3ce938ee9b1c3720da67))
+* **router:** report actual Tier 3 trigger rationale ([d361704](https://github.com/dyphn1/Harness-everything/commit/d361704a4bfdf6c42c93c7f7a9e6c1bad2c34ff7))
+* **router:** stop treating audit verbs as macro scope ([9e79e3b](https://github.com/dyphn1/Harness-everything/commit/9e79e3be00b446dba8082d06360c3c7ea0dcf2ae))
+* **rule-of-3:** align architecture failure threshold ([bc807a2](https://github.com/dyphn1/Harness-everything/commit/bc807a21466f299147378aec7f37ea7b3c56c42b))
+
 ## [0.30.2](https://github.com/dyphn1/Harness-everything/compare/v0.30.1...v0.30.2) (2026-10-01)
 
 ### Bug Fixes

package/ci/invariant-routing.test.js

@@ -82,6 +82,11 @@ check(/Selected workflow is a semantic contract/i.test(agents),'repository agent
 check(/User-visible Harness Status is mandatory/i.test(agents)&&/### 🚦 Harness Status/i.test(agents)&&/nested evidence bullets/i.test(agents),'repository agent contract requires readable unified user-visible status');
 check(/Tier-3\/Fable isolation disposition is mandatory/i.test(agents)&&/degraded fallback/i.test(agents),'repository worktree rule requires disposition without hard lock');
 
+const architectureSkill=read('improve-codebase-architecture/SKILL.md');
+check(/3 same-signature failures.*zoom-out/i.test(architectureSkill),'architecture skill aligns rollback with the third same-signature failure');
+check(!/>3 cascading errors/i.test(architectureSkill),'architecture skill no longer waits beyond the Rule-of-3 threshold');
+check(read('plugins/harness-everything/skills/improve-codebase-architecture/SKILL.md')===architectureSkill,'architecture skill mirror matches');
+
 const envSkill=read('environment-detection/SKILL.md');
 check(/semantic \*\*MUST\*\*/i.test(envSkill)&&/environment-sensitive/i.test(envSkill),'environment discovery is a conditional semantic MUST');
 check(read('plugins/harness-everything/skills/environment-detection/SKILL.md')===envSkill,'environment skill mirror matches');

package/ci/router-workflow-plan.test.js

@@ -104,6 +104,35 @@ if (validContract(memoryProhibited, 'memory prohibition')) {
   check(memoryProhibited.contract.workflowPlan.reasonCodes.includes('memory-persistence-prohibited'), 'memory prohibition conflict is auditable');
 }
 
+const boundedOperationPrompts = [
+  'Audit this SKILL.md only.',
+  'Compare these two functions.',
+  'Benchmark this parser function.',
+];
+for (const prompt of boundedOperationPrompts) {
+  const boundedOperation = runTier(prompt);
+  if (validContract(boundedOperation, `bounded operation: ${prompt}`)) {
+    check(boundedOperation.contract.classification.tier !== 'tier3', `bounded operation verb does not force Tier 3: ${prompt}`);
+    check(!boundedOperation.contract.workflowPlan.reasonCodes.includes('macro-scope-signal'), `bounded operation verb does not emit macro-scope-signal: ${prompt}`);
+    check(boundedOperation.contract.taskShape.observedSignals.macroScope === false, `bounded operation records macroScope=false: ${prompt}`);
+  }
+}
+
+const controlledAb = runTier('Run a controlled A/B benchmark of the agent with and without the Harness skills and report confidence intervals');
+if (validContract(controlledAb, 'controlled A/B benchmark')) {
+  check(controlledAb.contract.classification.tier === 'tier3', 'structured A/B benchmark remains Tier 3');
+  check(controlledAb.contract.taskShape.observedSignals.macroScope === true, 'structured A/B benchmark records macroScope=true');
+  check(controlledAb.contract.workflowPlan.reasonCodes.includes('macro-scope-signal'), 'structured A/B benchmark keeps macro-scope-signal');
+}
+
+const tier3Keyword = runTier('Create a new feature');
+if (validContract(tier3Keyword, 'Tier 3 keyword rationale')) {
+  check(tier3Keyword.contract.classification.tier === 'tier3', 'new feature remains Tier 3');
+  check(tier3Keyword.contract.workflowPlan.reasonCodes.includes('tier3-keyword'), 'new feature records tier3-keyword');
+  check(/Tier 3 keyword/i.test(tier3Keyword.contract.classification.rationale), 'Tier 3 keyword rationale names the actual trigger class');
+  check(!/repository-wide scope|structured comparative experiment/i.test(tier3Keyword.contract.classification.rationale), 'Tier 3 keyword rationale does not claim unrelated macro signals');
+}
+
 const staged = runTier('Refactor the entire authentication architecture in dependent stages.');
 if (validContract(staged, 'fable-staged')) {
   const plan = staged.contract.workflowPlan;

package/docs/routing.md

@@ -137,6 +137,8 @@ Typical triggers: typo/docs correction, narrow local edit, bounded explanation,
 
 Typical triggers: normal feature work, bug fixes, multi-file changes, focused benchmark/review. Usually selects `iterative-single`: bounded reason/act work plus objective verification. Focused skills such as `tdd`, `verification-loop`, `security-review`, `using-git-worktrees`, and `eval-harness` may be surfaced and must be resolved for applicability.
 
+Operation labels such as `audit`, `evaluate`, `benchmark`, or `compare` describe **what** work is being done; they do not by themselves establish macro scope. A focused audit/review remains bounded unless an independent scope/structure signal (for example repository-wide, all files/modules, or multi-workstream structure) elevates it. A structured A/B experiment is different: its explicit control/treatment comparison is itself a multi-lane execution structure, so `A/B test` / `A/B benchmark` remains a macro signal.
+
 No universal `TODO → TDD → verification-loop` order is implied. But when a skill is applicable, reading it does not grant permission to ignore its flow.
 
 ### Tier 3 — Macro

package/docs/workflows/improve-codebase-architecture.md

@@ -17,7 +17,7 @@ graph TD
   SafetyNet -->|No| CharTests["Write Characterization Tests first via tdd"]
   SafetyNet -->|Yes| Extract["Extract incrementally via tdd; verify tests after each change"]
   CharTests --> Extract
-  Extract --> ErrorCheck{"More than 3 cascading errors?"}
+  Extract --> ErrorCheck{"Third same-signature failure?"}
   ErrorCheck -->|Yes| Rollback["Rollback plus zoom-out; record traps in self-evolve"]
   ErrorCheck -->|No| DoneState["Refactoring complete"]
 ```
@@ -28,7 +28,7 @@ graph TD
 graph LR
   TechDebt["Trigger: refactor architecture or split object or apply SRP or tech debt"] --> ICA["improve-codebase-architecture / SKILL.md"]
   ICA --> TDD["tdd: Characterization Tests first, then incremental extraction"]
-  ICA --> ZoomOut["zoom-out: invoked with rollback after more than 3 cascading errors"]
+  ICA --> ZoomOut["zoom-out: invoked with rollback on the third same-signature failure"]
   ICA --> SelfEvolve["self-evolve: record traps"]
 ```
 
@@ -40,7 +40,7 @@ graph TD
   ScanInterfaces --> SRPProposal["Propose split into focused units plus seam abstractions"]
   SRPProposal --> CharNet["Add Characterization Tests for untested legacy paths"]
   CharNet --> Incremental["Incremental extraction with test check after each step"]
-  Incremental --> RollbackGate{"More than 3 cascading errors?"}
+  Incremental --> RollbackGate{"Third same-signature failure?"}
   RollbackGate -->|Yes| RollbackZoom["Rollback and zoom-out"]
   RollbackGate -->|No| ModularDone["SRP-compliant modules with safety net"]
 ```
@@ -56,5 +56,5 @@ Deep detail: `improve-codebase-architecture/references/README.md`.
 - [ ] Deepening and SRP proposal with object splitting and seam abstraction presented and approved before code changes
 - [ ] `tdd` launched; Characterization Tests added first when legacy code lacks tests
 - [ ] Extraction done incrementally with tests verified after each change
-- [ ] On more than 3 cascading errors, changes rolled back with `zoom-out` and traps recorded in `self-evolve`
+- [ ] On the third same-signature failure, changes rolled back with `zoom-out` and traps recorded in `self-evolve`
 - [ ] Not used for features, bugfixes, or style-only cleanups with no structure change

package/harness-everything/SKILL.md

@@ -4,7 +4,7 @@ description: "Route software/project work through Harness: classify tier/topolog
 license: Apache-2.0
 metadata:
   author: Miya Daniel
-  version: 0.30.2
+  version: 0.30.3
 ---
 
 # Harness Everything

package/harness-everything/scripts/tier-router.js

@@ -243,7 +243,7 @@ function run(userPrompt, context, options = {}) {
 
   const macroSignals = [
     /\b(?:every|each|all|entire|whole|full|complete)\s+(?:skill|skills|repo|repository|codebase|project|file|files|module|modules)/i,
-    /\b(?:evaluate|audit|benchmark|stress[- ]test|ab test|a\/b test|compare)\b/i,
+    /\b(?:controlled\s+)?a(?:\/|[- ]?)b\s+(?:test|benchmark)\b/i,
     /\b(?:repository[- ]wide|codebase[- ]wide|end[- ]to[- ]end)\b/i,
     /\b(?:multiple|several|four|fourteen|dozens)\s+(?:issues|skills|files|modules)/i,
     /(?:每個|每一個|所有|全部|整個|全套|逐一|多個|四個).*(?:skill|技能|檔案|問題|版本|基準|測試|評估|稽核|比較|壓力)/i,
@@ -254,7 +254,8 @@ function run(userPrompt, context, options = {}) {
   const hasDocsTarget = /\b(?:readme|documentation|docs?)\b/i.test(userPrompt);
   const hasTinyEditSignal = /\b(?:typo|spelling|wording|one line|single line)\b/i.test(userPrompt);
   const isTrivialDocsEdit = !hasMacroSignal && hasTrivialEditVerb && hasDocsTarget && hasTinyEditSignal;
-  const hasTier3Keyword = TIER3_KEYWORDS.some(keyword => matchKeyword(promptLower, keyword));
+  const matchedTier3Keyword = TIER3_KEYWORDS.find(keyword => matchKeyword(promptLower, keyword)) || null;
+  const hasTier3Keyword = matchedTier3Keyword !== null;
   const hasTier2Keyword = TIER2_KEYWORDS.some(keyword => matchKeyword(promptLower, keyword));
 
   let recommendedTier = 'Unclassified';
@@ -273,7 +274,9 @@ function run(userPrompt, context, options = {}) {
     addReason(reasonCodes, 'trivial-docs-edit');
   } else if (hasMacroSignal || hasTier3Keyword) {
     recommendedTier = 'Tier 3 (Macro Task)';
-    rationale = 'Prompt implies repository-wide scope, audit/benchmark work, architectural refactoring, or multi-agent collaboration.';
+    rationale = hasMacroSignal
+      ? 'Prompt implies repository-wide scope, a structured comparative experiment, architectural refactoring, or multi-agent collaboration.'
+      : `Prompt matched configured Tier 3 keyword: "${matchedTier3Keyword}".`;
     reasonCodes.splice(loadedConfig.reasonCodes.length);
     addReason(reasonCodes, hasMacroSignal ? 'macro-scope-signal' : 'tier3-keyword');
   } else if (hasTier2Keyword) {

package/improve-codebase-architecture/SKILL.md

@@ -4,7 +4,7 @@ description: Discovers and transforms shallow or bloated modules into deep, SRP-
 license: Apache-2.0
 metadata:
   author: Miya Daniel
-  version: 0.4.0
+  version: 0.30.3
 ---
 
 # Improve Codebase Architecture (Deep & SRP Refactoring)
@@ -16,14 +16,14 @@ metadata:
 | **Trigger / Input** | "refactor architecture", "split object/class", "apply SRP", tech debt |
 | **Expected Output** | SRP proposal, Characterization Test safety net, TDD-guided extraction. |
 | **State Mutations** | Extracts classes/functions/objects; adds characterization tests. |
-| **Enforcement Gate** | Scan docs first; Characterization Tests before refactoring untested code; >3 cascading errors → rollback + `zoom-out`. |
+| **Enforcement Gate** | Scan docs first; Characterization Tests before refactoring untested code; 3 same-signature failures → rollback + `zoom-out`. |
 
 ## Workflow
 
 1. `[Discover]`: no blind refactoring — scan `CONTEXT.md`, `docs/adr/`, core interfaces first. Targets: SRP violations (>300 lines / >10 complexity), shallow modules, coupled seams.
 2. `[Think]`: present the Deepening & SRP proposal (object splitting + seam abstraction) until approved.
 3. `[Try]`: launch `tdd`; Characterization Tests first if legacy code lacks tests; extract incrementally, verifying tests after each change.
-4. `[Summarize]`/`[Self-Evolve]`: >3 cascading errors → rollback + `zoom-out`; record traps in `self-evolve`.
+4. `[Summarize]`/`[Self-Evolve]`: 3 same-signature failures → rollback + `zoom-out`; record traps in `self-evolve`.
 
 Deep dive: <this-skill-dir>/references/README.md
 

package/opencode-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "harness-enforcement",
   "description": "Repository inventory for the opencode enforcement plugin and its standalone helper",
-  "version": "0.30.2",
+  "version": "0.30.3",
   "runtime": "index.mjs",
   "hooks": {
     "verify": "hooks/verify.js"

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "harness-everything",
-  "version": "0.30.2",
+  "version": "0.30.3",
   "description": "Harness OS: An Orchestrated Agent Operating System for AI-driven Development",
   "main": "harness-everything/scripts/bootstrap.js",
   "bin": {

package/plugins/harness-everything/.codex-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "harness-everything",
-  "version": "0.30.2",
+  "version": "0.30.3",
   "description": "Invariant-first engineering harness for routing, verification, and failure recovery while preserving agent autonomy.",
   "author": {
     "name": "Miya Daniel",

package/plugins/harness-everything/plugin.json

@@ -1,7 +1,7 @@
 {
   "$schema": "https://agent-plugins.org/schemas/1.0.0/plugin.schema.json",
   "name": "harness-everything",
-  "version": "0.30.2",
+  "version": "0.30.3",
   "description": "Invariant-first engineering harness for routing, verification, and failure recovery while preserving agent autonomy.",
   "author": {
     "name": "Miya Daniel",

package/plugins/harness-everything/skills/harness-everything/SKILL.md

@@ -4,7 +4,7 @@ description: "Route software/project work through Harness: classify tier/topolog
 license: Apache-2.0
 metadata:
   author: Miya Daniel
-  version: 0.30.2
+  version: 0.30.3
 ---
 
 # Harness Everything

package/plugins/harness-everything/skills/harness-everything/scripts/tier-router.js

@@ -243,7 +243,7 @@ function run(userPrompt, context, options = {}) {
 
   const macroSignals = [
     /\b(?:every|each|all|entire|whole|full|complete)\s+(?:skill|skills|repo|repository|codebase|project|file|files|module|modules)/i,
-    /\b(?:evaluate|audit|benchmark|stress[- ]test|ab test|a\/b test|compare)\b/i,
+    /\b(?:controlled\s+)?a(?:\/|[- ]?)b\s+(?:test|benchmark)\b/i,
     /\b(?:repository[- ]wide|codebase[- ]wide|end[- ]to[- ]end)\b/i,
     /\b(?:multiple|several|four|fourteen|dozens)\s+(?:issues|skills|files|modules)/i,
     /(?:每個|每一個|所有|全部|整個|全套|逐一|多個|四個).*(?:skill|技能|檔案|問題|版本|基準|測試|評估|稽核|比較|壓力)/i,
@@ -254,7 +254,8 @@ function run(userPrompt, context, options = {}) {
   const hasDocsTarget = /\b(?:readme|documentation|docs?)\b/i.test(userPrompt);
   const hasTinyEditSignal = /\b(?:typo|spelling|wording|one line|single line)\b/i.test(userPrompt);
   const isTrivialDocsEdit = !hasMacroSignal && hasTrivialEditVerb && hasDocsTarget && hasTinyEditSignal;
-  const hasTier3Keyword = TIER3_KEYWORDS.some(keyword => matchKeyword(promptLower, keyword));
+  const matchedTier3Keyword = TIER3_KEYWORDS.find(keyword => matchKeyword(promptLower, keyword)) || null;
+  const hasTier3Keyword = matchedTier3Keyword !== null;
   const hasTier2Keyword = TIER2_KEYWORDS.some(keyword => matchKeyword(promptLower, keyword));
 
   let recommendedTier = 'Unclassified';
@@ -273,7 +274,9 @@ function run(userPrompt, context, options = {}) {
     addReason(reasonCodes, 'trivial-docs-edit');
   } else if (hasMacroSignal || hasTier3Keyword) {
     recommendedTier = 'Tier 3 (Macro Task)';
-    rationale = 'Prompt implies repository-wide scope, audit/benchmark work, architectural refactoring, or multi-agent collaboration.';
+    rationale = hasMacroSignal
+      ? 'Prompt implies repository-wide scope, a structured comparative experiment, architectural refactoring, or multi-agent collaboration.'
+      : `Prompt matched configured Tier 3 keyword: "${matchedTier3Keyword}".`;
     reasonCodes.splice(loadedConfig.reasonCodes.length);
     addReason(reasonCodes, hasMacroSignal ? 'macro-scope-signal' : 'tier3-keyword');
   } else if (hasTier2Keyword) {

package/plugins/harness-everything/skills/improve-codebase-architecture/SKILL.md

@@ -4,7 +4,7 @@ description: Discovers and transforms shallow or bloated modules into deep, SRP-
 license: Apache-2.0
 metadata:
   author: Miya Daniel
-  version: 0.4.0
+  version: 0.30.3
 ---
 
 # Improve Codebase Architecture (Deep & SRP Refactoring)
@@ -16,14 +16,14 @@ metadata:
 | **Trigger / Input** | "refactor architecture", "split object/class", "apply SRP", tech debt |
 | **Expected Output** | SRP proposal, Characterization Test safety net, TDD-guided extraction. |
 | **State Mutations** | Extracts classes/functions/objects; adds characterization tests. |
-| **Enforcement Gate** | Scan docs first; Characterization Tests before refactoring untested code; >3 cascading errors → rollback + `zoom-out`. |
+| **Enforcement Gate** | Scan docs first; Characterization Tests before refactoring untested code; 3 same-signature failures → rollback + `zoom-out`. |
 
 ## Workflow
 
 1. `[Discover]`: no blind refactoring — scan `CONTEXT.md`, `docs/adr/`, core interfaces first. Targets: SRP violations (>300 lines / >10 complexity), shallow modules, coupled seams.
 2. `[Think]`: present the Deepening & SRP proposal (object splitting + seam abstraction) until approved.
 3. `[Try]`: launch `tdd`; Characterization Tests first if legacy code lacks tests; extract incrementally, verifying tests after each change.
-4. `[Summarize]`/`[Self-Evolve]`: >3 cascading errors → rollback + `zoom-out`; record traps in `self-evolve`.
+4. `[Summarize]`/`[Self-Evolve]`: 3 same-signature failures → rollback + `zoom-out`; record traps in `self-evolve`.
 
 Deep dive: <this-skill-dir>/references/README.md
 

package/sbom.cdx.json

@@ -2,23 +2,23 @@
   "$schema": "https://cyclonedx.org/schema/bom-1.7.schema.json",
   "bomFormat": "CycloneDX",
   "specVersion": "1.7",
-  "serialNumber": "urn:uuid:609a39f1-97ad-59d5-a8ef-97f1b6da412b",
+  "serialNumber": "urn:uuid:557653e9-e704-5fd3-b675-167e0cadb8c9",
   "version": 1,
   "metadata": {
-    "timestamp": "2026-10-01T02:54:31.907Z",
+    "timestamp": "2026-10-01T06:19:24.870Z",
     "tools": [
       {
         "vendor": "Harness Everything",
         "name": "generate-sbom.js",
-        "version": "0.30.2"
+        "version": "0.30.3"
       }
     ],
     "component": {
       "type": "application",
-      "bom-ref": "pkg:npm/harness-everything@0.30.2",
+      "bom-ref": "pkg:npm/harness-everything@0.30.3",
       "name": "harness-everything",
-      "version": "0.30.2",
-      "purl": "pkg:npm/harness-everything@0.30.2"
+      "version": "0.30.3",
+      "purl": "pkg:npm/harness-everything@0.30.3"
     }
   },
   "components": [
@@ -1999,7 +1999,7 @@
       ]
     },
     {
-      "ref": "pkg:npm/harness-everything@0.30.2",
+      "ref": "pkg:npm/harness-everything@0.30.3",
       "dependsOn": [
         "pkg:npm/%40commitlint/cli@19.8.1",
         "pkg:npm/%40commitlint/config-conventional@19.8.1",