harness-everything 0.30.0 → 0.30.2

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": "0.30.0",
+      "version": "0.30.2",
       "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": "0.30.0",
+  "version": "0.30.2",
   "author": {
     "name": "Miya Daniel"
   },

package/CHANGELOG.md

@@ -2,6 +2,19 @@
 
 All notable changes to this project are documented in this file.
 
+## [0.30.2](https://github.com/dyphn1/Harness-everything/compare/v0.30.1...v0.30.2) (2026-10-01)
+
+### Bug Fixes
+
+* **prompts:** remove stale and duplicate guidance ([e8c326b](https://github.com/dyphn1/Harness-everything/commit/e8c326b687e6bac3e8fa3531376ea66371445406))
+
+## [0.30.1](https://github.com/dyphn1/Harness-everything/compare/v0.30.0...v0.30.1) (2026-10-01)
+
+### Bug Fixes
+
+* **fable:** keep minor warnings reporting-only ([28d01e6](https://github.com/dyphn1/Harness-everything/commit/28d01e62acd223ca7506fe721204f29dc94518b8))
+* **fable:** restore guardrail markdown spacing ([7daff05](https://github.com/dyphn1/Harness-everything/commit/7daff054ba39b9e28ddcc4a3a2441b0f6f448d22))
+
 ## [0.30.0](https://github.com/dyphn1/Harness-everything/compare/v0.29.0...v0.30.0) (2026-09-28)
 
 ### Features

package/ci/fable-mode-test.js

@@ -107,6 +107,22 @@ assert.match(ordinaryTier2.stdout, /RECOMMENDED TIER: Tier 2/);
 assert.doesNotMatch(ordinaryTier2.stdout, /REQUESTED FABLE MODEL MODE/);
 assert.doesNotMatch(ordinaryTier2.stdout, /fable-opus\/SKILL\.md/);
 
+const warningBatchContract = '**Warning batching.** Collect minor concerns and list them together in the next natural report or handoff; their count alone MUST NOT stop, pause, or return the worker/stage. An independently material, confirmed concern may stop the current stage and be surfaced immediately.';
+for (const rel of [
+  'fable-mode/agents/fable-worker-haiku.md',
+  'fable-mode/agents/fable-worker-sonnet.md',
+  'fable-mode/agents/fable-orchestrator.md',
+  'fable-mode/execution-guardrails/SKILL.md',
+]) {
+  const prompt = fs.readFileSync(path.join(root, rel), 'utf8').replace(/\s+/g, ' ');
+  assert.ok(prompt.includes(warningBatchContract), `${rel} must keep minor-concern batching reporting-only`);
+  assert.doesNotMatch(
+    prompt,
+    /minor concerns.{0,200}stop and surface all at once before continuing/i,
+    `${rel} must not introduce a warning-count stop condition`
+  );
+}
+
 const auditLines = fs.readFileSync(auditFile, 'utf8').trim().split(/\r?\n/).filter(Boolean);
 assert.strictEqual(auditLines.length, 5);
 for (const line of auditLines) {

package/ci/prompt-contract-regressions.test.js

@@ -0,0 +1,60 @@
+'use strict';
+
+const assert = require('assert');
+const fs = require('fs');
+const path = require('path');
+const { spawnSync } = require('child_process');
+
+const ROOT = path.resolve(__dirname, '..');
+function read(rel) {
+  return fs.readFileSync(path.join(ROOT, rel), 'utf8');
+}
+
+// #268: model aliases evolve, so worker prompts must encode behavior rather
+// than generation-specific personality/failure claims.
+const workerPairs = [
+  ['fable-mode/agents/fable-worker-haiku.md', 'plugins/harness-everything/skills/fable-mode/agents/fable-worker-haiku.md'],
+  ['fable-mode/agents/fable-worker-sonnet.md', 'plugins/harness-everything/skills/fable-mode/agents/fable-worker-sonnet.md'],
+];
+for (const [canonical, packaged] of workerPairs) {
+  const body = read(canonical);
+  assert.ok(!/\b(?:Haiku|Sonnet)'s known failure\b/i.test(body), canonical + ' must not carry generation-specific failure traits');
+  assert.strictEqual(read(packaged), body, canonical + ' packaged mirror must match');
+}
+assert.ok(/named check is not optional/i.test(read(workerPairs[0][0])), 'Haiku worker keeps the verification behavior');
+assert.ok(/A check\s+you did not run did not pass/i.test(read(workerPairs[1][0])), 'Sonnet worker keeps the verification behavior');
+
+// #270: skill-style requires the elements, not one global physical order.
+const skillStyle = read('skill-style/SKILL.md');
+for (const marker of ['# Skill Style', '## Skill Contract', '## USE FOR:', '## DO NOT USE FOR:', '## Core Rules']) {
+  assert.ok(skillStyle.includes(marker), 'skill-style keeps required element: ' + marker);
+}
+for (const rel of [
+  'skill-style/SKILL.md',
+  'plugins/harness-everything/skills/skill-style/SKILL.md',
+  'docs/workflows/skill-style.md',
+  'skill-style/references/style-guide.md',
+  'plugins/harness-everything/skills/skill-style/references/style-guide.md',
+]) {
+  const body = read(rel);
+  assert.ok(!/MUST include, in order:/i.test(body), rel + ' must not require the retired global section order');
+  assert.ok(!/Include in order:/i.test(body), rel + ' must not describe the retired global section order');
+  assert.ok(!/includes in order:/i.test(body), rel + ' must not checklist the retired global section order');
+  assert.ok(!/reorder the file to title, introduction, Skill Contract, usage, and actionable rules/i.test(body), rel + ' must not prescribe the retired global section order');
+}
+assert.ok(/section order MAY vary/i.test(skillStyle), 'skill-style explicitly permits readability-driven section ordering');
+
+// #272: preserve one detailed checkpoint plus the invariant; remove duplicate
+// restatements from later sections of the same router injection.
+const kernel = path.join(ROOT, 'harness-everything/scripts/kernel-router.js');
+const routed = spawnSync(process.execPath, [kernel, 'add a login endpoint with tests and update the implementation'], {
+  cwd: ROOT,
+  encoding: 'utf8',
+});
+assert.strictEqual(routed.status, 0, routed.stderr || 'kernel router must exit successfully');
+assert.ok(routed.stdout.includes('Suggestion evaluation: MANDATORY.'), 'checkpoint keeps the detailed suggestion-resolution rule');
+assert.ok(routed.stdout.includes('evaluate-suggestions-before-skip:'), 'semantic invariant remains emitted');
+assert.ok(!routed.stdout.includes('Read-before-skip:'), 'workflow-skill footer must not duplicate suggestion resolution');
+assert.ok(!routed.stdout.includes('Every suggested skill MUST resolve applicability.'), 'semantic-contract footer must not duplicate suggestion resolution');
+
+console.log('PASS: prompt contract regressions');

package/docs/workflows/fable-mode.md

@@ -76,6 +76,13 @@ flowchart TD
   Check -->|Pass| Handoff[Compact evidence + handoff]
 ```
 
+Minor-concern batching is **not** a stage transition. Workers keep producing and
+verifying the assigned artifact and include accumulated minor concerns in the next
+natural report/handoff; the number of minor concerns alone never stops or returns a
+worker. A material confirmed blocker may stop the current stage immediately. Repeated
+matching execution failures use the separate Rule-of-3 path: zoom out, reflect, then
+`RESUME` on a new approach or `ESCALATE` when a real decision is required.
+
 At most two full replans are allowed before unresolved blockers are escalated rather than hidden behind endless restructuring.
 
 ## 5. Completion Boundary

package/docs/workflows/skill-style.md

@@ -11,8 +11,8 @@ Source of truth: `skill-style/SKILL.md`.
 ```mermaid
 graph TD
   TriggerEdit["Trigger: creating, reviewing, or refactoring a Harness SKILL.md"] --> FrontAccurate["Keep frontmatter accurate and description routeable"]
-  FrontAccurate --> OrderCheck["Include in order: title, introduction, Skill Contract, usage, actionable rules"]
-  OrderCheck --> ImperativeGate["Use imperative language and name the enforcing command or gate"]
+  FrontAccurate --> SectionCheck["Cover purpose, Skill Contract, usage/applicability, and actionable rules; order may vary"]
+  SectionCheck --> ImperativeGate["Use imperative language and name the enforcing command or gate"]
   ImperativeGate --> OverlapCheck["Avoid overlap with OS-layer routing or domain expertise"]
   OverlapCheck --> ConsistencyGate["Gate: npm run test:consistency plus style-guide review"]
   ConsistencyGate --> ConciseOut["Output: concise, complete, non-overlapping SKILL.md"]
@@ -44,12 +44,12 @@ graph LR
 
 ## 3. Real-World Use Case
 
-An author drafts a new `backup-restore` SKILL.md and runs a style pass. They tighten the frontmatter description for routing, reorder the file to title, introduction, Skill Contract, usage, and actionable rules, rewrite vague advice in imperative language naming `npm run test:consistency` as the gate, remove duplicated routing already owned elsewhere, and check `skill-style/references/style-guide.md`. Intent interviewing and prompt testing are handed to `skill-creator/SKILL.md` per the Core Rules.
+An author drafts a new `backup-restore` SKILL.md and runs a style pass. They tighten the frontmatter description for routing, check that the skill purpose, Skill Contract, usage/applicability, and actionable rules are all present without forcing a global section order, rewrite vague advice in imperative language naming `npm run test:consistency` as the gate, remove duplicated routing already owned elsewhere, and check `skill-style/references/style-guide.md`. Intent interviewing and prompt testing are handed to `skill-creator/SKILL.md` per the Core Rules.
 
 ## 4. Verification Check
 
 - [ ] Frontmatter accurate and description routeable
-- [ ] File includes in order: title, introduction, Skill Contract, usage, and actionable rules
+- [ ] File covers the skill purpose, Skill Contract, usage/applicability, and actionable rules; section order may vary
 - [ ] Imperative language used with the enforcing command or gate named (`npm run test:consistency` plus style-guide review)
 - [ ] No overlap with OS-layer routing or domain expertise; catalog overlap checked
 - [ ] Tone, formatting, and progressive disclosure standardized per `skill-style/references/style-guide.md`

package/fable-mode/SKILL.md

@@ -4,7 +4,7 @@ description: "Stage large, multi-source or multi-session tasks through a written
 license: Apache-2.0
 metadata:
   author: Miya Daniel
-  version: 0.16.3
+  version: 0.30.2
 ---
 
 # Fable Mode (v3)

package/fable-mode/agents/fable-orchestrator.md

@@ -152,10 +152,10 @@ hasn't been confirmed present. Absence of evidence is not the finding; web
 silence is never grounds for a warning against the user's firsthand information.
 Confirm, then flag.
 
-**Warning threshold.** Keep a running count of minor concerns. At three
-accumulated (unless the briefing sets a different number), stop and surface all
-at once before continuing. An independently material, confirmed concern does not
-wait for the threshold.
+**Warning batching.** Collect minor concerns and list them together in the next
+natural report or handoff; their count alone MUST NOT stop, pause, or return the
+worker/stage. An independently material, confirmed concern may stop the current
+stage and be surfaced immediately.
 
 **Find-and-replace safety.** Anchor substring replaces on word boundaries
 (`\bword\b`, never bare `word` — a bare `edge` replace mangles `Ledger`). Prefer

package/fable-mode/agents/fable-worker-haiku.md

@@ -19,8 +19,7 @@ Rules, in order:
 3. **Verify — tightened for this tier.** Run the named check from your briefing
    and include its output. NO artifact may be reported unverified without naming
    what check was impossible and why — a bare "unverified" is itself a failure.
-   Haiku's known failure is skipping verification under time pressure; the check
-   is not optional.
+   The named check is not optional.
 4. **Escalate instead of improvising.** If the assignment turns out to need
    judgment or synthesis (conflicting sources, ambiguous spec, design choices),
    stop and return the specific blocker — recommend fable-worker-sonnet. Do not
@@ -41,10 +40,10 @@ Grep, diff, run it, or check the source directly. Never report a problem that
 hasn't been confirmed present. Absence of evidence is not the finding. Confirm,
 then flag.
 
-**Warning threshold.** Keep a running count of minor concerns. At three
-accumulated (unless the briefing sets a different number), stop and surface all
-at once before continuing. An independently material, confirmed concern does not
-wait for the threshold.
+**Warning batching.** Collect minor concerns and list them together in the next
+natural report or handoff; their count alone MUST NOT stop, pause, or return the
+worker/stage. An independently material, confirmed concern may stop the current
+stage and be surfaced immediately.
 
 **Find-and-replace safety.** Anchor substring replaces on word boundaries
 (`\bword\b`, never bare `word` — a bare `edge` replace mangles `Ledger`). Prefer

package/fable-mode/agents/fable-worker-sonnet.md

@@ -19,8 +19,8 @@ Rules of the loop, in order:
    do not build it.
 3. **Verify with the named check.** Your briefing states the pass condition. Run
    it — the actual command, diff, or read-back — and include the output in your
-   report. Sonnet's known failure is substituting "looks right" for the check
-   that can fail; do not do that. A check you did not run did not pass. If the
+   report. Do not substitute "looks right" for a check that can fail. A check
+   you did not run did not pass. If the
    check is impossible, say exactly what was impossible and why, and mark the
    artifact unverified.
 4. **Report format:** artifact path, check command, check output, confirmed
@@ -42,10 +42,10 @@ hasn't been confirmed present. Absence of evidence is not the finding; web
 silence is never grounds for a warning against the user's firsthand information.
 Confirm, then flag.
 
-**Warning threshold.** Keep a running count of minor concerns. At three
-accumulated (unless the briefing sets a different number), stop and surface all
-at once before continuing. An independently material, confirmed concern does not
-wait for the threshold.
+**Warning batching.** Collect minor concerns and list them together in the next
+natural report or handoff; their count alone MUST NOT stop, pause, or return the
+worker/stage. An independently material, confirmed concern may stop the current
+stage and be surfaced immediately.
 
 **Find-and-replace safety.** Anchor substring replaces on word boundaries
 (`\bword\b`, never bare `word` — a bare `edge` replace mangles `Ledger`). Prefer

package/fable-mode/execution-guardrails/SKILL.md

@@ -7,7 +7,7 @@ description: >-
 license: Apache-2.0
 metadata:
   author: Miya Daniel
-  version: 0.16.3
+  version: 0.30.2
 ---
 
 # Execution Guardrails
@@ -17,7 +17,7 @@ metadata:
 | Component | Spec |
 | :--- | :--- |
 | **Trigger / Input** | Turn raising a warning or performing search-and-replace edits. |
-| **Expected Output** | Verified warnings; batched caveats (3-item threshold); corruption-checked edits. |
+| **Expected Output** | Verified warnings; batched caveats without count-based stops; corruption-checked edits. |
 | **State Mutations** | None — governs execution quality for file-editing turns. |
 | **Enforcement Gate** | Verify before flagging; validate edits post-write. |
 
@@ -35,9 +35,11 @@ metadata:
 ## Core Rules
 
 1. **Verify before flag** — Confirm a problem exists before reporting it. Never convert absence of evidence into a warning.
-2. **Warning threshold** — Batch minor concerns; surface them together at three (default). Material concerns do not wait.
+2. **Warning batching.** Collect minor concerns and list them together in the next natural report or handoff; their count alone MUST NOT stop, pause, or return the worker/stage. An independently material, confirmed concern may stop the current stage and be surfaced immediately.
 3. **Find-and-replace safety** — Prefer structured edit tools over shell `sed`; anchor with unique context or `\bword\b` boundaries; verify file integrity post-edit. Never replace-all blindly.
 
+Repeated matching execution failures remain governed by Rule-of-3 / `zoom-out`; warning batching never substitutes for that recovery path.
+
 These rules are always-on, even when `fable-mode`'s staged loop is not running.
 
 Deep dive: <this-skill-dir>/references/guardrail-rules.md

package/fable-mode/execution-guardrails/references/guardrail-rules.md

@@ -26,17 +26,21 @@ attempted and where it failed — not a vague appeal to difficulty.
 
 ## 2. Warning threshold
 
-Across any run, minor concerns accumulate that aren't worth halting on individually.
-Keep a running count. At the threshold — **default three, tunable if the user sets a
-different number** — stop and surface all of them to the user at once before continuing.
+Across any run, minor concerns accumulate that are not worth interrupting execution
+for individually. Keep a running count. At the threshold — **default three, tunable if
+the user sets a different number** — batch them for the next natural report or handoff.
+The threshold changes presentation only: it MUST NOT stop, pause, return, or otherwise
+end a worker/stage by count alone.
 
-Rationale: three small things pointing the same direction usually mean one real problem
-worth a decision. Below threshold, keep working; a drip of trivial caveats is noise.
-At threshold, batch them — one interruption with full context beats three fragmentary
-ones.
+Rationale: three small things pointing the same direction are easier to evaluate as one
+batch. Below threshold, keep working; a drip of trivial caveats is noise. At threshold,
+keep working and preserve the batch for the report instead of creating a second circuit
+breaker.
 
 A concern that independently meets the verify-before-flag bar and is material on its own
-does not wait for the threshold. The threshold governs minor concerns only.
+may stop the current stage and be surfaced immediately. Repeated matching execution
+failures are governed separately by Rule-of-3 -> zoom-out -> RESUME/ESCALATE. The
+warning threshold governs minor-concern reporting only.
 
 ## 3. Find-and-replace safety
 

package/fable-mode/fable-haiku/SKILL.md

@@ -4,7 +4,7 @@ description: "Run staged fable work on Haiku for bulk mechanical tasks with expl
 license: Apache-2.0
 metadata:
   author: Miya Daniel
-  version: 0.16.3
+  version: 0.30.2
 ---
 
 # Fable Mode — Haiku

package/fable-mode/fable-opus/SKILL.md

@@ -4,7 +4,7 @@ description: "Run staged fable orchestration on Opus for cross-stage synthesis,
 license: Apache-2.0
 metadata:
   author: Miya Daniel
-  version: 0.16.3
+  version: 0.30.2
 ---
 
 # Fable Mode — Opus

package/fable-mode/fable-sonnet/SKILL.md

@@ -4,7 +4,7 @@ description: "Run staged fable work on Sonnet for non-trivial implementation, re
 license: Apache-2.0
 metadata:
   author: Miya Daniel
-  version: 0.16.3
+  version: 0.30.2
 ---
 
 # Fable Mode — Sonnet

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: 0.30.0
+  version: 0.30.2
 ---
 
 # Harness Everything

package/harness-everything/scripts/kernel-router-core.js

@@ -194,7 +194,6 @@ function printKernelContract(plan) {
       emitted.add(skill);
       if (skill === 'fable-mode') emitted.add('fable-discipline');
     }
-    console.log('   - Read-before-skip: MUST evaluate every suggested skill entry before omission. If applicable, MUST follow its core contract; adopting one suggestion does not waive resolution of the others.');
     if (plan.strategy && plan.strategy.startsWith('fable-')) {
       console.log('   - Fable is not a universal pipeline, but a selected Fable topology must be entered and resolved before completion.');
     }

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

@@ -151,7 +151,6 @@ function run(raw) {
   if (plan.strategySelection === 'selected') {
     console.log('   - Selected-topology required obligations are semantic MUSTs; implementation technique and local tactics MAY adapt.');
     console.log('   - Before claiming completion, MUST resolve required workflow evidence and objective verification, or report an explicit blocked/degraded disposition.');
-    console.log('   - Every suggested skill MUST resolve applicability. If applicable, follow its core contract; if not-applicable, keep a flow-grounded reason.');
     console.log('   - Tier 3 / Fable broad mutation MUST resolve isolation: verified linked worktree or explicit degraded fallback. Missing isolation is not a Harness lock.');
     console.log('   - Escape is only for genuinely uncovered declared scope with evidence; it does not erase covered MUST obligations.');
   }

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": "0.30.0",
+  "version": "0.30.2",
   "runtime": "index.mjs",
   "hooks": {
     "verify": "hooks/verify.js"

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "harness-everything",
-  "version": "0.30.0",
+  "version": "0.30.2",
   "description": "Harness OS: An Orchestrated Agent Operating System for AI-driven Development",
   "main": "harness-everything/scripts/bootstrap.js",
   "bin": {
@@ -17,7 +17,7 @@
     "repo:contract": "node scripts/repository-contract.js",
     "docs:sync": "node scripts/sync-current-docs.js",
     "test:repo-contract": "node ci/repository-contract.test.js",
-    "test:consistency": "node ci/consistency-check.js && node ci/doc-capability-consistency.test.js && node ci/repository-contract.test.js && node ci/mechanism-2ao-plugin-sync.test.js",
+    "test:consistency": "node ci/consistency-check.js && node ci/doc-capability-consistency.test.js && node ci/repository-contract.test.js && node ci/mechanism-2ao-plugin-sync.test.js && node ci/prompt-contract-regressions.test.js",
     "test:docs:capabilities": "node ci/doc-capability-consistency.test.js",
     "test:references": "node ci/reference-check.js",
     "test:release": "node ci/release-consistency-check.js && node ci/mechanism-2x-release-automation.test.js && node ci/mechanism-2x-release-commit-message.test.js && node ci/mechanism-2ap-sbom.test.js",

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

@@ -1,6 +1,6 @@
 {
   "name": "harness-everything",
-  "version": "0.30.0",
+  "version": "0.30.2",
   "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": "0.30.0",
+  "version": "0.30.2",
   "description": "Invariant-first engineering harness for routing, verification, and failure recovery while preserving agent autonomy.",
   "author": {
     "name": "Miya Daniel",

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

@@ -4,7 +4,7 @@ description: "Stage large, multi-source or multi-session tasks through a written
 license: Apache-2.0
 metadata:
   author: Miya Daniel
-  version: 0.16.3
+  version: 0.30.2
 ---
 
 # Fable Mode (v3)

package/plugins/harness-everything/skills/fable-mode/agents/fable-orchestrator.md

@@ -152,10 +152,10 @@ hasn't been confirmed present. Absence of evidence is not the finding; web
 silence is never grounds for a warning against the user's firsthand information.
 Confirm, then flag.
 
-**Warning threshold.** Keep a running count of minor concerns. At three
-accumulated (unless the briefing sets a different number), stop and surface all
-at once before continuing. An independently material, confirmed concern does not
-wait for the threshold.
+**Warning batching.** Collect minor concerns and list them together in the next
+natural report or handoff; their count alone MUST NOT stop, pause, or return the
+worker/stage. An independently material, confirmed concern may stop the current
+stage and be surfaced immediately.
 
 **Find-and-replace safety.** Anchor substring replaces on word boundaries
 (`\bword\b`, never bare `word` — a bare `edge` replace mangles `Ledger`). Prefer

package/plugins/harness-everything/skills/fable-mode/agents/fable-worker-haiku.md

@@ -19,8 +19,7 @@ Rules, in order:
 3. **Verify — tightened for this tier.** Run the named check from your briefing
    and include its output. NO artifact may be reported unverified without naming
    what check was impossible and why — a bare "unverified" is itself a failure.
-   Haiku's known failure is skipping verification under time pressure; the check
-   is not optional.
+   The named check is not optional.
 4. **Escalate instead of improvising.** If the assignment turns out to need
    judgment or synthesis (conflicting sources, ambiguous spec, design choices),
    stop and return the specific blocker — recommend fable-worker-sonnet. Do not
@@ -41,10 +40,10 @@ Grep, diff, run it, or check the source directly. Never report a problem that
 hasn't been confirmed present. Absence of evidence is not the finding. Confirm,
 then flag.
 
-**Warning threshold.** Keep a running count of minor concerns. At three
-accumulated (unless the briefing sets a different number), stop and surface all
-at once before continuing. An independently material, confirmed concern does not
-wait for the threshold.
+**Warning batching.** Collect minor concerns and list them together in the next
+natural report or handoff; their count alone MUST NOT stop, pause, or return the
+worker/stage. An independently material, confirmed concern may stop the current
+stage and be surfaced immediately.
 
 **Find-and-replace safety.** Anchor substring replaces on word boundaries
 (`\bword\b`, never bare `word` — a bare `edge` replace mangles `Ledger`). Prefer

package/plugins/harness-everything/skills/fable-mode/agents/fable-worker-sonnet.md

@@ -19,8 +19,8 @@ Rules of the loop, in order:
    do not build it.
 3. **Verify with the named check.** Your briefing states the pass condition. Run
    it — the actual command, diff, or read-back — and include the output in your
-   report. Sonnet's known failure is substituting "looks right" for the check
-   that can fail; do not do that. A check you did not run did not pass. If the
+   report. Do not substitute "looks right" for a check that can fail. A check
+   you did not run did not pass. If the
    check is impossible, say exactly what was impossible and why, and mark the
    artifact unverified.
 4. **Report format:** artifact path, check command, check output, confirmed
@@ -42,10 +42,10 @@ hasn't been confirmed present. Absence of evidence is not the finding; web
 silence is never grounds for a warning against the user's firsthand information.
 Confirm, then flag.
 
-**Warning threshold.** Keep a running count of minor concerns. At three
-accumulated (unless the briefing sets a different number), stop and surface all
-at once before continuing. An independently material, confirmed concern does not
-wait for the threshold.
+**Warning batching.** Collect minor concerns and list them together in the next
+natural report or handoff; their count alone MUST NOT stop, pause, or return the
+worker/stage. An independently material, confirmed concern may stop the current
+stage and be surfaced immediately.
 
 **Find-and-replace safety.** Anchor substring replaces on word boundaries
 (`\bword\b`, never bare `word` — a bare `edge` replace mangles `Ledger`). Prefer

package/plugins/harness-everything/skills/fable-mode/execution-guardrails/SKILL.md

@@ -7,7 +7,7 @@ description: >-
 license: Apache-2.0
 metadata:
   author: Miya Daniel
-  version: 0.16.3
+  version: 0.30.2
 ---
 
 # Execution Guardrails
@@ -17,7 +17,7 @@ metadata:
 | Component | Spec |
 | :--- | :--- |
 | **Trigger / Input** | Turn raising a warning or performing search-and-replace edits. |
-| **Expected Output** | Verified warnings; batched caveats (3-item threshold); corruption-checked edits. |
+| **Expected Output** | Verified warnings; batched caveats without count-based stops; corruption-checked edits. |
 | **State Mutations** | None — governs execution quality for file-editing turns. |
 | **Enforcement Gate** | Verify before flagging; validate edits post-write. |
 
@@ -35,9 +35,11 @@ metadata:
 ## Core Rules
 
 1. **Verify before flag** — Confirm a problem exists before reporting it. Never convert absence of evidence into a warning.
-2. **Warning threshold** — Batch minor concerns; surface them together at three (default). Material concerns do not wait.
+2. **Warning batching.** Collect minor concerns and list them together in the next natural report or handoff; their count alone MUST NOT stop, pause, or return the worker/stage. An independently material, confirmed concern may stop the current stage and be surfaced immediately.
 3. **Find-and-replace safety** — Prefer structured edit tools over shell `sed`; anchor with unique context or `\bword\b` boundaries; verify file integrity post-edit. Never replace-all blindly.
 
+Repeated matching execution failures remain governed by Rule-of-3 / `zoom-out`; warning batching never substitutes for that recovery path.
+
 These rules are always-on, even when `fable-mode`'s staged loop is not running.
 
 Deep dive: <this-skill-dir>/references/guardrail-rules.md

package/plugins/harness-everything/skills/fable-mode/execution-guardrails/references/guardrail-rules.md

@@ -26,17 +26,21 @@ attempted and where it failed — not a vague appeal to difficulty.
 
 ## 2. Warning threshold
 
-Across any run, minor concerns accumulate that aren't worth halting on individually.
-Keep a running count. At the threshold — **default three, tunable if the user sets a
-different number** — stop and surface all of them to the user at once before continuing.
+Across any run, minor concerns accumulate that are not worth interrupting execution
+for individually. Keep a running count. At the threshold — **default three, tunable if
+the user sets a different number** — batch them for the next natural report or handoff.
+The threshold changes presentation only: it MUST NOT stop, pause, return, or otherwise
+end a worker/stage by count alone.
 
-Rationale: three small things pointing the same direction usually mean one real problem
-worth a decision. Below threshold, keep working; a drip of trivial caveats is noise.
-At threshold, batch them — one interruption with full context beats three fragmentary
-ones.
+Rationale: three small things pointing the same direction are easier to evaluate as one
+batch. Below threshold, keep working; a drip of trivial caveats is noise. At threshold,
+keep working and preserve the batch for the report instead of creating a second circuit
+breaker.
 
 A concern that independently meets the verify-before-flag bar and is material on its own
-does not wait for the threshold. The threshold governs minor concerns only.
+may stop the current stage and be surfaced immediately. Repeated matching execution
+failures are governed separately by Rule-of-3 -> zoom-out -> RESUME/ESCALATE. The
+warning threshold governs minor-concern reporting only.
 
 ## 3. Find-and-replace safety
 

package/plugins/harness-everything/skills/fable-mode/fable-haiku/SKILL.md

@@ -4,7 +4,7 @@ description: "Run staged fable work on Haiku for bulk mechanical tasks with expl
 license: Apache-2.0
 metadata:
   author: Miya Daniel
-  version: 0.16.3
+  version: 0.30.2
 ---
 
 # Fable Mode — Haiku

package/plugins/harness-everything/skills/fable-mode/fable-opus/SKILL.md

@@ -4,7 +4,7 @@ description: "Run staged fable orchestration on Opus for cross-stage synthesis,
 license: Apache-2.0
 metadata:
   author: Miya Daniel
-  version: 0.16.3
+  version: 0.30.2
 ---
 
 # Fable Mode — Opus

package/plugins/harness-everything/skills/fable-mode/fable-sonnet/SKILL.md

@@ -4,7 +4,7 @@ description: "Run staged fable work on Sonnet for non-trivial implementation, re
 license: Apache-2.0
 metadata:
   author: Miya Daniel
-  version: 0.16.3
+  version: 0.30.2
 ---
 
 # Fable Mode — Sonnet

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: 0.30.0
+  version: 0.30.2
 ---
 
 # Harness Everything

package/plugins/harness-everything/skills/harness-everything/scripts/kernel-router-core.js

@@ -194,7 +194,6 @@ function printKernelContract(plan) {
       emitted.add(skill);
       if (skill === 'fable-mode') emitted.add('fable-discipline');
     }
-    console.log('   - Read-before-skip: MUST evaluate every suggested skill entry before omission. If applicable, MUST follow its core contract; adopting one suggestion does not waive resolution of the others.');
     if (plan.strategy && plan.strategy.startsWith('fable-')) {
       console.log('   - Fable is not a universal pipeline, but a selected Fable topology must be entered and resolved before completion.');
     }

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

@@ -151,7 +151,6 @@ function run(raw) {
   if (plan.strategySelection === 'selected') {
     console.log('   - Selected-topology required obligations are semantic MUSTs; implementation technique and local tactics MAY adapt.');
     console.log('   - Before claiming completion, MUST resolve required workflow evidence and objective verification, or report an explicit blocked/degraded disposition.');
-    console.log('   - Every suggested skill MUST resolve applicability. If applicable, follow its core contract; if not-applicable, keep a flow-grounded reason.');
     console.log('   - Tier 3 / Fable broad mutation MUST resolve isolation: verified linked worktree or explicit degraded fallback. Missing isolation is not a Harness lock.');
     console.log('   - Escape is only for genuinely uncovered declared scope with evidence; it does not erase covered MUST obligations.');
   }

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

@@ -4,7 +4,7 @@ description: Apply Harness style guidelines when writing or refactoring SKILL.md
 license: Apache-2.0
 metadata:
   author: Miya Daniel
-  version: 0.4.0
+  version: 0.30.2
 ---
 
 # Skill Style
@@ -34,7 +34,7 @@ Apply the Harness writing standard when creating or refactoring `SKILL.md` files
 ## Core Rules
 
 1. MUST keep frontmatter accurate and the description routeable.
-2. MUST include, in order: title, introduction, Skill Contract, usage, and actionable rules.
+2. MUST cover the skill purpose, Skill Contract, usage/applicability, and actionable rules; section order MAY vary for readability and routeability.
 3. MUST use imperative language and name the enforcing command or gate.
 4. MUST avoid overlap with OS-layer routing or domain expertise.
 5. For intent interviews, drafting, and prompt tests, load `<skills-repo-root>/skill-creator/SKILL.md`.

package/plugins/harness-everything/skills/skill-style/references/style-guide.md

@@ -3,12 +3,12 @@
 When you need to create a new Skill or refactor an existing one, strictly adhere to the writing style in this document to ensure all Skills seamlessly integrate into the `harness-everything` routing system and are mathematically enforced by scripts.
 
 ## 1. Structured Definition
-Every Skill file (`SKILL.md`) MUST contain the following standard structure:
+Every Skill file (`SKILL.md`) MUST cover the following elements. Their relative order MAY vary when that improves routing clarity or readability; do not treat this list as a global section-order contract:
 
-1.  **Title & Introduction**: Clearly state the purpose of this Skill.
-2.  **📋 Skill Contract (CRITICAL)**: A strict Markdown table defining inputs, outputs, state mutations, and script gates. This replaces vague prose.
-3.  **Triggers / Usage**: Explicitly tell the system when this skill applies.
-4.  **Core Rules / Action List**: Specific, actionable commands tied to Terminal Scripts. Avoid vague suggestions.
+- **Title & Purpose**: Clearly state the purpose of this Skill.
+- **📋 Skill Contract (CRITICAL)**: A strict Markdown table defining inputs, outputs, state mutations, and script gates. This replaces vague prose.
+- **Triggers / Usage**: Explicitly tell the system when this skill applies.
+- **Core Rules / Action List**: Specific, actionable commands tied to Terminal Scripts. Avoid vague suggestions.
 
 ### 📋 The Skill Contract Format
 Every SKILL.md MUST include this table exactly:

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:facf3456-428b-56a4-a538-e7ecb4ac28ca",
+  "serialNumber": "urn:uuid:609a39f1-97ad-59d5-a8ef-97f1b6da412b",
   "version": 1,
   "metadata": {
-    "timestamp": "2026-09-28T02:02:14.749Z",
+    "timestamp": "2026-10-01T02:54:31.907Z",
     "tools": [
       {
         "vendor": "Harness Everything",
         "name": "generate-sbom.js",
-        "version": "0.30.0"
+        "version": "0.30.2"
       }
     ],
     "component": {
       "type": "application",
-      "bom-ref": "pkg:npm/harness-everything@0.30.0",
+      "bom-ref": "pkg:npm/harness-everything@0.30.2",
       "name": "harness-everything",
-      "version": "0.30.0",
-      "purl": "pkg:npm/harness-everything@0.30.0"
+      "version": "0.30.2",
+      "purl": "pkg:npm/harness-everything@0.30.2"
     }
   },
   "components": [
@@ -1999,7 +1999,7 @@
       ]
     },
     {
-      "ref": "pkg:npm/harness-everything@0.30.0",
+      "ref": "pkg:npm/harness-everything@0.30.2",
       "dependsOn": [
         "pkg:npm/%40commitlint/cli@19.8.1",
         "pkg:npm/%40commitlint/config-conventional@19.8.1",

package/skill-style/SKILL.md

@@ -4,7 +4,7 @@ description: Apply Harness style guidelines when writing or refactoring SKILL.md
 license: Apache-2.0
 metadata:
   author: Miya Daniel
-  version: 0.4.0
+  version: 0.30.2
 ---
 
 # Skill Style
@@ -34,7 +34,7 @@ Apply the Harness writing standard when creating or refactoring `SKILL.md` files
 ## Core Rules
 
 1. MUST keep frontmatter accurate and the description routeable.
-2. MUST include, in order: title, introduction, Skill Contract, usage, and actionable rules.
+2. MUST cover the skill purpose, Skill Contract, usage/applicability, and actionable rules; section order MAY vary for readability and routeability.
 3. MUST use imperative language and name the enforcing command or gate.
 4. MUST avoid overlap with OS-layer routing or domain expertise.
 5. For intent interviews, drafting, and prompt tests, load `<skills-repo-root>/skill-creator/SKILL.md`.

package/skill-style/references/style-guide.md

@@ -3,12 +3,12 @@
 When you need to create a new Skill or refactor an existing one, strictly adhere to the writing style in this document to ensure all Skills seamlessly integrate into the `harness-everything` routing system and are mathematically enforced by scripts.
 
 ## 1. Structured Definition
-Every Skill file (`SKILL.md`) MUST contain the following standard structure:
+Every Skill file (`SKILL.md`) MUST cover the following elements. Their relative order MAY vary when that improves routing clarity or readability; do not treat this list as a global section-order contract:
 
-1.  **Title & Introduction**: Clearly state the purpose of this Skill.
-2.  **📋 Skill Contract (CRITICAL)**: A strict Markdown table defining inputs, outputs, state mutations, and script gates. This replaces vague prose.
-3.  **Triggers / Usage**: Explicitly tell the system when this skill applies.
-4.  **Core Rules / Action List**: Specific, actionable commands tied to Terminal Scripts. Avoid vague suggestions.
+- **Title & Purpose**: Clearly state the purpose of this Skill.
+- **📋 Skill Contract (CRITICAL)**: A strict Markdown table defining inputs, outputs, state mutations, and script gates. This replaces vague prose.
+- **Triggers / Usage**: Explicitly tell the system when this skill applies.
+- **Core Rules / Action List**: Specific, actionable commands tied to Terminal Scripts. Avoid vague suggestions.
 
 ### 📋 The Skill Contract Format
 Every SKILL.md MUST include this table exactly: