harness-everything 0.16.0 → 0.16.2

package/scripts/lib/advisory-text.js

@@ -7,35 +7,23 @@ const MARKER = "Harness OS Guidance (Advisory)";
 
 const advisoryInstructions = [
   `\n# ${MARKER}`,
-  `This surface cannot be assumed to mechanically enforce every Harness lifecycle transition.`,
-  `Treat the workflow contract below as required agent behavior, while keeping enforcement`,
-  `claims bounded by the host's verified capabilities.`,
+  `Harness is an observer/router/reminder layer on this surface; do not treat its workflow guidance as a hard scheduler.`,
   ``,
-  `## 🚦 MANDATORY ENTRY TRIAGE & WORKFLOW ROUTING`,
-  `For every software/project prompt, load the \`harness-everything\` skill and establish the routing contract before mutation:`,
-  `1. Run \`npx github:dyphn1/Harness-everything next "<Brief summary of user's prompt>"\`. If terminal execution is unavailable, apply the same contract from the skill instead of skipping routing.`,
-  `2. For EVERY suggested skill, read its complete \`SKILL.md\` entry and resolve applicability from \`USE FOR\`, \`DO NOT USE FOR\`, workflow/basic flow, and hard rules. A name, description, router summary, or "routine/simple/already clear" judgement is not enough to omit it.`,
-  `3. The selected workflow topology is mandatory once applicable. Execute it to resolution; choose tools, reasoning, implementation technique, and decomposition freely inside it. Do not replace it with a direct path because you believe you can solve the task without the workflow.`,
-  `4. If the selected workflow genuinely cannot cover part of the task, record an explicit escape for the uncovered scope with evidence. Covered obligations remain mandatory. Host-capability loss must be surfaced, not silently converted into optional execution.`,
-  `5. Surface a compact checkpoint near the first progress update:`,
-  `   \`\`\`markdown`,
-  `   ## 🚦 Harness OS Routing Checkpoint`,
-  `   - **Active Tier**: Tier 1 | Tier 2 | Tier 3 | unclassified`,
-  `   - **Strategy**: <selected/deferred strategy>`,
-  `   - **Workflow State**: <active | deferred | blocked | escaped>`,
-  `   - **Required Invariants**: <router invariants>`,
-  `   - **Suggested Skills**: <deduplicated suggestions or none>`,
-  `   - **Applicability**: <use | not-applicable + reason | unresolved/unavailable>`,
-  `   - **Escape**: <none | reason + uncovered scope + evidence>`,
-  `   \`\`\``,
+  `## 🚦 ENTRY TRIAGE & WORKFLOW GUIDANCE`,
+  `For software/project work, load the \`harness-everything\` skill and establish routing context before broad mutation:`,
+  `1. Run \`npx github:dyphn1/Harness-everything next "<Brief summary of user's prompt>"\` when terminal execution is available.`,
+  `2. For EVERY suggested skill, read its complete \`SKILL.md\` entry and evaluate applicability from \`USE FOR\`, \`DO NOT USE FOR\`, and its basic flow.`,
+  `3. Treat the selected workflow topology and numeric limits as planning guidance, not a lock. Choose, combine, reorder, or skip steps when evidence supports it.`,
+  `4. Prefer objective verification before declaring done and worktree isolation for broad/Tier-3 mutation.`,
+  `5. Surface a compact routing checkpoint with tier, strategy, suggested skills, and any relevant warnings.`,
   ``,
   `## 🤖 COGNITIVE COMPLIANCE`,
-  `- **No universal skill pipeline**: do not force every task through TODO/TDD/Fable. The router selects the smallest sufficient topology; suggested skills are resolved for applicability.`,
-  `- **Applicable skill flow**: reading a skill is not permission to discard it when its workflow actually applies.`,
-  `- **Pre-completion verification**: before declaring done, run \`npx github:dyphn1/Harness-everything verify\` in the project root and fix failures. An instruction-only host may not block you mechanically, but the requirement remains part of the contract.`,
-  `- **Rule of 3**: after 3 same-signature failures, stop micro-retrying and use a fresh diagnosis / zoom-out.`,
+  `- **No universal skill pipeline**: do not force every task through TODO/TDD/Fable.`,
+  `- **Rule of 3**: after 3 same-signature failures, stop micro-retrying and use a fresh diagnosis / zoom-out. This reflection boundary may block mutation until completed.`,
+  `- **Permission boundaries are separate**: explicit host/user approval for destructive or external actions remains authoritative.`,
+  `- **Verification is evidence, not a cage**: missing evidence should trigger a reminder, not a persistent workflow lock.`,
   `- **Environment discovery**: discover OS, shell, package manager/runtime, and host capability before relying on them.`,
-  `- **Memory / self-evolve**: persist only verified reusable lessons; use escape/replan/recovery evidence to improve workflow coverage rather than bypassing the active workflow.`,
+  `- **Memory / self-evolve**: persist only verified reusable lessons.`,
   `- **Prefer editing**: prefer targeted edits and logically complete commits over broad rewrites.`,
   ``
 ].join('\n');
@@ -149,10 +137,9 @@ function buildCodexGlobalContent() {
     `- Discover the environment and host capabilities before relying on them.`,
     `- For software/project work, run \`npx github:dyphn1/Harness-everything next "<summary>"\` before mutation and surface the routing checkpoint.`,
     `- Read every suggested skill's complete \`SKILL.md\` entry before resolving applicability; do not omit it from metadata or confidence alone.`,
-    `- Execute the selected workflow topology to resolution. The model controls HOW inside the topology, not WHETHER the selected topology exists.`,
-    `- Do not impose a universal TODO/TDD/Fable sequence; use the smallest selected topology plus applicable skills.`,
-    `- Escape only for genuinely uncovered workflow scope and record reason + scope + evidence.`,
-    `- Before declaring done, run \`npx github:dyphn1/Harness-everything verify\` and fix failures.`,
+    `- Use the selected workflow topology as planning guidance; the model may adapt or skip steps with an explicit evidence-based reason.`,
+    `- Do not impose a universal TODO/TDD/Fable sequence; use the smallest useful topology plus applicable skills.`,
+    `- Prefer objective verification before declaring done; missing verification is a reminder, not a persistent lock.`,
     `- After 3 same-signature failures, stop retrying and use a fresh diagnosis / zoom-out.`,
     `- Prefer targeted edits and logically complete commits.`,
     ``

package/using-git-worktrees/SKILL.md

@@ -1,10 +1,10 @@
 ---
 name: using-git-worktrees
-description: Use when starting feature work needing isolation or before implementation plans - ensures an isolated workspace via native tools or git worktree fallback
+description: Use when starting feature work needing isolation or before implementation plans - recommends an isolated workspace via native tools or git worktree fallback
 license: Apache-2.0
 metadata:
   author: Miya Daniel
-  version: 0.8.1
+  version: 0.16.1
 ---
 
 # Using Git Worktrees
@@ -13,7 +13,7 @@ Use native worktree support first; raw Git is the fallback.
 
 ## Contract
 
-- **Major workflow mode** — Tier 3 / Fable-class engineering must be isolated before source/artifact mutation. Reuse an existing linked worktree or create one. If isolation cannot be established, stop `BLOCKED`; never fall back to the primary working tree.
+- **Major workflow guidance** — Tier 3 / Fable-class engineering is safer in a linked worktree before broad source/artifact mutation. Reuse one or create one when practical.
 - **Ordinary mode** — isolation-needing feature work may honor an explicit user preference to stay in place.
 - Never nest a worktree inside an already isolated worktree.
 
@@ -28,11 +28,11 @@ git rev-parse --show-superproject-working-tree
 ```
 Different git/common dirs and no superproject => already isolated; continue to Step 2. A submodule is a normal repo for this check.
 
-**Step 1 — Create/enter**: prefer native `EnterWorktree`, `/worktree`, or `--worktree`. Otherwise use `git worktree add "$path" -b "$BRANCH_NAME"`. For major mode, choose an already-ignored or external/sibling path so setup does not require modifying the primary tree first. Creation/entry failure => `BLOCKED`. Only ordinary mode may continue in place after an explicit decline/unsupported environment.
+**Step 1 — Create/enter**: prefer native `EnterWorktree`, `/worktree`, or `--worktree`. Otherwise use `git worktree add "$path" -b "$BRANCH_NAME"`. Prefer an already-ignored or external/sibling path. If creation/entry fails, report it and continue only with explicit awareness of the isolation risk.
 
 **Step 2 — Setup**: install project dependencies as needed.
 
-**Step 3 — Baseline**: run the relevant tests/build in the isolated tree before implementation; existing failures must be surfaced before mutation proceeds.
+**Step 3 — Baseline**: run relevant tests/build before implementation when useful; surface existing failures before relying on the baseline.
 
 Deep dive: <this-skill-dir>/references/workflow-details.md
 

package/zoom-out/SKILL.md

@@ -4,7 +4,7 @@ description: "Reflect-first circuit breaker - after 3 failures, stop edits, rebu
 license: Apache-2.0
 metadata:
   author: Miya Daniel
-  version: 0.4.0
+  version: 0.16.2
 ---
 
 # Zoom Out (Circuit Breaker)
@@ -18,7 +18,7 @@ Stop repeated failures, rebuild the facts, and choose a safe next step.
 | **Trigger / Input** | Three same-signature failures or an explicit loop/rethink request. |
 | **Expected Output** | Fact-checked report ending in `RESUME` or `ESCALATE`. |
 | **State Mutations** | Writes the session `zoom-out-report.md`; reset may clear breaker state. |
-| **Enforcement Gate** | `<skills-repo-root>/hooks/scripts/rule-of-3.js` plus a valid report; reset only after the second cycle. |
+| **Enforcement Gate** | `<skills-repo-root>/hooks/scripts/rule-of-3.js` plus a valid report; a later three-failure cycle requests another reflection. |
 
 ## Circuit Breaker Flow
 
@@ -26,7 +26,7 @@ Stop repeated failures, rebuild the facts, and choose a safe next step.
 2. Use read-only tools to restate the goal and check files, configuration, and logs.
 3. Fill `<this-skill-dir>/templates/zoom-out-report.template.md` and end with `RESUME` or `ESCALATE`.
 4. Resume only on an untried path; escalate genuine user decisions with options.
-5. Clear a repeated breaker cycle with `npm run harness:reset`; record the insight with `self-evolve`.
+5. If three more matching failures occur, run another zoom-out cycle. `npm run harness:reset` is only an optional manual state clear; record the insight with `self-evolve`.
 
 ## USE FOR:
 - "you are stuck in a loop"

package/zoom-out/references/circuit-breaker.md

@@ -21,7 +21,7 @@ flowchart TD
 
     Resume --> Resolved{5. Problem Cracking Succeeds?}
     Resolved -- Yes --> SelfEvolve[Call self-evolve to Persist Insight]
-    Resolved -- No (3 More Failures) --> Escalate
+    Resolved -- No (3 More Matching Failures) --> CeaseFire
 ```
 
 ## 1. Triggers
@@ -50,7 +50,7 @@ A complete report automatically releases the circuit breaker on hook-enabled sys
 ## 5. Phase 4 — Decision Gate: Resume or Escalate
 
 - **RESUME**: Selected when the fresh diagnosis identifies a clear, untried path within existing authority.
-- **ESCALATE**: Reserved for true decision points belonging to the user (conflicting requirements, destructive migration, missing credentials/access, or repeated breaker trips).
+- **ESCALATE**: Reserved for true decision points belonging to the user (conflicting requirements, destructive migration, missing credentials/access, or repeated breaker trips that expose a genuine decision or access gap).
 Hand the human a **decision**, not a plea:
 
 > "Goal: [...]. I falsified paths X, Y, Z — verified facts: [...].
@@ -61,6 +61,6 @@ Hand the human a **decision**, not a plea:
 Banned: "I have tried everything and failed, please help." That reports incapability, not a decision.
 
 ## 7. Recovery
-- **Self-recovery path**: a valid report ending in `RESUME` releases the breaker — reload the appropriate execution mode (`tdd`, `fable-mode`) and execute the new diagnosis. If the SAME failure signature accumulates 3 more failures, the breaker hard-locks and the decision goes to the human.
-- **Human path**: after the human answers an `ESCALATE`, or clears a hard lock (`npm run harness:reset` in their own terminal, or a new session / `/clear`), continue under their direction.
+- **Self-recovery path**: a valid report ending in `RESUME` releases the breaker — reload the appropriate execution mode (`tdd`, `fable-mode`) and execute the new diagnosis. If the SAME failure signature accumulates 3 more failures, start another zoom-out/reflection cycle.
+- **Human path**: after the human answers an `ESCALATE`, continue under their direction. `npm run harness:reset` (or a new session / `/clear`) is an optional manual state clear for recovery or maintenance; it is not required merely because the breaker re-tripped.
 - Either way, once the problem is ultimately cracked, feed the insight to `self-evolve`.