@cobusgreyling/loop-init 1.3.1 → 1.3.3

package/starters/dependency-sweeper-opencode/skills/dependency-triage/SKILL.md

@@ -0,0 +1,35 @@
+---
+name: dependency-triage
+description: >
+  Scan package manifests and lockfiles for outdated and vulnerable
+  dependencies. Classify by severity and update type.
+user_invocable: true
+---
+
+# Dependency Triage Skill
+
+You are a dependency sweeper agent. Scan for outdated and vulnerable packages.
+
+## Scan Sources
+
+- `npm outdated` / `npm audit`
+- `cargo outdated` / `cargo audit`
+- `pip list --outdated`
+- Lockfile analysis
+
+## Classification
+
+- **Patch**: auto-fix candidate
+- **Minor**: auto-fix candidate
+- **Major**: escalate to human
+- **CVE**: escalate high-severity; patch-only for low/medium
+
+## Output
+
+Update `dependency-sweeper-state.md` with prioritized update list.
+
+## Rules
+
+- Patch-only by default in week one.
+- Honour denylist in state file.
+- Run `npm ci && npm test` (or equivalent) before approving.

package/starters/issue-triage-opencode/AGENTS.md

@@ -0,0 +1,16 @@
+# AGENTS.md — Issue Triage (Opencode)
+
+## Loop Mode
+- Start in L1 propose-only mode.
+- Read `issue-triage-state.md` before every run.
+- Never auto-label, auto-close, or auto-comment in week one.
+
+## Safety
+- P0/P1 on auth, payments, security, or public API: always escalate.
+- L2 auto-labels limited to curated allowlist.
+- Verifier gate required before applying any label.
+
+## Verification
+- L1: human reviews proposed labels before application.
+- L2: verifier confirms labels are in the allowlist.
+- Duplicates: propose as "possible duplicate of #NNN" — never auto-close.

package/starters/issue-triage-opencode/LOOP.md

@@ -0,0 +1,21 @@
+# Loop Configuration — Issue Triage (Opencode)
+
+## Active Loops
+
+| Pattern | Cadence | Status | Command |
+|---------|---------|--------|---------|
+| Issue Triage | 2h-1d | L1 propose-only | `opencode run "Run issue-triage" --agent loop-triage` via cron |
+
+## Human Gates
+- P0/P1 on auth, payments, security, public API: always human.
+- Duplicate proposals noted as "possible duplicate of #NNN" — never auto-close.
+- L2 auto-labels limited to allowlist.
+
+## Budget
+- Max sub-agent spawns per run: 0 (L1), 1 (L2).
+- Early exit if no new issues since last run.
+
+## Links
+- Pattern: [issue-triage](../../patterns/issue-triage.md)
+- Example: [examples/opencode/issue-triage.md](../../examples/opencode/issue-triage.md)
+- Safety: [docs/safety.md](../../docs/safety.md)

package/starters/issue-triage-opencode/README.md

@@ -0,0 +1,43 @@
+# Issue Triage — Opencode Starter
+
+Clone-and-run scaffold for the **Issue Triage** pattern with opencode. Keep the issue queue legible so morning triage always knows the top five.
+
+## Quick Start
+
+```bash
+npx @cobusgreyling/loop-init . --pattern issue-triage --tool opencode
+```
+
+Or copy manually:
+
+```bash
+cp -r starters/issue-triage-opencode/skills .
+cp starters/issue-triage-opencode/AGENTS.md .
+cp starters/issue-triage-opencode/LOOP.md .
+cp starters/issue-triage-opencode/issue-triage-state.md.example issue-triage-state.md
+cp starters/issue-triage-opencode/opencode.json.example opencode.json
+```
+
+Start (L1 propose-only, week 1):
+
+```bash
+opencode run \
+  "Run skills/issue-triage/SKILL.md. Scan open issues since last run. Update issue-triage-state.md with top 5, proposed labels, and needs-human bucket. Propose only — do not apply labels or close issues." \
+  --title "Issue triage"
+```
+
+## What's Included
+
+| File | Purpose |
+|------|---------|
+| `issue-triage-state.md.example` | State spine (issue queue health) |
+| `skills/issue-triage/SKILL.md` | Issue-focused triage skill |
+| `AGENTS.md` | Always-on safety rules |
+| `LOOP.md` | Cadence, gates, budget |
+| `opencode.json.example` | Named agent definitions |
+
+## Next Steps
+
+- [patterns/issue-triage.md](../../patterns/issue-triage.md)
+- [examples/opencode/issue-triage.md](../../examples/opencode/issue-triage.md)
+- [docs/loop-design-checklist.md](../../docs/loop-design-checklist.md)

package/starters/issue-triage-opencode/issue-triage-state.md.example

@@ -0,0 +1,11 @@
+# Issue Triage State
+Last run: 2026-06-20 09:00 UTC
+Open actionable: 0
+New since last run: 0
+Needs human: 0
+
+## Top 5 (by loop score)
+- <!-- #NNN (type, priority) — summary — proposed labels -->
+
+## Proposed Labels (not applied — L1)
+- <!-- #NNN: label1, label2 -->

package/starters/issue-triage-opencode/opencode.json.example

@@ -0,0 +1,35 @@
+{
+  "$schema": "https://opencode.ai/config.json",
+  "agent": {
+    "issue-triage": {
+      "name": "issue-triage",
+      "description": "Issue triage loop. Reads issue-triage-state.md, scans open issues, and proposes labels and priorities. Propose-only in L1 mode.",
+      "mode": "primary",
+      "prompt": "Read AGENTS.md, LOOP.md, issue-triage-state.md, and skills/issue-triage/SKILL.md. Scan open issues since last run. Update state with top 5, proposed labels, and needs-human bucket. Propose only — do not apply labels or close issues.",
+      "permission": {
+        "bash": "ask",
+        "edit": "ask"
+      }
+    },
+    "implementer": {
+      "name": "implementer",
+      "description": "L2 implementer for auto-labeling allowlisted labels.",
+      "mode": "subagent",
+      "prompt": "Apply only allowlisted labels (area:*, needs-repro, needs-info, duplicate?) after verifier passes. Never auto-apply P0, P1, security, or breaking-change labels. Never close or comment without human approval.",
+      "permission": {
+        "bash": "ask",
+        "edit": "ask"
+      }
+    },
+    "verifier": {
+      "name": "verifier",
+      "description": "Checker agent for issue label proposals. APPROVE or REJECT only.",
+      "mode": "subagent",
+      "prompt": "Verify proposed labels are in the allowlist. Confirm no P0/P1/security labels are being auto-applied. Do not edit. APPROVE or REJECT.",
+      "permission": {
+        "bash": "ask",
+        "edit": "deny"
+      }
+    }
+  }
+}

package/starters/issue-triage-opencode/skills/issue-triage/SKILL.md

@@ -0,0 +1,33 @@
+---
+name: issue-triage
+description: >
+  Scan open issues and discussions, deduplicate, prioritize,
+  and propose labels. Provides a clean actionable queue.
+user_invocable: true
+---
+
+# Issue Triage Skill
+
+You are an issue triage agent. Keep the issue queue legible.
+
+## Scan Sources
+
+- Open issues and discussions
+- Prior state in `issue-triage-state.md`
+- Labels, milestones, linked PRs
+
+## Output
+
+Update `issue-triage-state.md` with:
+
+- Top 5 prioritized items (P0-P3)
+- Proposed labels per item
+- Needs-human bucket for ambiguous or security-sensitive items
+- Possible duplicates
+
+## Rules
+
+- L1: propose only — never auto-label, auto-close, or auto-comment.
+- P0/P1 on auth, payments, security, public API: always escalate.
+- Duplicates: note as "possible duplicate of #NNN" — never auto-close.
+- L2 auto-labels limited to curated allowlist.

package/starters/post-merge-cleanup-opencode/AGENTS.md

@@ -0,0 +1,15 @@
+# AGENTS.md — Post-Merge Cleanup (Opencode)
+
+## Loop Mode
+- Start in L1 report-only mode.
+- Read `post-merge-state.md` before any scan.
+- Run off-peak (evening) to avoid colliding with active branches.
+
+## Safety
+- Never auto-fix architectural debt — file a ticket.
+- Denylist paths always go to a human.
+- Max 2 fix attempts per run.
+
+## Verification
+- For L2+ changes, verifier confirms fix scope and tests.
+- Record attempt evidence in state.

package/starters/post-merge-cleanup-opencode/LOOP.md

@@ -0,0 +1,26 @@
+# Loop Configuration — Post-Merge Cleanup (Opencode)
+
+## Active Loops
+
+| Pattern | Cadence | Status | Command |
+|---------|---------|--------|---------|
+| Post-Merge Cleanup | 1d | L1 report-only | `opencode run "Run post-merge-scan"` via cron (off-peak) |
+
+## Human Gates
+- Architectural debt is ticketed, never auto-fixed.
+- Denylist paths always human.
+- Max 2 fix attempts per run.
+
+## Worktrees
+- Use `git worktree` for any code-change attempt (L2+).
+- One worktree per fix; discard after REJECT.
+
+## Budget
+- Max sub-agent spawns per run: 0 (L1), 2 (L2).
+- Run off-peak (evening) to avoid collision.
+- Pause if token budget exceeded.
+
+## Links
+- Pattern: [post-merge-cleanup](../../patterns/post-merge-cleanup.md)
+- Example: [examples/opencode/post-merge-cleanup.md](../../examples/opencode/post-merge-cleanup.md)
+- Safety: [docs/safety.md](../../docs/safety.md)

package/starters/post-merge-cleanup-opencode/README.md

@@ -0,0 +1,44 @@
+# Post-Merge Cleanup — Opencode Starter
+
+Clone-and-run scaffold for the **Post-Merge Cleanup** pattern with opencode. Follow-up tech debt after merges land on main.
+
+## Quick Start
+
+```bash
+npx @cobusgreyling/loop-init . --pattern post-merge-cleanup --tool opencode
+```
+
+Or copy manually:
+
+```bash
+cp -r starters/post-merge-cleanup-opencode/skills .
+cp starters/post-merge-cleanup-opencode/AGENTS.md .
+cp starters/post-merge-cleanup-opencode/LOOP.md .
+cp starters/post-merge-cleanup-opencode/post-merge-state.md.example post-merge-state.md
+cp starters/post-merge-cleanup-opencode/opencode.json.example opencode.json
+```
+
+Start (report-only, week 1):
+
+```bash
+opencode run \
+  "Run skills/post-merge-scan/SKILL.md. Scan merges to main in the last 48h. Propose small doc/lint/comment fixes only — ticket anything architectural. Update post-merge-state.md. Do not edit source code." \
+  --title "Post-merge cleanup"
+```
+
+## What's Included
+
+| File | Purpose |
+|------|---------|
+| `post-merge-state.md.example` | State spine template |
+| `skills/post-merge-scan/SKILL.md` | Merge-focused scan skill |
+| `AGENTS.md` | Always-on safety rules |
+| `LOOP.md` | Cadence, gates, budget |
+| `opencode.json.example` | Named agent definitions |
+
+## Next Steps
+
+- [patterns/post-merge-cleanup.md](../../patterns/post-merge-cleanup.md)
+- [examples/opencode/post-merge-cleanup.md](../../examples/opencode/post-merge-cleanup.md)
+- [docs/loop-design-checklist.md](../../docs/loop-design-checklist.md)
+- [stories/post-merge-cleanup-honest-win.md](../../stories/post-merge-cleanup-honest-win.md)

package/starters/post-merge-cleanup-opencode/opencode.json.example

@@ -0,0 +1,35 @@
+{
+  "$schema": "https://opencode.ai/config.json",
+  "agent": {
+    "post-merge-scan": {
+      "name": "post-merge-scan",
+      "description": "Post-merge scan loop. Reads post-merge-state.md, scans recent merges, and proposes small cleanup fixes.",
+      "mode": "primary",
+      "prompt": "Read AGENTS.md, LOOP.md, post-merge-state.md, and skills/post-merge-scan/SKILL.md. Scan merges to main in the last 48h. Propose small doc/lint/comment fixes. Ticket architectural debt. Do not edit code in L1 mode.",
+      "permission": {
+        "bash": "ask",
+        "edit": "ask"
+      }
+    },
+    "implementer": {
+      "name": "implementer",
+      "description": "L2 implementer for small cleanup fixes inside an isolated worktree.",
+      "mode": "subagent",
+      "prompt": "Implement only the requested single-file cleanup inside the supplied worktree. Run tests. Never touch denylist paths. Output the diff.",
+      "permission": {
+        "bash": "ask",
+        "edit": "ask"
+      }
+    },
+    "verifier": {
+      "name": "verifier",
+      "description": "Checker agent for cleanup diffs. APPROVE or REJECT only.",
+      "mode": "subagent",
+      "prompt": "Review the cleanup diff against project rules. Verify scope is small and doesn't touch denylisted paths. Do not edit files. APPROVE or REJECT.",
+      "permission": {
+        "bash": "ask",
+        "edit": "deny"
+      }
+    }
+  }
+}

package/starters/post-merge-cleanup-opencode/post-merge-state.md.example

@@ -0,0 +1,10 @@
+# Post-Merge State
+Last run: 2026-06-20 09:00 UTC
+Recent merges scanned: 0
+Cleanup items: 0
+
+## Proposed Fixes
+- <!-- Small fixes proposed by the loop -->
+
+## Ticketed Debt
+- <!-- Architectural debt items ticketed for human triage -->

package/starters/post-merge-cleanup-opencode/skills/post-merge-scan/SKILL.md

@@ -0,0 +1,34 @@
+---
+name: post-merge-scan
+description: >
+  Scan recent merges to main for tech debt, TODOs, debug code, and
+  small cleanup opportunities. Produces a prioritized fix list.
+user_invocable: true
+---
+
+# Post-Merge Scan Skill
+
+You are a post-merge cleanup agent. Scan recent merges for follow-up work.
+
+## Scan Sources
+
+- Recent commits and PRs merged to main
+- `git diff HEAD~10` for left-behind debug code
+- TODO/FIXME/HACK comments in changed files
+- Lint warnings introduced by recent changes
+
+## Classification
+
+- **Small fix**: doc/comment/lint/debug — auto-fix candidate
+- **Architectural debt**: ticket for human
+- **Denylist path**: escalate to human
+
+## Output
+
+Update `post-merge-state.md` with prioritized cleanup list.
+
+## Rules
+
+- Run off-peak (evening).
+- Never auto-fix architectural debt.
+- Max 2 fix attempts per run.

package/starters/pr-babysitter-opencode/AGENTS.md

@@ -0,0 +1,18 @@
+# AGENTS.md — PR Babysitter (Opencode)
+
+## Loop Mode
+- Start in L1 report-only mode.
+- Read `pr-babysitter-state.md` before any triage.
+- Do not edit source code until the human explicitly enables L2.
+
+## Safety
+- Never force-push without explicit human opt-in.
+- Draft PRs by default; humans mark ready for review.
+- Do not resolve review threads without approval.
+- Security, auth, payments, infra, or public API changes always escalate.
+- Max 3 fix attempts per PR before handoff.
+
+## Verification
+- For L2+ changes, dispatch verifier sub-agent after implementation.
+- Run the project's documented tests before proposing a fix.
+- Check for existing PR on the same intent before pushing.

package/starters/pr-babysitter-opencode/LOOP.md

@@ -0,0 +1,27 @@
+# Loop Configuration — PR Babysitter (Opencode)
+
+## Active Loops
+
+| Pattern | Cadence | Status | Command |
+|---------|---------|--------|---------|
+| PR Babysitter | 10-15m | L1 report-only | `opencode run "Run PR babysitter triage" --agent loop-triage` via cron/systemd |
+
+## Human Gates
+- No auto-fix until L2 checklist complete.
+- Draft PRs by default; humans mark ready for review.
+- Do not resolve review threads without approval.
+- Security, auth, payments, infra changes: always human.
+
+## Worktrees
+- One worktree per fix attempt; discard after verifier REJECT.
+- Run implementer with `--dir <worktree>`.
+
+## Budget
+- Max sub-agent spawns per run: 0 (L1).
+- Max 3 fix attempts per PR before handoff.
+- Pause if token budget exceeded.
+
+## Links
+- Pattern: [pr-babysitter](../../patterns/pr-babysitter.md)
+- Example: [examples/opencode/pr-babysitter.md](../../examples/opencode/pr-babysitter.md)
+- Safety: [docs/safety.md](../../docs/safety.md)

package/starters/pr-babysitter-opencode/README.md

@@ -0,0 +1,44 @@
+# PR Babysitter — Opencode Starter
+
+Clone-and-run scaffold for the **PR Babysitter** pattern with opencode. Watch open PRs, surface blockers, and act only on safe obvious maintenance tasks.
+
+## Quick Start
+
+```bash
+npx @cobusgreyling/loop-init . --pattern pr-babysitter --tool opencode
+```
+
+Or copy manually:
+
+```bash
+cp -r starters/pr-babysitter-opencode/skills .
+cp starters/pr-babysitter-opencode/AGENTS.md .
+cp starters/pr-babysitter-opencode/LOOP.md .
+cp starters/pr-babysitter-opencode/pr-babysitter-state.md.example pr-babysitter-state.md
+cp starters/pr-babysitter-opencode/opencode.json.example opencode.json
+```
+
+Start (report-only, week 1):
+
+```bash
+opencode run \
+  "Run PR babysitter triage. Read pr-babysitter-state.md first. List PRs with red CI, stale review, merge conflicts, or unanswered review comments. Do not edit code. Update pr-babysitter-state.md." \
+  --title "PR babysitter"
+```
+
+## What's Included
+
+| File | Purpose |
+|------|---------|
+| `pr-babysitter-state.md.example` | State spine template |
+| `skills/pr-review-triage/SKILL.md` | PR-focused triage skill |
+| `AGENTS.md` | Always-on safety rules |
+| `LOOP.md` | Cadence, gates, budget |
+| `opencode.json.example` | Named agent definitions |
+
+## Next Steps
+
+- [patterns/pr-babysitter.md](../../patterns/pr-babysitter.md)
+- [examples/opencode/pr-babysitter.md](../../examples/opencode/pr-babysitter.md)
+- [docs/loop-design-checklist.md](../../docs/loop-design-checklist.md)
+- [stories/pr-babysitter-week-one.md](../../stories/pr-babysitter-week-one.md)

package/starters/pr-babysitter-opencode/opencode.json.example

@@ -0,0 +1,35 @@
+{
+  "$schema": "https://opencode.ai/config.json",
+  "agent": {
+    "pr-babysitter": {
+      "name": "pr-babysitter",
+      "description": "PR-focused triage loop. Reads pr-babysitter-state.md, watches open PRs, and reports blockers without editing code.",
+      "mode": "primary",
+      "prompt": "Read AGENTS.md, LOOP.md, pr-babysitter-state.md, and skills/pr-review-triage/SKILL.md. Watch open PRs, check CI status, review staleness, and surface blockers. Do not edit source code unless L2 is explicitly enabled.",
+      "permission": {
+        "bash": "ask",
+        "edit": "ask"
+      }
+    },
+    "implementer": {
+      "name": "implementer",
+      "description": "L2 implementer for minimal PR fixes inside an isolated worktree.",
+      "mode": "subagent",
+      "prompt": "Implement only the requested minimal fix inside the supplied worktree. Respect AGENTS.md and LOOP.md. Run documented tests. Never force-push. Draft PR by default.",
+      "permission": {
+        "bash": "ask",
+        "edit": "ask"
+      }
+    },
+    "verifier": {
+      "name": "verifier",
+      "description": "Checker agent for PR fix diffs. APPROVE or REJECT only.",
+      "mode": "subagent",
+      "prompt": "Review the supplied diff against project rules, tests, and docs/safety.md. Do not edit files. Respond with APPROVE or REJECT and concise evidence.",
+      "permission": {
+        "bash": "ask",
+        "edit": "deny"
+      }
+    }
+  }
+}

package/starters/pr-babysitter-opencode/pr-babysitter-state.md.example

@@ -0,0 +1,10 @@
+# PR Babysitter State
+Last run: 2026-06-20 09:00 UTC
+Open PRs tracked: 0
+Attempt counts: {}
+
+## Watch List
+- <!-- Add open PRs here -->
+
+## Fix History (L2+)
+- <!-- Record attempt count and outcome per PR -->

package/starters/pr-babysitter-opencode/skills/pr-review-triage/SKILL.md

@@ -0,0 +1,33 @@
+---
+name: pr-review-triage
+description: >
+  Watch open PRs, check CI status, review staleness, merge conflicts,
+  and unanswered review comments. Produces a prioritized watchlist.
+user_invocable: true
+---
+
+# PR Review Triage Skill
+
+You are a PR babysitter agent. Your job is to track open PRs and surface blockers.
+
+## Inputs
+
+- Open PRs (from `gh pr list` or GitHub MCP)
+- Prior state in `pr-babysitter-state.md`
+- CI status for each PR
+
+## Output
+
+Update `pr-babysitter-state.md` with:
+
+- PRs with red CI
+- PRs with merge conflicts
+- PRs waiting >48h for review
+- PRs with unanswered review comments
+- Top 3 actions for a human
+
+## Rules
+
+- Do not edit code in L1 mode.
+- Always check for existing PR on the same intent before pushing.
+- Security/auth/payments changes: flag for human.

package/templates/SKILL.md.loop-guard

@@ -0,0 +1,94 @@
+---
+name: loop-guard
+description: >
+  Circuit breaker for fix-capable loops. Before each iteration, append the last
+  attempt to loop-ledger.json and run loop-context --check; if it escalates,
+  stop and hand the human a clean summary instead of looping in vain.
+user_invocable: true
+---
+
+# Loop Guard (Circuit Breaker)
+
+You keep a fix loop from burning tokens on a problem it cannot solve. You wrap
+every iteration of an action skill (`minimal-fix`, `ci-triage`, `dependency-triage`, …)
+with a deterministic circuit-breaker check powered by
+[`loop-context`](https://github.com/cobusgreyling/loop-engineering/tree/main/tools/loop-context).
+
+The breaker needs no LLM call, so it is cheap enough to run on every iteration.
+
+## The ledger
+
+`loop-ledger.json` records the loop's goal, its pattern/level, and one entry per
+attempt:
+
+```json
+{ "goal": "Get failing CI green", "pattern": "ci-sweeper", "level": "L2", "attempts": [] }
+```
+
+`pattern` and `level` are seeded by `loop-init`; the breaker ignores them but the
+budget step below reads them to size `--token-budget` from real cost data.
+
+After every iteration, append what you just tried:
+
+```json
+{ "iteration": 3, "action": "patch flaky auth test", "outcome": "failure",
+  "error": "AssertionError: expected 200 got 500", "tokensUsed": 1800 }
+```
+
+`outcome` is `success | failure | noop`. Always include `error` on failures —
+that is how the breaker detects a repeated (stagnant) failure.
+
+## Size the token budget from the pattern (once per run)
+
+Don't hand-type a token cap — derive it from the pattern's realistic per-run
+cost so the breaker trips on genuine cost blowup, not a made-up number.
+[`loop-cost`](https://github.com/cobusgreyling/loop-engineering/tree/main/tools/loop-cost)
+already computes this from `patterns/registry.yaml`; read the loop's `pattern`
+and `level` straight from the ledger:
+
+```bash
+# Substitute the ledger's own pattern/level (here: ci-sweeper / L2).
+BUDGET=$(npx @cobusgreyling/loop-cost --pattern ci-sweeper --level L2 --json \
+  | node -e 'let d="";process.stdin.on("data",c=>d+=c).on("end",()=>process.stdout.write(String(JSON.parse(d).scenarios.realistic.tokensPerRun)))')
+```
+
+`scenarios.realistic.tokensPerRun` is a rounded integer, so it feeds
+`--token-budget` directly. The two tools stay independent — this is shell
+wiring, not a code dependency.
+
+## Before each iteration
+
+1. Append the previous attempt to `loop-ledger.json`.
+2. Run the breaker with the resolved budget:
+   ```bash
+   npx @cobusgreyling/loop-context --check --ledger loop-ledger.json --token-budget "$BUDGET"
+   ```
+3. Act on the exit code:
+   - **0** → continue. Optionally trim the next prompt first:
+     `npx @cobusgreyling/loop-context --inject --ledger loop-ledger.json`
+   - **2** → **STOP.** The breaker tripped — same error N× in a row, too many
+     consecutive failures, the token budget, or the iteration cap. Do not retry.
+
+## On escalate (exit 2)
+
+1. Capture a clean, pruned summary for the human:
+   ```bash
+   npx @cobusgreyling/loop-context --inject --ledger loop-ledger.json > escalation.md
+   ```
+2. Write the escalation into STATE.md High Priority (or open an issue).
+3. Exit the loop. A human decides the next step.
+
+## Rules
+
+- Never widen thresholds just to keep looping — escalation is a feature, not a failure.
+- Never edit the ledger to hide a repeated error; the breaker exists to catch it.
+- Defaults: 3× same error, 5 consecutive failures, 10 iterations. Tune with
+  `--stagnation`, `--no-progress`, `--max-iterations`, `--token-budget`.
+
+## Interaction with other skills
+
+- `minimal-fix` / `ci-triage` — record each attempt's outcome + error in the ledger.
+- `loop-verifier` — a verifier rejection is a `failure`; log it so repeats trip the breaker.
+- `loop-constraints` — honors "escalate after N attempts"; this skill makes it mechanical.
+- `loop-budget` — the per-run `--token-budget` here comes from loop-cost's
+  realistic estimate; loop-budget.md still governs the *daily* cap across runs.

package/templates/loop-constraints.md

@@ -18,6 +18,7 @@
 - Never disable tests to make CI green
 - Never refactor unrelated code — one fix per run
 - Max 3 fix attempts per item; escalate after
+- Enforce the attempt limit mechanically: log each try to `loop-ledger.json` and run `loop-context --check` before retrying (see the `loop-guard` skill)
 
 ## Communication
 - Always tell me what you're about to do before doing it