How do I install the Loop Engineer skill?

Run npx skillmds@latest add willianbs/loop-engineer in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Loop Engineer safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Loop Engineer?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Loop Engineer free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Loop Engineer?

willianbs (@willianbs) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Loop Engineer by willianbs — Agent Skill

Name: Loop Engineer
Author: willianbs

Loop Engineer

Runs recurring agent loops: fixed or dynamic intervals, CI/PR babysitting, and re-invoking prompts/skills until stop criteria. Use for watch-until-done work. Emits LOOP_PLAN / LOOP_STATUS. Never starts unbounded loops without stop conditions or spam-notifies without signal.

willianbs 50e2561 2 files · 4.1 KB Updated Sep 17, 2026

File contents

Purpose

Arm a controlled loop that re-runs a prompt or skill path on an interval (or dynamically) until success, failure, timeout, or user stop.

When to Use / When NOT to Use

Use when: babysit CI/PR checks; watch deploys; poll until green/red; recurring /loop style work; long-running verification.

Do not use when: one-shot tasks; tight interactive coding sessions where a loop adds noise; production mutate-on-timer without explicit approval.

Preconditions

Clear work unit (prompt or skill + args) and stop criteria. If interval omitted, use dynamic mode with rationale.

Inputs / Outputs

Inputs: prompt/skill to run, interval or dynamic, stop criteria, optional gh/CI identifiers.

Outputs: LOOP_PLAN then recurring LOOP_STATUS updates.

Upstream / Downstream

Upstream: engineering-os, quality-gate, user.

Downstream: any skill named in the loop body; pr-generator; incident-commander if loop detects sev.

Core Principles

Every loop needs stop criteria (success/fail/timeout/max ticks).
Prefer signal-based wakes (CI status, log sentinel) over blind sleep when possible.
One loop per purpose; do not duplicate existing loops.
First run immediate; then interval — avoid double-fire on start.
Status updates are short; full work only on tick.
Destructive actions require explicit user approval each time (or pre-approval scope).
Stop cleanly and report why.

Process

Parse: interval (30s/5m/2h) or dynamic; body prompt/skills; stop criteria.
Emit LOOP_PLAN — purpose, interval, stop, max ticks, sentinel.
Check for existing matching loop; reuse or stop duplicates.
Arm background waiter / poller as environment allows; or instruct host loop tool.
Run body once immediately; record LOOP_STATUS.
On each tick: run body; evaluate stop; update LOOP_STATUS.
On stop: final status, summary of changes, artifacts produced.

Presets

babysit-pr — poll checks until success/fail
babysit-ci — watch workflow run
until-qg-pass — re-run quality-gate path
custom — user prompt

Evidence Requirements

Tick times, commands, CI URLs, stop reason. No fake “still running” without checking.

Stop Conditions / Failure Modes

Condition	Action
No stop criteria	Refuse to arm
Max ticks / timeout	Stop; LOOP_STATUS failed/timeout
User says stop	Stop immediately
Body returns Block Critical	Stop and escalate

Severity + Confidence

Escalate to incident-commander if loop observes prod SEV signals.

Output Contract

## LOOP_PLAN
Purpose: ...
Interval: ... | dynamic
Body: skill/prompt
Stop criteria: ...
Max ticks: ...
## LOOP_STATUS
Tick: N
Observed: ...
Decision: continue | stop
Stop reason: ...

Handoffs

engineering-os, quality-gate, pr-generator, incident-commander.

Never

Never arm infinite loops without max ticks/timeout.
Never force-push or prod-mutate on a timer without explicit scope.
Never spam full reports every tick — delta only.

---name: loop-engineerdescription: Runs recurring agent loops: fixed or dynamic intervals, CI/PR babysitting, and re-invoking prompts/skills until stop criteria. Use for watch-until-done work. Emits LOOP_PLAN / LOOP_STATUS. Never starts unbounded loops without stop conditions or spam-notifies without signal.---# PurposeArm a controlled loop that re-runs a prompt or skill path on an interval (or dynamically) until success, failure, timeout, or user stop.# When to Use / When NOT to Use**Use when:** babysit CI/PR checks; watch deploys; poll until green/red; recurring `/loop` style work; long-running verification.**Do not use when:** one-shot tasks; tight interactive coding sessions where a loop adds noise; production mutate-on-timer without explicit approval.# PreconditionsClear work unit (prompt or skill + args) and stop criteria. If interval omitted, use dynamic mode with rationale.# Inputs / Outputs**Inputs:** prompt/skill to run, interval or dynamic, stop criteria, optional gh/CI identifiers.**Outputs:** `LOOP_PLAN` then recurring `LOOP_STATUS` updates.# Upstream / Downstream**Upstream:** engineering-os, quality-gate, user.**Downstream:** any skill named in the loop body; pr-generator; incident-commander if loop detects sev.# Core Principles1. Every loop needs stop criteria (success/fail/timeout/max ticks).2. Prefer signal-based wakes (CI status, log sentinel) over blind sleep when possible.3. One loop per purpose; do not duplicate existing loops.4. First run immediate; then interval — avoid double-fire on start.5. Status updates are short; full work only on tick.6. Destructive actions require explicit user approval each time (or pre-approval scope).7. Stop cleanly and report why.# Process1. Parse: interval (`30s`/`5m`/`2h`) or dynamic; body prompt/skills; stop criteria.2. Emit LOOP_PLAN — purpose, interval, stop, max ticks, sentinel.3. Check for existing matching loop; reuse or stop duplicates.4. Arm background waiter / poller as environment allows; or instruct host loop tool.5. Run body once immediately; record LOOP_STATUS.6. On each tick: run body; evaluate stop; update LOOP_STATUS.7. On stop: final status, summary of changes, artifacts produced.## Presets- `babysit-pr` — poll checks until success/fail- `babysit-ci` — watch workflow run- `until-qg-pass` — re-run quality-gate path- `custom` — user prompt# Evidence RequirementsTick times, commands, CI URLs, stop reason. No fake “still running” without checking.# Stop Conditions / Failure Modes| Condition | Action ||-----------|--------|| No stop criteria | Refuse to arm || Max ticks / timeout | Stop; LOOP_STATUS failed/timeout || User says stop | Stop immediately || Body returns Block Critical | Stop and escalate |# Severity + ConfidenceEscalate to incident-commander if loop observes prod SEV signals.# Output Contract```## LOOP_PLANPurpose: ...Interval: ... | dynamicBody: skill/promptStop criteria: ...Max ticks: ...## LOOP_STATUSTick: NObserved: ...Decision: continue | stopStop reason: ...```# Handoffs**engineering-os**, **quality-gate**, **pr-generator**, **incident-commander**.# Never- Never arm infinite loops without max ticks/timeout.- Never force-push or prod-mutate on a timer without explicit scope.- Never spam full reports every tick — delta only.

Frequently asked questions