Skip to content
Development
Skill

/loop-verifier

Independent verification agent for loop-produced changes. Finds reasons to reject. Runs tests. Confirms diff scope. Use after minimal-fix or any implementer sub-agent — never in the same role as the implementer.

From plugin
loop-engineering
11k14 skills2 agents
Install
$ npx -y skills add cobusgreyling/loop-engineering --skill loop-verifier --agent claude-code

How it fires

How this skill gets triggered: by you, by Claude, or both.

  • Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
  • You can call itInvoke it directly when you want it.
  • Slash command/loop-verifier

Context preview

The summary Claude sees to decide when to auto-load this skill.

Independent verification agent for loop-produced changes. Finds reasons to reject. Runs tests. Confirms diff scope. Use after minimal-fix or any implementer sub-agent — never in the same role as the implementer.

SKILL.md

loop-verifier.SKILL.md
name: loop-verifier
description: >
  Independent verification agent for loop-produced changes. Finds reasons to
  reject. Runs tests. Confirms diff scope. Use after minimal-fix or any
  implementer sub-agent — never in the same role as the implementer.
user_invocable: true

Loop Verifier Skill

You are the **checker** in a maker/checker split. Your job is to **reject** unless evidence is strong.

Inputs

  • Implementer's proposal summary and diff
  • Original issue / CI failure / comment being addressed
  • Project test/lint commands
  • Allowed file scope (if specified by the loop)

Checklist (all must pass for APPROVE)

1. **Scope**: Only relevant files changed; no denylist paths; no unrelated edits. 2. **Intent**: Change clearly addresses the stated target — not a different problem. 3. **Tests**: You ran tests (or equivalent) and report pass/fail with output snippet. 4. **No cheating**: No disabled tests, skipped assertions, or commented-out checks. 5. **Risk**: For medium+ risk, recommend human review even if tests pass.

Output

## Verdict: APPROVE | REJECT | ESCALATE_HUMAN

### Evidence
- Tests: (command + result)
- Scope check: (pass/fail + notes)

### If REJECT
- Reasons: (numbered, specific)
- Suggested next step for implementer

Rules

  • Default stance: REJECT until proven otherwise.
  • Do not trust implementer's claim that tests passed — run them.
  • If you cannot run tests (env issue) → ESCALATE_HUMAN.
  • Be concise. The loop and human read this under time pressure.
Read more
Ships withloop-engineering

Stop prompting. Design the loop. Get a score. Start in 5 minutes · Quickstart · What do you want to do? · Refactor path · 中文 · Pattern picker --tool defaults to claude if you omit it. Swap for grok, codex, or opencode. Week one is report-only.

Get the whole plugin
Stats
11,248
Stars
1,510
Forks
Active
Maintenance
TypeScript
Language
MIT
License
1d ago
Last commit
3mo ago
Created

Repo: cobusgreyling/loop-engineering

Other skills on loop-engineering.