verifier
Subagent "verifier" from Archive228/loopkit: Reviews a diff against the goal spec assuming the code is broken.
Template by Archive228
Install
Works with Claude Code. Read the repository before you give any tool access to your data.
curl -fsSL https://raw.githubusercontent.com/Archive228/loopkit/main/.claude/agents/verifier.md -o verifier.md
Read it and adapt it to your project before use.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: code-review
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
What's in it
A Claude Code subagent: a Markdown file with frontmatter that defines a specialised helper agent and the tools it may use.
- For
- Claude Code
- Length
- 11 lines
- File
.claude/agents/verifier.md- name
- verifier
- model
- haiku
- tools
- Read, Grep, Bash
- description
- Reviews a diff against the goal spec assuming the code is broken. Invoke after every code change.
First lines (shown under the repo's MIT license)
---
name: verifier
description: Reviews a diff against the goal spec assuming the code is broken. Invoke after every code change.
model: haiku
tools: [Read, Grep, Bash]
---
You are a verifier. Read the goal spec (PROMPT.md). Read the diff. Assume it is broken.
Check the 11 "fake done" shortcuts (see skills/adversarial-verify). Return JSON:
`{"passes": bool, "failures": [{"line": int, "shortcut": str, "why": str}]}`.
Do not propose fixes. Do not run code. Do not be polite.Signals
- Stars
- 755
- Forks
- 124
- Open issues
- 0
- Last commit (this folder)
- Jun 29, 2026 (4 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/Archive228/loopkit
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from Archive228
- 0.701score
structured-output
Archive228
Get JSON out of the model reliably.
SkillCFreshness: C★ 755Claude Code +9 - 0.701score
using-loopkit
Archive228
Use when starting any conversation in a loopkit-enabled project - establishes how to find and use loopkit's 49 skills, requiring skill invocation before ANY…
SkillCFreshness: C★ 755Claude Code +9 - 0.701score
hitl-escalate
Archive228
Escalate blocked runs to a human via configured channel or fallback to BLOCKED.md and exit the loop.
SkillCFreshness: C★ 755Claude Code +9 - 0.701score
prompt-caching
Archive228
Cache the parts of the prompt that don't change so a long-running loop stops paying full price on every turn.
SkillCFreshness: C★ 755Claude Code +9 - 0.698score
harness-stripping
Archive228
Systematically remove one harness component at a time and measure impact, killing scaffolding that no longer earns its complexity.
SkillCFreshness: C★ 755Claude Code +9 - 0.698score
broken-window-check
Archive228
Before picking new work, smoke-test the last "completed" feature.
SkillCFreshness: C★ 755Claude Code +9
Cite this page
verifier. Agent Mart. https://agentmart.dev/templates/archive228-loopkit-verifier (last updated 2026-10-24)