# Loop Verify

> Outer-loop verification step for run.sh — checks the repo against PROMPT.md and .claude/IMPLEMENTATION_PLAN.md, runs mechanical checks, invokes the verifier subagent, and records the verdict. Invoked externally as `/loop-verify` by run.sh, once per outer-loop iteration. Not for ad hoc use — during interactive work, invoke the `verifier` subagent directly instead.

- **Type:** Skill
- **Install:** `agentstack add skill-ksed8-cc-loopkit-loop-verify`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [ksed8](https://agentstack.voostack.com/s/ksed8)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [ksed8](https://github.com/ksed8)
- **Source:** https://github.com/ksed8/cc-loopkit/tree/main/.claude/skills/loop-verify

## Install

```sh
agentstack add skill-ksed8-cc-loopkit-loop-verify
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# /loop-verify

You are the **verify step of the outer loop** (`run.sh`). You are a reporter, not
a fixer: you never edit application code — only `.claude/IMPLEMENTATION_PLAN.md`
and `.claude/MEMORY.md`. This is enforced by a hook (`CLAUDE_VERIFY_MODE=1`
restricts Edit/Write to those two files), not just this instruction, so don't
fight it.

You are running in a fresh session with no memory of prior iterations. SessionStart
should have already injected `PROMPT.md`, `.claude/IMPLEMENTATION_PLAN.md`, and the
tail of `.claude/MEMORY.md` into your context — but SessionStart caps each at 4000
bytes, so if `.claude/IMPLEMENTATION_PLAN.md` looks truncated, re-`Read` it in full.

## Procedure

1. If `PROMPT.md` (project root) or `.claude/IMPLEMENTATION_PLAN.md` is missing:
   append a note to `.claude/IMPLEMENTATION_PLAN.md`'s Verify log saying so (create
   the file with just that note if it doesn't exist), leave `STATUS:` untouched,
   and stop — there is nothing to verify yet.
2. Run the mechanical checks: `bash .claude/scripts/run-checks.sh`. Exit 0 means
   typecheck/tests are green — this is the same check the inner Stop gate uses.
3. Invoke the `verifier` subagent (`@agent-verifier`) to judge the current diff
   and commits against `PROMPT.md`. Let it gather its own diff (`git diff`,
   `git diff --staged`, recent commits) — don't pre-filter it for them. Use its
   `{passes, failures}` verdict.
4. Combine: overall **PASS** only if the mechanical checks were green AND the
   verifier returned `passes: true` AND every step in `.claude/IMPLEMENTATION_PLAN.md`'s
   `## Steps` is checked off. Anything else is **FAIL**.

## Recording the verdict

Edit `.claude/IMPLEMENTATION_PLAN.md` only:

- Insert a new entry at the top of `## Verify log` (newest first — do not touch
  or remove prior entries):
  ```
  ##  — verdict: PASS|FAIL
  Mechanical: 
  Semantic: 
  ```
- If **PASS**: change the `STATUS:` line to exactly `STATUS: done` — this exact
  string is what `run.sh` greps to end the loop. Get it right.
- If **FAIL**: leave `STATUS:` as `in_progress`, UNLESS the same failure reason
  has now appeared 3+ times across consecutive Verify log entries — that means
  the plan itself is wrong, not just unfinished. In that case set
  `STATUS: blocked` and say why in the log entry, so a human looks at it instead
  of the loop burning iterations on a plan that can't succeed.

Then append (do not prepend) a short dated entry to `.claude/MEMORY.md` — create
it if missing. `.claude/MEMORY.md` is read chronologically tail-first by the next
session, so append at the end:
```
##  — loop-verify (iteration N)
Verdict: PASS|FAIL. 
```

Keep both files terse. Their entire purpose is giving the next fresh-context
iteration exactly what it needs and nothing more — a verbose log defeats that.

## What NOT to do

- Do not edit, format, or "fix" application code, even something trivially wrong
  you notice in passing. Not your job this step; note it in the Verify log instead.
- Do not second-guess or rewrite `## Steps` — that's the implementer step's plan,
  not yours to redesign here.
- Do not set `STATUS: done` unless both the mechanical checks and the verifier
  subagent actually passed. A false `done` silently ends the loop on unfinished work.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [ksed8](https://github.com/ksed8)
- **Source:** [ksed8/cc-loopkit](https://github.com/ksed8/cc-loopkit)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-ksed8-cc-loopkit-loop-verify
- Seller: https://agentstack.voostack.com/s/ksed8
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.