Review Loop

What it does

Example prompts

• “review loop”
• “adversarial review”
• “independent review”
• “/review-loop”

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

1. 1Implement. Keep the change inside the scope you declared. Unrelated cleanup that arrives in
2. 2Produce evidence before dispatch. Run the targeted tests and, when the change has a surface a
3. 3Dispatch a fresh checker. Use the Task/Agent tool to spawn adversarial-reviewer in its own
4. 4Read the verdict, not the tone. A checker that praises the change but lists a HIGH finding
5. 5Fix and re-dispatch. Every round gets a checker with a fresh context. Reusing the previous
6. 6Stop when a current APPROVE exists for the code as it stands, backed by evidence from that

What it can do on your machine

Read from SKILL.md and the folder at commit 34d881d. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • git

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Review Loop loads about 1.5k tokens when it runs, and up to ~2.1k if it reads all its reference files. Until then it costs about 111 tokens; SKILL.md has 789 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~111

When it runs · the whole SKILL.md, loaded when a task matches

~1.5k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~2.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from sangrokjung/claude-forge at commit 34d881d, republished under its MIT licence (© sangrokjung). 789 words, ~1,485 tokens.

name

review-loop

description

Run the adversarial verification loop — implement, then hand the change to a fresh checker that did not write it, fix what it finds, and re-dispatch until APPROVE. Use before claiming any behavioural change is done, and on requests like "review loop", "adversarial review", "independent review", "get this verified", "is this actually done", "maker checker", "second pair of eyes on this change". Not for prose, docs or typo edits.

maker implements → targeted test / real-surface QA → fresh checker
     ↑                                                    │
     └────────── REQUEST_CHANGES ← findings ──────────────┘
                                                          │
                                          APPROVE on current code → done

© sangrokjung, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (references) in skills/review-loop of sangrokjung/claude-forge.

• SKILL.md
• references/convergence-detection.md

Open the folder on GitHubat commit 34d881d