Reviewloop

What it does

When your agent uses it

• Fixes all actionable comments
• The user wants to fully optimize a PR against all automated code review feedback

Example prompts

• “/reviewloop”

Requirements

• Compatibility (from SKILL.md): Requires git, gh (GitHub CLI) authenticated, and at least one review bot installed on the repo.
• Pre-approved tools (allowed-tools): Bash(gh:*), Bash(git:*), Bash(sleep:*)

Workflow steps

5 steps, taken from the step headings in SKILL.md.

1. 1Identify the PR
2. 2Discover active review bots
3. 3Review bot loop
4. 4Final CI check
5. 5Report

What it can do on your machine

Read from SKILL.md and the folder at commit 04da760. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Bash(gh:*)
  • Bash(git:*)
  • Bash(sleep:*)

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Shell commands in SKILL.md call:

  • gh
  • git

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

• Network

  No URLs in SKILL.md. Its commands use gh and 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.

• Compatibility

  Requires git, gh (GitHub CLI) authenticated, and at least one review bot installed on the repo.

  From compatibility in the SKILL.md frontmatter.

Context cost

Reviewloop loads about 2.3k tokens when it runs, and up to ~2.6k if it reads all its reference files. Until then it costs about 84 tokens; SKILL.md has 907 words of instructions outside code blocks.

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

~84

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

~2.3k

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

~2.6k

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 ankitvgupta/exo at commit 04da760, republished under its MIT licence (© ankitvgupta). 907 words, ~2,295 tokens.

name

reviewloop

description

Iteratively improves a PR until all review bots (Greptile, Devin, and others) are satisfied with zero unresolved comments, then fixes any CI failures. Triggers reviews, fixes all actionable comments, pushes, re-triggers, and repeats. Use when the user wants to fully optimize a PR against all automated code review feedback.

allowed-tools

Bash(gh:*), Bash(git:*), Bash(sleep:*)

compatibility

Requires git, gh (GitHub CLI) authenticated, and at least one review bot installed on the repo.

license

MIT

metadata.author

ankitvgupta

metadata.version

2.0

gh pr view --json number,headRefName -q '{number: .number, branch: .headRefName}'

gh api repos/{owner}/{repo}/pulls/<PR_NUMBER>/reviews
gh api repos/{owner}/{repo}/pulls/<PR_NUMBER>/comments

git push

gh pr checks <PR_NUMBER>

gh api repos/{owner}/{repo}/pulls/<PR_NUMBER>/reviews --paginate

gh api repos/{owner}/{repo}/pulls/<PR_NUMBER>/comments --paginate

# First page (no cursor)
gh api graphql -f query='
{
  repository(owner: "OWNER", name: "REPO") {
    pullRequest(number: PR_NUMBER) {
      reviewThreads(first: 100) {
        pageInfo { hasNextPage endCursor }
        nodes {
          id
          isResolved
          comments(first: 5) {
            nodes { body path line author { login } createdAt }
          }
        }
      }
    }
  }
}'

# If pageInfo.hasNextPage is true, fetch next page:
gh api graphql -f query='
query($cursor: String!) {
  repository(owner: "OWNER", name: "REPO") {
    pullRequest(number: PR_NUMBER) {
      reviewThreads(first: 100, after: $cursor) {
        pageInfo { hasNextPage endCursor }
        nodes {
          id
          isResolved
          comments(first: 5) {
            nodes { body path line author { login } createdAt }
          }
        }
      }
    }
  }
}' -F cursor="<endCursor from previous page>"

gh api graphql -f query='
mutation {
  t1: resolveReviewThread(input: {threadId: "ID1"}) { thread { isResolved } }
  t2: resolveReviewThread(input: {threadId: "ID2"}) { thread { isResolved } }
}'

git add -A
git commit -m "address review bot feedback (reviewloop iteration N)"
git push

gh pr checks <PR_NUMBER>

Reviewloop complete.
  Review iterations: 2
  CI fix attempts:   1
  Bots satisfied:    Greptile (5/5), Devin (0 unresolved)
  CI status:         passing
  Resolved:          12 comments
  Remaining:         0

Reviewloop stopped after 5 review iterations + 3 CI attempts.
  Bots satisfied:    Greptile (5/5)
  Bots unsatisfied:  Devin (2 unresolved comments)
  CI status:         failing (lint)
  Resolved:          10 comments
  Remaining:         2

Remaining issues:
  - [Devin] src/auth.ts:45 — "Consider rate limiting this endpoint"
  - [Devin] src/db.ts:112 — "Missing index on user_id column"
  - [CI] lint: unused import in src/utils.ts:3

© ankitvgupta, 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 .claude/skills/reviewloop of ankitvgupta/exo.

• SKILL.md
• references/graphql-queries.md

Open the folder on GitHubat commit 04da760