claude

claude is an agent for coding agents from mdelapenya/coding-skills. It costs 0 tokens per session (542 once invoked), scanned A, original, MIT.

A guide for running the pull-request reviewer from Claude Code, a coding agent that can work with GitHub and GitLab repositories. It describes commands for reviewing a checked-out branch or a specified pull request.

In plain words
What is it for?
Use it to review a current branch, a pull-request number, URL, or repository shorthand, and to repeat the review with Claude Code’s loop command.
Why use it?
It removes uncertainty about how to provide the pull request and how repeated reviews work in Claude Code.

Agent

Part of the coding-skills plugin — 5 skills, 5 agents shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/mdelapenya/coding-skills/claude
Clone the repo
git clone --depth 1 https://github.com/mdelapenya/coding-skills

Or install coding-skills, the plugin that ships this one along with the rest of its 5 skills, 5 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for claude

README.md
[![agentmods](https://agentmods.dev/badge/agents/mdelapenya/coding-skills/claude.svg)](https://agentmods.dev/agents/mdelapenya/coding-skills/claude)
Your own site
<a href="https://agentmods.dev/agents/mdelapenya/coding-skills/claude"><img src="https://agentmods.dev/badge/agents/mdelapenya/coding-skills/claude.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 542 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00542
Opus 5 $0.00000 $0.00271
Sonnet 5 $0.00000 $0.00108
Haiku 4.5 $0.00000 $0.00054

Measured 3d ago against content hash c9d56a0bc8aa, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

claude scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/pr-reviewer/references/agents/claude.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Code

Topic file for running pr-reviewer from inside Claude Code.

Fetch tooling

Claude Code has the Bash tool. The skill drives the fetch itself using gh (GitHub) or glab (GitLab) — you do not need to pre-load anything before invoking /pr-reviewer. Two ways to invoke it:

  • From inside the matching repo:
    • /pr-reviewer — review the currently checked-out PR branch
    • /pr-reviewer <num> — clone PR <num> from the current repo's remote into a temp dir and review it
  • From a barebones directory (no git repo needed):
    • /pr-reviewer https://github.com/<org>/<repo>/pull/<n> — clones into cwd if it is empty, otherwise into temp
    • /pr-reviewer <org>/<repo>#<n> (GitHub) or <group>/<project>!<n> (GitLab) shorthand — same behavior

Looping primitive

Claude Code ships a /loop slash command (verified at the time of writing):

/loop /pr-reviewer [<num>]

This re-invokes the skill repeatedly, model-paced (omit the interval). Each iteration:

  1. Re-establishes PR context (re-fetches via gh/glab) and reuses the existing clone, refreshing it with git fetch && git reset --hard.
  2. Runs one full round of the skill.
  3. Appends to <base-dir>/findings.md.

Recommended flow:

  1. Run /pr-reviewer [<num>] once to produce round 1.
  2. If round 1 finishes without converging and you want iteration:
    /loop /pr-reviewer [<num>]
    
  3. The loop exits naturally when:
    • The skill writes converged: true to findings.md
    • The skill reaches --rounds=N
    • The user stops the loop

Timed loop (PR still moving)

If the author is actively pushing commits, use a timed loop so each iteration re-fetches at a sensible cadence:

/loop 10m /pr-reviewer [<num>]

Posting the final report

The skill prints the report by default. To post it on GitHub:

gh pr review <pr-number> --comment --body-file <path-the-skill-printed>

Always confirm with the user before posting — a review is visible to others.

Read the full file on GitHub · 59 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 3d ago First seen · 59 lines · 0 tokens per session scan A c9d56a0bc8aa

Subscribe to this mod's changes

claude is an agent published in the GitHub repository mdelapenya/coding-skills (2 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 542 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.