claude-code-power-config: Skill for Claude Code

.claude/skills/pr-ci-review/SKILL.md

pr-ci-review is a skill for Claude Code from AlexisBalayre/claude-code-power-config. It costs 48 tokens per session (5,240 once invoked), scanned A, original, MIT.

A structured code-review process for local changes or a pull request. A pull request is a proposed set of code changes waiting to be reviewed before merging.

In plain words
What is it for?
Use it to review a pull request or local changes, run the required pre-checks, coordinate focused reviewers, consolidate findings, and optionally apply fixes.
Why use it?
It checks relevant correctness and security risks in the changed code and records the review results in a format that automated checks can use.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md; mentions subagents; mentions AGENTS.md.

This is AlexisBalayre/claude-code-power-config's own configuration. It tells Claude Code how to work on claude-code-power-config itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-code-power-config configures →

Reuse

Borrowing it

Nothing to install: this file belongs to AlexisBalayre/claude-code-power-config. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/AlexisBalayre/claude-code-power-config/main/.claude/skills/pr-ci-review/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/AlexisBalayre/claude-code-power-config

Made for: Claude Code.

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 pr-ci-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/alexisbalayre/claude-code-power-config/pr-ci-review/github.svg)](https://agentmods.dev/skills/alexisbalayre/claude-code-power-config/pr-ci-review)
Your own site
<a href="https://agentmods.dev/skills/alexisbalayre/claude-code-power-config/pr-ci-review"><img src="https://agentmods.dev/badge/skills/alexisbalayre/claude-code-power-config/pr-ci-review/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for pr-ci-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/alexisbalayre/claude-code-power-config/pr-ci-review"><img src="https://agentmods.dev/badge/skills/alexisbalayre/claude-code-power-config/pr-ci-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,240 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00048 $0.05240
Opus 5 $0.00024 $0.02620
Sonnet 5 $0.00010 $0.01048
Haiku 4.5 $0.00005 $0.00524

Measured 11d ago against content hash de4ea3c8eb7b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

pr-ci-review 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 11d 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.

.claude/skills/pr-ci-review/SKILL.md · 157 lines

How it starts

The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Code Review Protocol

Provide a context-aware code review of local changes or a pull request, across six reviewer areas, and emit a structured record of everything it considered. You orchestrate: you steer, gate, consolidate, and act. You do NOT review code yourself; the area subagents do.

The governing rule is spend only where it buys recall. Deterministic tooling and the human in the loop are free, so lean on them first and spawn an agent only when judgment is the thing missing. Recall comes from the deterministic suite plus the correctness and security reviewers; almost everything else is a cut.

Setup: the CI paths (--json-schema, the review-metrics record, the poster) assume your own CI wiring — a workflow whose preflight checks out the PR head and resolves the mode, that invokes /pr-ci-review with the PR named in prose plus a schema, appends each run's record to a ci/review-metrics orphan branch, and renders/posts the record with a poster script. This template ships no workflow; without one, the local report / --fix paths work unchanged.

Review Constraints

  • Grounded, not speculative: every finding is grounded in the actual changed code. No speculation; a false positive erodes trust.
  • Tag by severity, not by whether to post: tag each finding important (fix before merge), nit (real but minor), or pre-existing (predates this diff).
  • Record-all, rank by display: the structured record captures every confirmed finding plus the refuted ones, and CI renders all of it: important findings as inline comments on the diff, nit, pre-existing, and refuted findings in collapsed sections of the review body. You do not do the posting: the record is not a companion to the comments, it is what they are made from. A sub-important finding's description is therefore read by the author, not only the retro; write it as a self-contained one-liner.
  • Leave linters alone: do not raise anything Biome or tsc already catches; that is noise, not a finding.

Read the full file on GitHub · 157 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. 11d ago First seen · 157 lines · 48 tokens per session scan A de4ea3c8eb7b

Subscribe to this mod's changes

pr-ci-review is a skill published in the GitHub repository AlexisBalayre/claude-code-power-config (2 stars, last pushed 1mo ago), licensed MIT. It adds 48 tokens to every session and 5,240 once invoked, about $0.0002 per session on Opus 5. 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.

Related

Other skills, from other repositories

verify-implementation

A workflow that runs a project’s verification skills to produce a report on coding patterns, architecture rules, and project conventions. It is intended for work after implementation, before a pull request, or during code review.

sangrokjung/claude-forge · 37 tokens

review-loop

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"…

sangrokjung/claude-forge · 100 tokens

frontend-code-review

Trigger when the user requests a review of frontend files (e.g., .tsx, .ts, .js). Support both pending-change reviews and focused file reviews while applying the checklist rules.

sangrokjung/claude-forge · 42 tokens

go-code-reviewer

Review Go code with a defect-first approach using repository policy (constitution.md first, then AGENTS.md fallback). Use for code review, PR review, quality checks, risk analysis, and regression detection.

johnqtcg/awesome-skills · 45 tokens

go-review-lead

Orchestrate a comprehensive Go code review by triaging code changes, dispatching vertical review skills (security, concurrency, error, logic, performance, quality, test, observability) as parallel agents, then consolidating results into a unified report. Use for full Go PR review or comprehensive code review. Replaces…

johnqtcg/awesome-skills · 80 tokens

security-review

A code-security review guide that checks code changes, pull requests, or services for risks an attacker could exploit.

johnqtcg/awesome-skills · 164 tokens