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

.claude/agents/README.md

README is an agent for Claude Code from AlexisBalayre/claude-code-power-config. It costs 0 tokens per session (806 once invoked), scanned A, original, MIT.

A catalogue of helper agents that can inspect a codebase and return short findings to the main coding conversation. Some agents start automatically when their described trigger matches.

In plain words
What is it for?
It helps check coding conventions, database changes, security risks, and system architecture questions. The listed agents only read files, except the security reviewer, which can also run shell commands.
Why use it?
It keeps detailed checks from filling the main conversation while making specialist reviews available at relevant points.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: 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/agents/README.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 README

README.md
[![agentmods](https://agentmods.dev/badge/agents/alexisbalayre/claude-code-power-config/readme.svg)](https://agentmods.dev/agents/alexisbalayre/claude-code-power-config/readme)
Your own site
<a href="https://agentmods.dev/agents/alexisbalayre/claude-code-power-config/readme"><img src="https://agentmods.dev/badge/agents/alexisbalayre/claude-code-power-config/readme.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 806 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 $0.00000 $0.00806
Opus 5 $0.00000 $0.00403
Sonnet 5 $0.00000 $0.00161
Haiku 4.5 $0.00000 $0.00081

Measured 7d ago against content hash a0b4f65dcb3b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

README 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 7d 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/agents/README.md · 39 lines

How it starts

The opening of the file, as written. The whole thing — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent catalog

Subagents run in their own context window and return only a summary, so deep analysis never bloats the main conversation.

Proactive agents

Claude dispatches these automatically when the trigger matches (each is described "Use PROACTIVELY"); you can also force one — e.g. "run the security-reviewer on these changes." They are read-only (no edits).

Agent When to use Model · tools
convention-checker Before a commit, or after editing ≥3 files across apps//services//packages/. Fast audit against docs/conventions/*. Haiku · Read/Glob/Grep
migration-reviewer After editing packages/acme-db/src/schema/** or running pnpm db:generate. Checks schema + migration safety and backwards-compatibility. Sonnet · Read/Glob/Grep
security-reviewer After editing auth, API routes, WebSocket handlers, forms, or secret handling. Checks injection, broken access control, secrets exposure, OWASP Top 10. Opus · Read/Glob/Grep/Bash
architecture-explainer A why/how question about service boundaries, data flow, or cross-service interactions. Answers grounded in docs/, never invented. Sonnet · Read/Glob/Grep

Dispatched agents

These are workers for a specific skill or hook, not proactive triggers. The review-* family is spawned (relevance-gated, model-tiered) by the pr-ci-review skill; comment-pruner is dispatched by the comment-pruner.sh Stop hook.

Agent What it does Model · tools
comment-pruner Prunes low-value comments added in the current session, delete-when-uncertain, with a hard floor for tooling directives (@ts-expect-error, eslint-disable, …). The one agent here that edits. Also usable manually for a repo-wide sweep. Sonnet · Read/Edit/Grep/Glob/Bash
review-context Spec/protocol contradictions and infrastructure anti-patterns, each finding grounded in the contract it breaks. Sonnet · Read/Glob/Grep/Bash
review-conventions Audits changed files against docs/conventions/*, accepted ADRs, and AGENTS.md, quoting the exact rule violated. Sonnet · Read/Glob/Grep/Bash
review-correctness Logic/behavior defects deterministic tooling can't catch, including silent regressions on the surface tests don't cover. Opus · Read/Glob/Grep/Bash
review-docs Accuracy and usefulness of prose a change introduces; strict on noise comments and stale docs. Sonnet · Read/Glob/Grep/Bash
review-maintainability Structural regressions — wrong layer, duplication, needless indirection — each with a citable mechanism. Sonnet · Read/Glob/Grep/Bash
review-security Real, reachable security issues at trust boundaries, cross-referenced against the threat model. Opus · Read/Glob/Grep/Bash
review-validator Adversarial gate: tries to refute each finding against the actual code before it is posted or auto-fixed. Opus · Read/Glob/Grep/Bash

Read the full file on GitHub · 39 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. 7d ago First seen · 39 lines · 0 tokens per session scan A a0b4f65dcb3b

Subscribe to this mod's changes

README is an agent published in the GitHub repository AlexisBalayre/claude-code-power-config (2 stars, last pushed 27d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 806 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.

Related

Other agents, from other repositories

architect

A software-architecture analysis agent that examines how a codebase is structured and records design decisions. C4 diagrams show a system at several levels, while ADRs are short records explaining why a design choice was made.

sangrokjung/claude-forge · 112 tokens

code-reviewer

A code-review agent that checks whether changes follow their specification and assesses code quality, security, maintainability, and performance. It reports findings with severity levels and file-and-line references.

sangrokjung/claude-forge · 96 tokens

planner

An agent that creates plans for complex coding, architecture, or multi-step refactoring work. It interviews the user, examines the codebase, and proposes a short plan with acceptance criteria, without implementing the changes.

sangrokjung/claude-forge · 112 tokens

escalation-fixer

Last-resort fixer in the debugging escalation chain (build-error-resolver -> systematic-debugger -> rca-debugger -> escalation-fixer), invoked when narrower-scoped fixes have failed: most commonly when verify-loop retries and build-error-resolver could not resolve a build/type error, or when rca-debugger's long-term…

sangrokjung/claude-forge · 118 tokens

adversarial-reviewer

Independent read-only checker for behavioural changes. Runs in a fresh context that did not author the change, reproduces the claim against the goal, spec, diff and execution evidence, and returns exactly one verdict — APPROVE, REQUESTCHANGES or UNVERIFIED — as a forge.review/v1 envelope. MUST BE USED before claiming…

sangrokjung/claude-forge · 102 tokens

rca-debugger

Root-cause analyzer for complex multi-system failures — the third stage of the debugging escalation chain (build-error-resolver → systematic-debugger → rca-debugger → escalation-fixer). Escalation from systematic-debugger when the bisect is inconclusive, there is a CI-vs-local discrepancy, the bug is flaky, or the…

sangrokjung/claude-forge · 118 tokens