eval-agents

Audit custom subagent definitions for Claude Code (.claude/agents/*.md) and Codex (.codex/agents/*.toml): loadability against the native schema, description overlap, model tier, tool scope, and headless-safe instructions. Use when onboarding to a project with agents, after adding or importing agents, or when the parent agent delegates to the wrong agent.

Jump to install Review files

Repository: FlorianBruniaux/claude-code-ultimate-guide
Last source activity: October 27, 2026 at 13:27
Detected SKILL.md language: English
Stars: 6,417
Forks: 828

Install options

The review-first prompt is selected by default. You can switch to a direct command or download a local copy.

Install with an AI assistant

Copy this prompt into the AI assistant you're using.

Follow https://skillsmp.com/skill-install/prompt.md to install only the Agent Skill at https://github.com/FlorianBruniaux/claude-code-ultimate-guide/tree/main/examples/skills/eval-agents.

A direct command skips the review prompt. Inspect the source before running it.

npx skills add https://github.com/FlorianBruniaux/claude-code-ultimate-guide --skill eval-agents

The command stays on one line. Scroll horizontally to inspect it before copying.

Prefer a local copy? Download the files currently available to SkillsMP.

Review the source files

Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.

SKILL.md

Source instructions · Read-only preview

name	eval-agents
description	Audit custom subagent definitions for Claude Code (.claude/agents/.md) and Codex (.codex/agents/.toml): loadability against the native schema, description overlap, model tier, tool scope, and headless-safe instructions. Use when onboarding to a project with agents, after adding or importing agents, or when the parent agent delegates to the wrong agent.

Back to search Back to installation

agent-rationale

Record why each hunk of an agent-written commit looks the way it does (intent, rejected alternative, risk, evidence, open question) in git notes under refs/notes/rationale, anchored by hunk hash, so a reviewer can read it beside the diff and see when a note went stale. Use after committing agent-written code that a human will review. Not for commit messages, PR descriptions or AI attribution metrics.

2026-11-10

update-threat-db

Update the guide's threat intelligence through AgentSec Triage, research new coding-agent and MCP security advisories or researcher IOC lists (malicious repositories, hashes, campaign gists), and synchronize the security feed. Use for threat database refreshes or mise a jour de la base de menaces, not repository security scans or Claude Code release tracking.

2026-11-07

security-check

Quick configuration security check against known threats database

2026-11-07

View all from this repository

eval-agents

Source facts

Install options

Install with an AI assistant

Review the source files

More from this repository

Install with an AI assistant

More from this repository