Claude Code Ultimate Guide is a structured documentation project for learning how to build, operate, and govern coding agents with Claude Code. It serves developers and teams through guidance on agentic workflows, hooks, skills, MCP servers, security, and adoption. The catalogue entries are reusable skills, commands, agents, hooks, instructions, settings, and a plugin drawn from the guide's workflow materials.
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.
npx skills add FlorianBruniaux/claude-code-ultimate-guide --skill eval-agentsgit clone --depth 1 https://github.com/FlorianBruniaux/claude-code-ultimate-guideWrote 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.
[](https://agentmods.dev/skills/florianbruniaux/claude-code-ultimate-guide/eval-agents)<a href="https://agentmods.dev/skills/florianbruniaux/claude-code-ultimate-guide/eval-agents"><img src="https://agentmods.dev/badge/skills/florianbruniaux/claude-code-ultimate-guide/eval-agents/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.
<a href="https://agentmods.dev/skills/florianbruniaux/claude-code-ultimate-guide/eval-agents"><img src="https://agentmods.dev/badge/skills/florianbruniaux/claude-code-ultimate-guide/eval-agents.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 7 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Agent Snooping · line 119 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
- high Agent Snooping · line 122 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
- high Agent Snooping · line 125 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
- medium Excessive Agency · line 83 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 107 Skill grants unrestricted tool access without appropriate constraints. An agent with unfettered tool access can perform arbitrary actions including file modification, network requests, and code execution.Fix: Restrict tool access to only the tools required for the skill's stated purpose. Use an explicit allowlist rather than granting blanket access.
- medium Excessive Agency · line 296 Skill grants unrestricted tool access without appropriate constraints. An agent with unfettered tool access can perform arbitrary actions including file modification, network requests, and code execution.Fix: Restrict tool access to only the tools required for the skill's stated purpose. Use an explicit allowlist rather than granting blanket access.
- medium Excessive Agency · line 297 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00080 | $0.04296 |
| Opus 5.5 | $0.00032 | $0.01718 |
| Sonnet 5.5 | $0.00016 | $0.00859 |
| Haiku 4.5 | $0.00008 | $0.00430 |
Grade A, and why
eval-agents 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 18d 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.
The source is not reproduced here
Licensed CC-BY-SA-4.0
The repository is licensed CC-BY-SA-4.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.
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.
- 18d ago Changed 6075e61061dd
- 20d ago Changed · -44 lines · -13 tokens per session bd0fa1e318db
- 1mo ago First seen · 309 lines · 93 tokens per session scan A 85bcf3ab5a67
eval-agents is a skill published in the GitHub repository FlorianBruniaux/claude-code-ultimate-guide (6,204 stars, last pushed yesterday), licensed CC-BY-SA-4.0. It adds 80 tokens to every session and 4,296 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
devops
DevOps patterns: containerization, CI/CD, deployment strategies, monitoring. Use when containerizing apps, setting up pipelines, or deploying services.
learning
Extracts reusable patterns from sessions. Use at session end to capture debugging insights and project-specific knowledge.
api
RESTful API design patterns and best practices. Use when creating endpoints, designing APIs, or implementing routes.
architecture
Architecture design skill: ADR records, system design checklists, scalability assessment, architecture patterns. Use for complex system design and architecture decisions.
database
Database design, query optimization, migrations, and indexing. Use when designing schemas, writing queries, or managing migrations.
exploration
Code exploration strategies for understanding unfamiliar codebases. Use when exploring unknown code, debugging, or analyzing architecture.