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 tobihagemann/turbo --skill review-agentic-setupgit clone --depth 1 https://github.com/tobihagemann/turboWrote 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/tobihagemann/turbo/review-agentic-setup)<a href="https://agentmods.dev/skills/tobihagemann/turbo/review-agentic-setup"><img src="https://agentmods.dev/badge/skills/tobihagemann/turbo/review-agentic-setup/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/tobihagemann/turbo/review-agentic-setup"><img src="https://agentmods.dev/badge/skills/tobihagemann/turbo/review-agentic-setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Agent Snooping · line 53 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00095 | $0.01801 |
| Opus 5 | $0.00048 | $0.00901 |
| Sonnet 5 | $0.00019 | $0.00360 |
| Haiku 4.5 | $0.00010 | $0.00180 |
Grade A, and why
review-agentic-setup 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.
How it starts
The opening of the file, as written. The whole thing — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Agentic Setup
Detect agentic coding infrastructure and flag gaps across Claude Code and Codex CLI conventions. Analysis only. Does not install or configure anything.
Scope
Agentic setup review always operates at the project level. Scope parameters (diff commands, file lists) are accepted but ignored.
When called standalone, use the git repository root as the project root (fall back to the current working directory if not in a git repo).
Step 1: Detect Infrastructure
Search for agentic coding configuration in the project. Classify findings into five categories:
Agent Instructions
| File | Read by | What to check |
|---|---|---|
CLAUDE.md (project root) |
Claude Code | Exists? Sections present (project structure, conventions, build commands, rules)? |
CLAUDE.md (subdirectories) |
Claude Code | Any nested CLAUDE.md files for sub-module guidance? |
AGENTS.md (root and subdirectories) |
Codex | Exists? Content areas (setup, conventions, testing, architecture)? |
AGENTS.override.md |
Codex | Exists? Overrides AGENTS.md at the same directory level. |
README.md |
Both | Mentions AI-assisted development, agent workflows, or prompting guidance? |
Read each file that exists and summarize its coverage areas. Note which tools can use it.
Claude Code does not read AGENTS.md directly. Projects share instructions across both tools by:
- Import: CLAUDE.md includes
@AGENTS.mdto pull in shared content - Symlink:
CLAUDE.mdsymlinked toAGENTS.md(or vice versa) so both tools read the same file
Check for both patterns when the project has agent instruction files.
Installed Skills
Check both skill locations. For each skill directory, read the SKILL.md frontmatter to extract name and description. Group skills by type:
| Location | Used by |
|---|---|
.claude/skills/ |
Claude Code |
.agents/skills/ |
Codex |
Skill types:
- Analysis — review, audit, or inspection skills
- Workflow — multi-step process skills
- Pipeline — skills that compose other skills
- Utility — formatting, staging, committing, or other focused tools
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.
- 11d ago First seen · 165 lines · 95 tokens per session scan A f398066a0f8b
review-agentic-setup is a skill published in the GitHub repository tobihagemann/turbo (402 stars, last pushed yesterday), licensed MIT. It adds 95 tokens to every session and 1,801 once invoked, about $0.0005 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 2026-08-30.
Other skills, from other repositories
plan-ceo-review
CEO/founder-mode plan review. Rethink the problem, find the 10-star product, challenge premises, expand scope when it creates a better product. Three modes: SCOPE EXPANSION (dream big), HOLD SCOPE (maximum rigor), SCOPE REDUCTION (strip to essentials). Originally from Garry Tan's gstack…
master
Turn reference docs into active mastery through retrieval practice, case binding, and scenario simulation. Combines Skycak (learning science) and Chin (expertise acceleration) frameworks. Use when you want to deeply learn material, not just read it.
upskilling-coach
Expert coach for learning, mastering, and upskilling in any domain. Use when the user wants to learn, master, improve, upskill, get better at, or get coached on any topic. Helps build consistent practice habits, identify prerequisites, design efficient learning loops, avoid common pitfalls, maintain discipline, and…
agentic-review
Deep multi-agent code review for local changes. Inspired by AmpCode's agentic review. Use when you want comprehensive analysis of staged changes, unstaged changes, specific commits, or branch differences. Spawns parallel specialized agents (security, performance, patterns, architecture) and synthesizes actionable…
design-swarm
Orchestrate a team of 10 design agents for holistic UI audit, ideation, and implementation. Use when: "design swarm", "holistic audit", "design review with all lenses", "full design analysis". Modes: audit, ideate, implement (any combination). Targets: screenshots, URLs, file paths, or text briefs.
qa
Full QA on all session changes using Codex as a second pair of eyes. Use when user says "QA", "full QA", "QA my changes", "QA all your changes", or "use codex to review". Runs git diff, sends changes to Codex for thorough review, and synthesizes findings.