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 claude-printgit 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/claude-print)<a href="https://agentmods.dev/skills/tobihagemann/turbo/claude-print"><img src="https://agentmods.dev/badge/skills/tobihagemann/turbo/claude-print/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/claude-print"><img src="https://agentmods.dev/badge/skills/tobihagemann/turbo/claude-print.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 Excessive Agency · line 15 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
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 | $0.00059 | $0.01099 |
| Opus 5 | $0.00030 | $0.00549 |
| Sonnet 5 | $0.00012 | $0.00220 |
| Haiku 4.5 | $0.00006 | $0.00110 |
Grade A, and why
claude-print 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.
How it starts
The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Print
Run a non-interactive Claude Code CLI print-mode call from Codex. This is the Codex edition's low-level Claude bridge for one-shot review and consultation prompts.
Step 1: Choose Permission Scope and Model
Default to read-only review:
claude -p --permission-mode dontAsk --allowedTools="Read,Grep,Glob,Bash(git diff:*),Bash(git log:*),Bash(git show:*),Bash(git status:*),Bash(git rev-parse:*),Bash(git ls-files:*)" "<prompt>" < /dev/null
The Bash allow-list is restricted to read-only git subcommands so peer review cannot mutate the working tree, branches, or remotes. Use broader permissions only when the user explicitly asks Claude to perform write-capable work.
Omit --model, leaving the run on Claude Code's configured model. When the user named a model for this run, add --model <model> to every claude -p command in this skill and pass the name verbatim — the flag takes an alias or a full model name.
Step 2: Shape the Prompt
Keep the prompt compact and explicit:
- State that Claude is an independent reviewer.
- Include the exact scope: diff command, files, or plan/spec path. Pass text you did not author through the context file.
- Include the required output contract.
- Tell Claude to verify codebase claims by reading files before reporting findings.
- Tell Claude not to modify files unless the current task explicitly requests write-capable work.
- Tell Claude to answer the request itself rather than delegating to a peer review or consultation skill that crosses back to Codex. The prompt has already crossed the tool boundary; a further crossing that fails mid-flight leaves this run holding a question instead of an answer.
For large context, print the absolute path of the context file first:
mkdir -p "$PWD/.turbo/claude" && echo "$PWD/.turbo/claude/<tag>-ctx.txt"
Write the context file to the printed path with apply_patch so nothing is interpreted on the way in, then substitute that same printed value for <printed-path> below. An earlier cd in a compound command leaves the session in a different directory, so a relative path resolves against that directory instead:
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.
- 7d ago First seen · 75 lines · 59 tokens per session scan A 9e1d3913ae37
claude-print is a skill published in the GitHub repository tobihagemann/turbo (402 stars, last pushed 2d ago), licensed MIT. It adds 59 tokens to every session and 1,099 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
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…
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.
refactor-advisor
A code review helper that finds common design and maintenance problems in a codebase and suggests ways to restructure the code.
zh-code-reviewer
A Chinese-language code-review specialist that produces a structured review report. It examines coding style, possible bugs, performance, security, and design choices.
review-implementing
Process and implement code review feedback systematically. Use when user provides reviewer comments, PR feedback, code review notes, or asks to implement suggestions from reviews.
code-auditor
Performs comprehensive codebase analysis covering architecture, code quality, security, performance, testing, and maintainability. Use when user wants to audit code quality, identify technical debt, find security issues, assess test coverage, or get a codebase health check.