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 consult-claudegit 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/consult-claude)<a href="https://agentmods.dev/skills/tobihagemann/turbo/consult-claude"><img src="https://agentmods.dev/badge/skills/tobihagemann/turbo/consult-claude/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/consult-claude"><img src="https://agentmods.dev/badge/skills/tobihagemann/turbo/consult-claude.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 Excessive Agency · line 30 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 | $0.00059 | $0.01149 |
| Opus 5 | $0.00030 | $0.00575 |
| Sonnet 5 | $0.00012 | $0.00230 |
| Haiku 4.5 | $0.00006 | $0.00115 |
Grade A, and why
consult-claude 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 3d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Consult Claude
Use Claude Code as an external collaborator from Codex. Unlike $peer-review, this skill is conversational and exploratory.
Step 1: Define the Question
State:
- What problem needs input
- What has already been tried
- What constraints the answer must respect
- What files, commands, plans, or error messages matter
- What kind of answer is useful: hypotheses, tradeoffs, concrete fix, or review
When a recommendation is wanted, bar answers that appeal to scope: state that "out of scope" or "leave it alone" is not an acceptable argument on its own, and that recommending no change must be justified on technical merit. Demand one pick per decision, the reasoning, and the strongest counterargument to that pick, with hedging across options ruled out.
When the consultation runs until Claude approves, fix the line that ends every response: require every response to end with exactly one fixed line stating the verdict, in a designated positive or negative form, carrying nothing else. Stop consulting when that line reaches the positive form, so a politely worded answer does not end the consultation early and agreement does not go unrecognized. Pair it with a compact output contract demanding that each finding ship a ready-to-paste replacement rather than an instruction, which keeps a round cheap enough to iterate.
When the consultation is a prose rewrite bound by a house style, name the shapes that style forbids in the first prompt, so they do not have to be corrected across follow-up turns. Common ones: prefixing a summary with a grammatical subject the convention omits, expanding a pronoun to its full noun phrase at every occurrence, and splitting a sentence so a condition is restated in both halves.
Step 2: Run $claude-print Skill
Run the $claude-print skill with the assembled question. Default to read-only permissions.
For follow-up questions, include Claude's previous answer and the new evidence gathered since then. When the consultation runs until Claude approves, open each follow-up by listing what was already applied, so Claude judges the current state rather than re-reporting findings that are already fixed. Cap the consultation at five turns, counting the initial request. When the fifth verdict is still negative, carry the outstanding findings into Step 3 as unresolved and state that the consultation ended without approval.
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.
- 3d ago Changed · +2 lines 201db6f4d54f
- 5d ago Changed · +2 lines 811ffebdc367
- 9d ago First seen · 62 lines · 59 tokens per session scan A 2ef1249448b3
consult-claude is a skill published in the GitHub repository tobihagemann/turbo (402 stars, last pushed 3d ago), licensed MIT. It adds 59 tokens to every session and 1,149 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
error-translator
A Chinese-language assistant that translates English programming errors and explains what they mean. It covers common errors from languages and frameworks including Python, JavaScript, TypeScript, Java, and others.
eslint-fix
A project-aware assistant for finding and fixing ESLint errors, warnings, and configuration compatibility problems. ESLint is a tool that checks JavaScript and TypeScript code for style and common mistakes.
perf-profiler
A performance investigation guide that uses repeatable measurements and profiling evidence to find where software spends time or resources. Profiling records runtime activity such as CPU use, memory use, database work, or network delays.
log-analyzer
A log-analysis helper that reads application and system logs to find unusual patterns and likely causes. Logs are records of events such as errors, requests, warnings, and service activity.
error-resilience-expert
Expert guide for error handling patterns, resilience engineering, retry strategies, circuit breakers, and graceful degradation across React, Next.js, and Node.js / Panduan ahli pola penanganan error, rekayasa ketahanan, strategi retry, circuit breaker, dan degradasi anggun di React, Next.js, dan Node.js.
serena
Semantic code understanding with IDE-like symbol operations. Use when: (1) Large codebase analysis (>50 files), (2) Symbol-level operations (find, rename, refactor), (3) Cross-file reference tracking, (4) Project memory and session persistence, (5) Multi-language semantic navigation. Triggers: "find symbol", "rename…