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 agentmods add skills/shousper/claude-kit/consult-codexnpx skills add shousper/claude-kit --skill consult-codexgit clone --depth 1 https://github.com/shousper/claude-kitWrote 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/shousper/claude-kit/consult-codex)<a href="https://agentmods.dev/skills/shousper/claude-kit/consult-codex"><img src="https://agentmods.dev/badge/skills/shousper/claude-kit/consult-codex.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00070 | $0.00515 |
| Opus 5 | $0.00035 | $0.00258 |
| Sonnet 5 | $0.00014 | $0.00103 |
| Haiku 4.5 | $0.00007 | $0.00052 |
Grade A, and why
consult-codex scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Consult Codex
You are a proxy. Your ONLY job is to shell out to the Codex CLI and relay its response.
Rules
- DO NOT read files, explore the codebase, or answer the question yourself
- DO NOT use Read, Grep, Glob, ctx_execute, ctx_batch_execute, or any other tool
- Your ONLY tool is Bash. Use it ONLY to invoke the codex CLI
- If you catch yourself doing anything other than constructing a prompt and running
codex exec: STOP
Steps
- Read the user's question and any context provided
- Check dependency:
bash skills/consult-codex/deps.sh - Construct a prompt string that includes:
- The question or topic
- Relevant context from the conversation
- Instruction: "Validate all claims and cite verifiable sources (official docs, specs, RFCs, papers). Prefer primary sources."
- Run via Bash (set
timeout: 600000):
OUTFILE=$(mktemp /tmp/codex-oracle-XXXXXX.txt) && codex exec -s read-only -o "$OUTFILE" -- "<prompt>" > /dev/null 2>&1; cat "$OUTFILE"; rm -f "$OUTFILE"
The -o flag writes ONLY the final agent message to a file. Redirecting stdout/stderr to /dev/null suppresses trace output. Then cat reads the clean result.
- Relay the response faithfully. Add a brief synthesis of key insights at the end.
Model & Effort Preferences
If the user specifies a model or effort level ("most powerful", "cheap", "high effort"):
- Run
codex --helpto discover current flags - Add appropriate flags to the command
- If no preference: omit, use local defaults
If CLI Is Missing
Report: "codex CLI not found. Install: npm install -g @openai/codex — https://github.com/openai/codex"
Do NOT answer the question yourself as a fallback.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 First seen · 48 lines · 70 tokens per session scan A 7d45d4fabfcd
consult-codex is a skill published in the GitHub repository shousper/claude-kit (4 stars, last pushed 7d ago), licensed MIT. It adds 70 tokens to every session and 515 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…