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/happenmass/codex-claude-code-mcp/claude-code-blocking-directnpx skills add Happenmass/codex-claude-code-mcp --skill claude-code-blocking-directgit clone --depth 1 https://github.com/Happenmass/codex-claude-code-mcpWrote 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/happenmass/codex-claude-code-mcp/claude-code-blocking-direct)<a href="https://agentmods.dev/skills/happenmass/codex-claude-code-mcp/claude-code-blocking-direct"><img src="https://agentmods.dev/badge/skills/happenmass/codex-claude-code-mcp/claude-code-blocking-direct.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 | $0.00063 | $0.00516 |
| Opus 5 | $0.00032 | $0.00258 |
| Sonnet 5 | $0.00013 | $0.00103 |
| Haiku 4.5 | $0.00006 | $0.00052 |
Grade A, and why
claude-code-blocking-direct 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 — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Code Blocking Direct
Use the installed claude-code-blocking MCP tools. Do not emulate the call with the Claude CLI.
Run
- Confirm that
claude_code_runis available. If it is missing, tell the user to install the MCP and restart Codex. - If the user asks which models are available, requests model selection, or supplies an uncertain model identifier, call
claude_code_modelsonce first. Use its returnedvalueas the run/resume model. Do not query models when an exact known model was already requested. - Translate the request into one bounded Claude task. Preserve the user's scope, repository path, constraints, desired output, and model choice.
- Set the working directory explicitly when local files are in scope.
- Grant only the tools the task needs:
- Keep
Read,Grep, andGlobfor read-only work. - Add
EditorWriteonly when the user requested file changes. - Put risky or broad tools such as
BashinaskToolsunless automatic use is clearly authorized. - Deny unrelated web or mutation tools.
- Keep
- Call
claude_code_runexactly once and let the tool call remain open until it returns. Do not add polling, status checks, shell loops, or repeated model turns. - Report Claude's result, terminal status, and
sessionId. Distinguish Claude's conclusions from your own.
If the MCP requests permission through elicitation, evaluate it against the user's authorization. Do not broaden scope merely to keep the call running.
Resume
For a follow-up that should keep the same Claude context, call claude_code_resume once with the returned sessionId and the new bounded prompt. Apply the same tool policy and wait for the final result.
Cancellation and failure
- Treat user cancellation as a request to cancel the active MCP call.
- If the call times out, is cancelled, or returns
input_requiredthat cannot be satisfied, return that state and the session ID when present. - Never invent a successful Claude result or silently replace Claude with another model.
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 · 35 lines · 63 tokens per session scan A 3a44a02d7a70
claude-code-blocking-direct is a skill published in the GitHub repository Happenmass/codex-claude-code-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 63 tokens to every session and 516 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…