mcp-codex-worker: Skill for Claude Code

.claude/skills/worker-architecture-contract/SKILL.md

worker-architecture-contract is a skill for Claude Code from sorryorc/mcp-codex-worker. It costs 32 tokens per session (276 once invoked), scanned A, original, MIT.

A set of rules describing how the main coding agent, worker tools, inexpensive read-only calls, evidence records, saved outputs, and automatic checks should work together. It defines boundaries for planning, implementation, review, security, and large outputs.

In plain words
What is it for?
Use it when explaining or changing worker architecture, tool boundaries, receipts, artifacts, deterministic checks, sandbox paths, or blocking policies.
Why use it?
It prevents model explanations from being treated as proof and reduces confusion about which part of the system is responsible for each task. It also sets safety limits for workspace access and permission bypasses.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions Codex.

This is sorryorc/mcp-codex-worker's own configuration. It tells Claude Code how to work on mcp-codex-worker itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything mcp-codex-worker configures →

Reuse

Borrowing it

Nothing to install: this file belongs to sorryorc/mcp-codex-worker. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/sorryorc/mcp-codex-worker/main/.claude/skills/worker-architecture-contract/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/sorryorc/mcp-codex-worker

Made for: Claude Code.

Wrote 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.

agentmods badge for worker-architecture-contract

README.md
[![agentmods](https://agentmods.dev/badge/skills/sorryorc/mcp-codex-worker/worker-architecture-contract.svg)](https://agentmods.dev/skills/sorryorc/mcp-codex-worker/worker-architecture-contract)
Your own site
<a href="https://agentmods.dev/skills/sorryorc/mcp-codex-worker/worker-architecture-contract"><img src="https://agentmods.dev/badge/skills/sorryorc/mcp-codex-worker/worker-architecture-contract.svg" alt="Measured on agentmods" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 276 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00032 $0.00276
Opus 5 $0.00016 $0.00138
Sonnet 5 $0.00006 $0.00055
Haiku 4.5 $0.00003 $0.00028

Measured 6d ago against content hash 5ec72c317faa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

worker-architecture-contract 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 6d 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.

.claude/skills/worker-architecture-contract/SKILL.md · 35 lines

What it actually says

Worker Architecture Contract

Load-Bearing Boundaries

  • Main Codex plans, decides, and performs final review.
  • Worker tools absorb bulk reading, shell output, diff digestion, and implementation loops.
  • Lite tools are read-only cheap gateway calls. They are not authoritative for high-risk acceptance.
  • Receipts and artifacts are the evidence boundary. Model prose is not proof.
  • Deterministic gates can reject scope, failed checks, and malformed output without extra LLM calls.

Invariants

  • All paths stay inside SANDBOX_ROOT.
  • bypassPermissions is rejected unless explicitly allowed.
  • Large outputs should be artifact-backed.
  • New strictness must be advisory unless blocking_policy=enforce.

When Not To Use

Do not use this for single failing command diagnosis. Use worker-debugging-playbook.

Verification

  • npm test
  • rg -n "SANDBOX_ROOT|bypassPermissions|artifact_refs|blocking_policy" src

Provenance and maintenance

Re-read src/server.ts, src/security.ts, src/artifacts.ts, and src/reliability.ts after contract changes.

Changes

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.

  1. 6d ago First seen · 35 lines · 32 tokens per session scan A 5ec72c317faa

Subscribe to this mod's changes

worker-architecture-contract is a skill published in the GitHub repository sorryorc/mcp-codex-worker (2 stars, last pushed 4d ago), licensed MIT. It adds 32 tokens to every session and 276 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

go-testing

Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.

Gentleman-Programming/gentle-ai · 26 tokens

memstack-business-gdpr

Use this skill when the user says 'GDPR', 'data protection', 'privacy compliance', 'DPA', 'DSAR', 'data subject request', 'cookie consent', 'privacy audit', 'CCPA', or asks 'do I need GDPR for this repo'. Scans the repository to detect what personal data is collected, classifies sensitivity, determines whether GDPR…

cwinvestments/memstack · 121 tokens

memstack-automation-webhook-designer

Use this skill when the user says 'webhook', 'webhook handler', 'webhook endpoint', 'receive events', 'HMAC verification', 'idempotency', or needs secure webhook handlers with signature verification, retry handling, and dead letter queues. Do NOT use for full n8n workflows or scheduled tasks.

cwinvestments/memstack · 74 tokens

memstack-deployment-domain-ssl

Use this skill when the user says 'setup domain', 'configure DNS', 'SSL certificate', 'domain-ssl', 'custom domain', 'HTTPS setup', or needs to configure DNS records, SSL certificates, and custom domains for any hosting provider. Do NOT use for full deployment workflows.

cwinvestments/memstack · 66 tokens

memstack-development-refactor-planner

Use this skill when the user says 'refactor', 'refactoring plan', 'code cleanup', 'reduce duplication', 'simplify code', 'tech debt', 'god class', 'tight coupling', or needs to systematically improve existing code. Identifies targets, assesses risk, and builds incremental execution plans. Do NOT use for writing new…

cwinvestments/memstack · 81 tokens

memstack-product-feedback-analyzer

Use this skill when the user says 'analyze feedback', 'feedback analysis', 'what are customers asking for', or has support tickets, reviews, or survey data to categorize, score, and prioritize into actionable reports. Do NOT use for competitor analysis or market research.

cwinvestments/memstack · 61 tokens