mcp-codex-worker: Skill for Claude Code

.claude/skills/worker-campaign-cheap-reliability/SKILL.md

worker-campaign-cheap-reliability is a skill for Claude Code from sorryorc/mcp-codex-worker. It costs 35 tokens per session (300 once invoked), scanned A, original, MIT.

A measured workflow for investigating and reducing quality problems caused by using lower-cost workers.

In plain words
What is it for?
Use it to collect failed jobs, compare results before and after changes, classify risky work, and route important cases for stronger review.
Why use it?
It helps identify which failures are actually caused by the worker and adds review or blocking checks according to risk. It also requires evidence before turning an advisory warning into a hard stop.

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-campaign-cheap-reliability/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-campaign-cheap-reliability

README.md
[![agentmods](https://agentmods.dev/badge/skills/sorryorc/mcp-codex-worker/worker-campaign-cheap-reliability.svg)](https://agentmods.dev/skills/sorryorc/mcp-codex-worker/worker-campaign-cheap-reliability)
Your own site
<a href="https://agentmods.dev/skills/sorryorc/mcp-codex-worker/worker-campaign-cheap-reliability"><img src="https://agentmods.dev/badge/skills/sorryorc/mcp-codex-worker/worker-campaign-cheap-reliability.svg" alt="Measured on agentmods" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 300 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00035 $0.00300
Opus 5 $0.00017 $0.00150
Sonnet 5 $0.00007 $0.00060
Haiku 4.5 $0.00003 $0.00030

Measured 8d ago against content hash 733d5ef627c0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

worker-campaign-cheap-reliability 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 8d 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-campaign-cheap-reliability/SKILL.md · 39 lines

What it actually says

Worker Campaign Cheap Reliability

Goal

Turn "cheap worker feels degraded" into measured failure classes and gated mitigations.

Phases

  1. Baseline: run npm test, npm run codex:audit -- --since-minutes=60, and collect recent failed episodes.
  2. Instrument: ensure reliability profile, episode summary, receipt abnormal verdict, and tool metrics exist.
  3. Gate: use strict for normal risky edits and critical for security, release, migration, or broad refactors.
  4. Review: send semantic-risk cases to main-thread or strong-model review.
  5. Promote: only make a warning into a hard block after eval cases prove low false-positive risk.

Wrong Paths To Fence Off

  • Do not rely on more output tokens as thinking time.
  • Do not expose all tools to a weak model by default.
  • Do not trust a model-created Observation without runtime receipt.

When Not To Use

Do not use this for one isolated failed command. Use worker-debugging-playbook.

Verification

  • npm test
  • npm run codex:guard
  • Compare trajectory scores before and after a change.

Provenance and maintenance

Add real user feedback cases as eval episodes before tightening blocking gates.

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. 8d ago First seen · 39 lines · 35 tokens per session scan A 733d5ef627c0

Subscribe to this mod's changes

worker-campaign-cheap-reliability is a skill published in the GitHub repository sorryorc/mcp-codex-worker (2 stars, last pushed 6d ago), licensed MIT. It adds 35 tokens to every session and 300 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-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-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-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