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.
curl -O https://raw.githubusercontent.com/sorryorc/mcp-codex-worker/main/.claude/skills/worker-research-methodology/SKILL.mdgit clone --depth 1 https://github.com/sorryorc/mcp-codex-workerWrote 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/sorryorc/mcp-codex-worker/worker-research-methodology)<a href="https://agentmods.dev/skills/sorryorc/mcp-codex-worker/worker-research-methodology"><img src="https://agentmods.dev/badge/skills/sorryorc/mcp-codex-worker/worker-research-methodology.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 5.1 | $0.00032 | $0.00283 |
| Opus 5 | $0.00016 | $0.00142 |
| Sonnet 5 | $0.00006 | $0.00057 |
| Haiku 4.5 | $0.00003 | $0.00028 |
Grade A, and why
worker-research-methodology 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.
What it actually says
Worker Research Methodology
Lifecycle
- Capture source signal and label its evidence strength.
- State the mechanism and predicted metric movement.
- Implement behind observe-only instrumentation.
- Run against real and synthetic episodes.
- Promote, revise, or retire with a written reason.
Evidence Bar
- One mechanism should explain positive and negative cases.
- A change must survive adversarial review for blocking risk.
- Claims about cheap-model improvement need before/after data.
- Treat prompt-leak analysis posts as weak-to-medium evidence: useful for hypothesis generation, not for asserting vendor behavior or copying hidden instructions.
Reference Handling
- Record the URL and claim type.
- Prefer public summaries over copying long source text.
- Convert every borrowed idea into a falsifiable worker hypothesis.
- If a source discusses leaked or proprietary prompts, use structure-level observations only.
When Not To Use
Do not use this for already-specified config or docs updates. Use worker-config-and-flags.
Verification
- Store experiment data in metrics or test fixtures.
- Re-run
npm testafter promotion.
Provenance and maintenance
Record retired ideas so future agents do not repeat the same experiment.
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.
- 6d ago First seen · 42 lines · 32 tokens per session scan A b0f8713cb7c5
worker-research-methodology 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 283 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.
Other skills, from other repositories
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
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…
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.
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.
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…
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.