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 skills add ucsahinn/codex-chef --skill evidence-researchgit clone --depth 1 https://github.com/ucsahinn/codex-chefWrote 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/ucsahinn/codex-chef/evidence-research)<a href="https://agentmods.dev/skills/ucsahinn/codex-chef/evidence-research"><img src="https://agentmods.dev/badge/skills/ucsahinn/codex-chef/evidence-research/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ucsahinn/codex-chef/evidence-research"><img src="https://agentmods.dev/badge/skills/ucsahinn/codex-chef/evidence-research.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00071 | $0.00870 |
| Opus 5 | $0.00036 | $0.00435 |
| Sonnet 5 | $0.00014 | $0.00174 |
| Haiku 4.5 | $0.00007 | $0.00087 |
Grade A, and why
evidence-research 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 9d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Evidence Research
Produce decision-ready research whose material claims trace to checked sources. Do not turn a broad web search into an imitation systematic review.
Invocation
- Direct:
$evidence-research <question>. - Plugin:
$codex-chef-workflows:evidence-research <question>. - Implicit activation is allowed for clear deep, literature, market, landscape, comparative, or evidence-synthesis requests, not ordinary factual lookup.
Research Contract
Read scoping-and-charter.md first. State the decision, primary question, focused sub-questions, audience, scope, exclusions, geography, time horizon, deadline, evidence standard, stopping rule, and deliverable. Use a bounded labeled default when missing inputs do not materially change authority, cost, or method.
Separate fact, inference, and recommendation. Every material claim needs
checked source IDs, confidence, uncertainty, and relevant disagreement.
Workflow
- Choose orientation, decision-support, landscape, implementation, evidence-review, or original-analysis mode.
- Design concepts, queries, source classes, inclusion/exclusion rules, and a reproducible log with search-and-screening.md.
- Deduplicate, screen, and record provenance, method, population/corpus, recency, conflicts, applicability, limitations, and full-text status using source-appraisal.md.
- Build a source matrix and claim ledger. Compare convergence, disagreement, missing evidence, and alternative explanations with synthesis-and-uncertainty.md.
- Use qualitative, quantitative, or mixed methods only when the question and data justify them. Profile data before modeling and document code, transformations, assumptions, and sensitivity checks using qualitative-and-quantitative.md.
- Select domain-appropriate primary sources and standards through domain-method-routing.md. Use PRISMA or Cochrane methods only for genuine, correctly labeled review work.
- Package the requested memo, report, slides, bibliography, dataset, or reproducible appendix under reproducibility-and-ethics.md.
What ships with it
14 files 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.
- agents/openai.yaml 448 B
- assets/research-charter.template.md 949 B
- assets/research-report.template.json 2.0 KB
- references/domain-method-routing.md 1.8 KB
- references/forward-tests.md 1.2 KB
- references/qualitative-and-quantitative.md 1.7 KB
- references/reproducibility-and-ethics.md 1.7 KB
- references/scoping-and-charter.md 1.8 KB
- references/search-and-screening.md 2.0 KB
- references/source-appraisal.md 1.5 KB
- references/sources.md 2.0 KB
- references/synthesis-and-uncertainty.md 1.4 KB
- references/verification-rubric.md 1.5 KB
- scripts/validate-research-report.mjs 9.5 KB runs code
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.
- 9d ago First seen · 81 lines · 71 tokens per session scan A 406e96544f5e
evidence-research is a skill published in the GitHub repository ucsahinn/codex-chef (6 stars, last pushed 22d ago), licensed MIT. It adds 71 tokens to every session and 870 once invoked, about $0.0004 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
code-review-excellence
This skill should be used when the user asks to review a diff or pull request, write review comments, audit code quality, establish review standards, or improve how a team performs code review.
git-workflow
This skill should be used when the user asks to "create git commit", "manage branches", "follow git workflow", "use Conventional Commits", "handle merge conflicts", or asks about git branching strategies, version control best practices, pull request workflows. Provides comprehensive Git workflow guidance for team…
architecture-design
Use only when creating new registrable ML components that require Factory or Registry patterns.
results-analysis
This skill should be used when the user asks to "analyze experimental results", "run strict statistical analysis", "compare model performance", "generate scientific figures", "check significance", "do ablation analysis", or mentions interpreting experiment data with rigorous statistics and visualization. It focuses on…
review-response
Systematic review response workflow from comment analysis to professional rebuttal writing. Use when the user asks to "write rebuttal", "respond to reviewers", "draft review response", or "analyze review comments". Improves paper acceptance rates.
daily-paper-generator
Use when the user asks to generate daily paper digests on a general topic. This skill supports both arXiv and bioRxiv (or either one), then produces structured Chinese/English summaries for selected papers.