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 Phelan164/codex-howto --skill evidence-reviewgit clone --depth 1 https://github.com/Phelan164/codex-howtoWrote 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/phelan164/codex-howto/evidence-review)<a href="https://agentmods.dev/skills/phelan164/codex-howto/evidence-review"><img src="https://agentmods.dev/badge/skills/phelan164/codex-howto/evidence-review/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/phelan164/codex-howto/evidence-review"><img src="https://agentmods.dev/badge/skills/phelan164/codex-howto/evidence-review.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 | $0.00039 | $0.00122 |
| Opus 5 | $0.00019 | $0.00061 |
| Sonnet 5 | $0.00008 | $0.00024 |
| Haiku 4.5 | $0.00004 | $0.00012 |
Grade A, and why
evidence-review 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 10d 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
Evidence Review
- Read the requested diff and applicable repository guidance.
- Trace each suspected problem to a concrete file, behavior, or broken contract.
- Return actionable findings ordered by impact.
- Include a precise location, failing scenario, evidence, and fix direction.
- Omit style preferences and unsupported speculation.
- State explicitly when no actionable finding is verified.
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.
- 10d ago First seen · 14 lines · 39 tokens per session scan A d5487a54f3d8
evidence-review is a skill published in the GitHub repository Phelan164/codex-howto (4 stars, last pushed 2d ago), licensed MIT. It adds 39 tokens to every session and 122 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
agent-skill-release-review
Review a Codex, Claude Code, or agent skill/plugin before public release. Use when the user wants to assess trigger quality, folder structure, documentation, validation gaps, GitHub readiness, or OSS release quality for an agent extension.
focused-code-review
Perform a concise, severity-ranked review of a non-trivial diff. Trigger after implementation or when explicitly asked to review code.
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.
openlore-execute-refactor
Apply a confirmed .openlore/refactor-plan.md with a test gate after each change. Use when asked to execute or continue an OpenLore refactoring plan.
openlore-review-changes
Review code changes using OpenLore risk, call, coverage, and cluster evidence without editing code. Use when asked for a change review, pre-PR safety check, or merge recommendation.
repo-harness-cross-review
Independent outside review of the current review scope (branch diff plus staged, unstaged, untracked changes). Claude hosts use direct Codex; Codex hosts use OpenAI's official Claude Code Codex plugin app-server runtime. Use before merging, after a tricky change, or for a debug second opinion.