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 agentmods add skills/kevinbigham/codex-safe-starter/codex-safe-workflownpx skills add KevinBigham/codex-safe-starter --skill codex-safe-workflowgit clone --depth 1 https://github.com/KevinBigham/codex-safe-starterWrote 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/kevinbigham/codex-safe-starter/codex-safe-workflow)<a href="https://agentmods.dev/skills/kevinbigham/codex-safe-starter/codex-safe-workflow"><img src="https://agentmods.dev/badge/skills/kevinbigham/codex-safe-starter/codex-safe-workflow.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 | $0.00040 | $0.00336 |
| Opus 5 | $0.00020 | $0.00168 |
| Sonnet 5 | $0.00008 | $0.00067 |
| Haiku 4.5 | $0.00004 | $0.00034 |
Grade A, and why
codex-safe-workflow 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 3d 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
Codex Safe Workflow
Use this skill for changes to the Codex Safe Starter repo. It is the canonical repo-scoped skill and should stay under .agents/skills/codex-safe-workflow/.
- Read
AGENTS.mdanddocs/codex/repo_map.md. - Plan non-trivial edits with objective, scope, files, verification, risks, and rollback.
- Keep changes project-local unless the maintainer explicitly approves a global change.
- Do not install tools by default. Stage install proposals in
codex-upgrade/SECURITY_REVIEW.md. - Run:
node scripts/secret-scan.mjsnode scripts/selftest.mjsnode scripts/doctor.mjs --cinode scripts/smoke.mjsnode codex-upgrade/benchmarks/run-smoke.mjs --final
- Before commit, stage only intended files and run
node scripts/secret-scan.mjs --staged. - Update
PORTABILITY_REPORT.mdandCODEX_STACK_REPORT.mdwhen portability, validation, Git, agent, skill, or install decisions change. - Keep MCP, hooks, rules, plugins, and permission-profile migrations staged in docs unless the maintainer explicitly approves activating them.
For the detailed checklist, read references/workflow-checklist.md.
What ships with it
2 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.
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.
- 3d ago First seen · 25 lines · 40 tokens per session scan A 23d5fc7e22dd
codex-safe-workflow is a skill published in the GitHub repository KevinBigham/codex-safe-starter (1 stars, last pushed 1mo ago), licensed MIT. It adds 40 tokens to every session and 336 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
nature-statistics
Audit, revise, or draft manuscript statistical reporting for Nature / high-impact journal submissions. Use when the user asks to check statistical analysis sections, p values, confidence intervals, sample size, biological versus technical replicates, randomization, blinding, multiple-comparison correction, model…
nature-citation
Add strict Nature/CNS citations to manuscript text by splitting long passages into citable segments, searching only accepted flagship and subjournal titles from Nature Portfolio, the AAAS Science family, and Cell Press, filtering by publication time range, and exporting one reference-manager-ready output by default.…
baoyu-youtube-transcript
Downloads YouTube video transcripts/subtitles and cover images by URL or video ID. Supports multiple languages, translation, chapters, and speaker identification. Caches raw data for fast re-formatting. Use when user asks to "get YouTube transcript", "download subtitles", "get captions", "YouTube字幕", "YouTube封面"…
review-plan
Review a plan by running internal reviews and a peer review in parallel and returning combined findings. Use when the user asks to "review my plan", "check my plan", "critique my plan", or wants feedback on a plan.
reply-to-pr-threads
Draft, confirm, and post replies to GitHub PR review threads. Handles per-category reply formatting, re-fetches thread resolution state so auto-resolved threads are skipped, and posts via GraphQL. Use when the user asks to "reply to PR threads", "post PR thread replies", or "draft PR reply messages".
answer-reviewer-questions
For each reviewer question on a PR, recall implementation reasoning and compose a raw answer. Use when the user asks to "answer reviewer questions", "draft answers to PR questions", or "explain reviewer questions".