Borrowing it
Nothing to install: this file belongs to tbhb/vale-ai-tells. 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/tbhb/vale-ai-tells/main/.claude/skills/codex-commit/SKILL.mdgit clone --depth 1 https://github.com/tbhb/vale-ai-tellsWrote 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/tbhb/vale-ai-tells/codex-commit)<a href="https://agentmods.dev/skills/tbhb/vale-ai-tells/codex-commit"><img src="https://agentmods.dev/badge/skills/tbhb/vale-ai-tells/codex-commit.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 | $0.00061 | $0.00726 |
| Opus 5 | $0.00030 | $0.00363 |
| Sonnet 5 | $0.00012 | $0.00145 |
| Haiku 4.5 | $0.00006 | $0.00073 |
Grade A, and why
codex-commit 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 7d 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Commit workflow
Run from the repository that holds the changes. Start with .agents/skills/codex-commit/scripts/preflight.sh.
Stop on an interrupted Git operation or missing precondition. Create and maintain an update_plan checklist for base, grouping, staging, draft, prose, review, gates, confirmation, commit, and rebase.
Use the recommended base from preflight. Read the whole diff and divide it into independently revertible logical changes. Stage every path by name with git add --. Never use git add ., git add -A, or git add --all. Confirm the index with the cached stat and short status.
Write the complete message to repo-root COMMIT_AGENTMSG. Use <type>(<scope>)?(!)?: <imperative description>. The body records why the change exists rather than restating the diff. Use only checked claims. Omit counts, sales language, and provenance. Hard-wrap body lines at 72 and trailers at 100. Put Assisted-by before the required Signed-off-by printed by preflight.
Invoke codex-fix-prose on COMMIT_AGENTMSG mise run lint-commit-msg. Then delegate codex-review-commit-message with fork_turns: "none", supplying only the repository root, optional --amend, and instruction to follow that skill. Resolve every finding and repeat prose lint plus independent review until it returns exactly VERDICT: PASS.
Only after receiving that verdict, run:
bash .agents/skills/codex-commit/scripts/stamp-review.sh <repo-root> <verdict-file>
mise run lint-commit-msg
Save the delegated agent's exact final response in the verdict file. The stamping script accepts only VERDICT: PASS and records both the draft digest and the staged tree.
After any edit to the draft or index, repeat the prose pass and independent review before stamping again.
Confirmation and commit
Default mode always requires explicit operator confirmation unless preflight reports commit: GRANTED. Show the staged paths and complete message first. When the workflow needs confirmation, end the turn and ask Commit this message? Present Commit it, Revise the message, Restage and redraft, and Stop here. Don't commit in the turn that asks. The original request to commit doesn't count as this final confirmation.
What ships with it
4 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.
- 7d ago First seen · 45 lines · 61 tokens per session scan A 0a90b7b3b335
codex-commit is a skill published in the GitHub repository tbhb/vale-ai-tells (83 stars, last pushed yesterday), licensed MIT. It adds 61 tokens to every session and 726 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
anti-slop
Remove AI slop from any voice-bearing prose — original posts, threads, articles, long-form, emails, docs, READMEs, marketing copy, bios, scripts. Use when drafting text meant to sound like a specific person or brand, when rewriting text that reads generic, corporate, or AI-generated, or when asked to humanize…
kill-slop
Audit a file or draft for AI slop and off-voice lines against the author's bound voice, report findings with in-voice swaps, then apply approved fixes. Use when the user says "kill slop", "/kill-slop [file]", "find the slop in this", "audit this for slop", or wants a deck, article, page, or draft cleaned to sound like…
contextual-commit
Write contextual commits that capture intent, decisions, and constraints alongside code changes. Use when committing code, finishing a task, or when the user asks to commit. Extends Conventional Commits with structured action lines in the commit body that preserve WHY code was written, not just WHAT changed.
gh-issues
Fetch GitHub issues, spawn sub-agents to implement fixes and open PRs, then monitor and address PR review comments. Usage: /gh-issues [owner/repo] [--label bug] [--limit 5] [--milestone v1.0] [--assignee @me] [--fork user/repo] [--watch] [--interval 5] [--reviews-only] [--cron] [--dry-run] [--model glm-5]…
git-commit
Generate well-formatted git commit messages following conventional commit standards.
git-commit
Stage, write, and structure git commits and pull requests cleanly. Read this before committing — for conventional-commit message format, when to split commits, and how to open a PR with the gh CLI.