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-pr/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-pr)<a href="https://agentmods.dev/skills/tbhb/vale-ai-tells/codex-pr"><img src="https://agentmods.dev/badge/skills/tbhb/vale-ai-tells/codex-pr/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/tbhb/vale-ai-tells/codex-pr"><img src="https://agentmods.dev/badge/skills/tbhb/vale-ai-tells/codex-pr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00074 | $0.00751 |
| Opus 5 | $0.00037 | $0.00376 |
| Sonnet 5 | $0.00015 | $0.00150 |
| Haiku 4.5 | $0.00007 | $0.00075 |
Grade A, and why
codex-pr 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Open a pull request
Use update_plan for these phases: preflight, draft, prose gates, independent review, confirmation, publication, and requested follow-through. Keep only one phase in_progress.
Preflight
Run:
bash .agents/skills/codex-pr/scripts/preflight.sh
Stop on a missing prerequisite or an interrupted Git operation. If the branch is behind its base, use codex-rebase first. Tell the user about uncommitted changes before continuing. The preflight scaffolds PR_AGENTDESC.md and reports an existing pull request.
Draft with a delegated writer
Spawn one subagent with this bounded task:
Use the codex-write-pr-description skill in <repo root>. Write or revise PR_AGENTDESC.md, run its validator, and return only its DRAFT result.
Don't draft the file in the calling context. If the writer reports DRAFT: BLOCKED, report the blocker and stop.
Run the prose workflow over PR_AGENTDESC.md with mise run lint-pr-description when codex-fix-prose is available. Otherwise run that task directly and resolve only mechanical findings.
Review with a fresh delegated agent
Spawn a different subagent:
Use the codex-review-pr-description skill in <repo root>. Review PR_AGENTDESC.md against the branch and return its verdict.
On CHANGES REQUIRED, send the findings verbatim to a fresh writer, then review again with a fresh reviewer. Bound finding-driven revisions at three. After PASS, the reviewer records the reviewed digest through record-review.sh. Don't run that script from the calling agent.
Run mise run lint-pr-description after review. Any edit invalidates the digest, so repeat the independent review after a change.
Get confirmation in default mode
Show the branch, base, commit count, and complete draft. Unless preflight reports pr: GRANTED, ask before publication by putting this question and its choices in the final response when using Default mode:
- open, fix, and merge
- open, watch, and fix
- open and watch
- open only
What ships with it
6 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.
- 9d ago First seen · 75 lines · 74 tokens per session scan A 9ec84b28b6a3
codex-pr is a skill published in the GitHub repository tbhb/vale-ai-tells (87 stars, last pushed yesterday), licensed MIT. It adds 74 tokens to every session and 751 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 2026-08-30.
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…
humanizer
Humanize and de-slop AI-sounding prose while preserving meaning, specific detail, and genuine human quirks. When a voice sample or style profile is available, rewrite in that writer's actual voice. Remove recurring AI tells such as inflated significance, stock vocabulary, uniform rhythm, excessive hedging, formulaic…
authenticity-check
Score how authentically text reads as a real human author's work, flag spans that read as AI-generated, AI-templated, or generically derivative, and run a separate read-only scan for suspicious Unicode provenance carriers. Return an authenticity band, a 0-100 score, provenance signals, and span-level reasons. Use when…
ai-slop-detector
Universal prose audit. Scores writing on TWO axes — AI-Slop (does this read like AI wrote it?) and Comprehension (can a fresh reader follow this?). Use PROACTIVELY as a mandatory final QA pass on ANY prose generated for humans to read — every email (internal or external), proposal, report, status update, blog post…
humanizer-czech
Odstraň znaky AI-generovaného psaní z českého textu. Použij při editaci nebo revizi textu, aby zněl přirozeněji a lidštěji. Detekuje a opravuje 27 vzorců včetně: nafouklého významu, propagačního jazyka, anglického slovosledu, kalků, nominalizace, monotónního rytmu, nadužívání spojek, typických českých AI klišé…