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-review-pr-description/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-review-pr-description)<a href="https://agentmods.dev/skills/tbhb/vale-ai-tells/codex-review-pr-description"><img src="https://agentmods.dev/badge/skills/tbhb/vale-ai-tells/codex-review-pr-description/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-review-pr-description"><img src="https://agentmods.dev/badge/skills/tbhb/vale-ai-tells/codex-review-pr-description.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 | $0.00060 | $0.00402 |
| Opus 5 | $0.00030 | $0.00201 |
| Sonnet 5 | $0.00012 | $0.00080 |
| Haiku 4.5 | $0.00006 | $0.00040 |
Grade A, and why
codex-review-pr-description 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 11d 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
Review a pull request description
Act as an independent reviewer. Don't edit PR_AGENTDESC.md or rely on the writer's explanation.
Clear any older review before reading:
bash .agents/skills/codex-pr/scripts/record-review.sh <repo root> clear
The argument is the repository root. Default to the current directory. Read the draft, its base: field, <base>..HEAD commit messages, <base>...HEAD name-status and diff, and .github/pull_request_template.md. A missing draft or empty branch is a finding.
Don't repeat mechanical validator rules. Judge:
- truthfulness: the branch supports each claim and each verification command
- substance: sections answer the template rather than restating the diff
- fit: title, summary, labels, and draft status cover the whole branch
- coherence: the branch forms one mergeable and revertible change
- prose integrity: omit counts and selling language, along with process, model, and tool provenance
Name exact offending text and a specific correction. Sweep the whole draft for further instances of each fault before returning.
If the draft passes, record the exact reviewed bytes yourself:
bash .agents/skills/codex-pr/scripts/record-review.sh <repo root>
Then return only:
VERDICT: PASS
Otherwise leave the digest cleared. Return only:
VERDICT: CHANGES REQUIRED
1. [truthfulness|substance|fit|coherence] <problem>
text: <exact text>
fix: <specific correction>
What ships with it
1 file 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.
- 11d ago First seen · 50 lines · 60 tokens per session scan A 4c8935eac7a0
codex-review-pr-description is a skill published in the GitHub repository tbhb/vale-ai-tells (92 stars, last pushed yesterday), licensed MIT. It adds 60 tokens to every session and 402 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…
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…
voice-critic
Skill "voice-critic" from petar-djukic/writing-skills, covering voice critic (read-only gatekeeper), the five dimensions, snark scale and hard rules (constitution §4), judged vs computed, and the judge's leash and the unhedged-prediction work list (for inject-vernacular).
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…