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-fix-prose/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-fix-prose)<a href="https://agentmods.dev/skills/tbhb/vale-ai-tells/codex-fix-prose"><img src="https://agentmods.dev/badge/skills/tbhb/vale-ai-tells/codex-fix-prose/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-fix-prose"><img src="https://agentmods.dev/badge/skills/tbhb/vale-ai-tells/codex-fix-prose.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 | $0.00057 | $0.00567 |
| Opus 5 | $0.00028 | $0.00283 |
| Sonnet 5 | $0.00011 | $0.00113 |
| Haiku 4.5 | $0.00006 | $0.00057 |
Grade A, and why
codex-fix-prose 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
Orchestrate a prose fix
Keep findings and retries out of the parent context. Parse the request into a target and complete lint command, then run:
bash .agents/skills/codex-fix-prose/scripts/preflight.sh <target> <lint command>
Stop on BLOCKED. On PROCEED, create a plan with update_plan: baseline, writer, mechanical verification, independent review, final lint.
Record the baseline before delegation:
bash .agents/skills/codex-fix-prose/scripts/check-suppressions.sh --baseline <target>
Save the absolute state: path that command prints. It identifies this workflow and records its target. Until cleanup, the script refuses a second workflow on the same target. Pass the state to every delegated writer and reviewer in this run.
Delegate codex-write-prose-fix with fork_turns: "none". Give it only the repository root, target, workflow state, lint command, and instruction to follow that skill. Wait for its terminal report. Never edit the target in the parent.
Run check-suppressions.sh --verify <state> <target>. Any finding means the run isn't clean. Delegate codex-review-prose-fix with fork_turns: "none", giving it the repository root, target, and workflow state. If it returns changes required, save those findings in <state>/notes, delegate the writer again with the same minimal prompt, and repeat verification and review. Bound this writer/reviewer loop at three review rounds.
Finally run the complete lint command once in the parent. Always run check-suppressions.sh --cleanup <state> before returning once no delegated agent needs the state, even when the outcome is unresolved or blocked. Report PROSE: CLEAN only when the writer reported clean, the suppression check is silent, the independent reviewer returned REVIEW: CLEAN, and the final lint command passes. Otherwise return the short unresolved or blocked report. Mark each plan item as it completes.
Safety rules:
- Only the delegated writer may edit the target, and the target is the only file it may edit.
- Never change lint configuration, dictionaries, hooks, or suppression comments.
- Don't infer clean from silent output unless preflight proved the target has prose rules.
- Don't expose full lint findings in the parent response unless the workflow blocks and the operator needs a decision.
What ships with it
3 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.
- 11d ago First seen · 37 lines · 57 tokens per session scan A 7cf3ebd9c6b7
codex-fix-prose is a skill published in the GitHub repository tbhb/vale-ai-tells (92 stars, last pushed today), licensed MIT. It adds 57 tokens to every session and 567 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…
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…