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 commands/ofershap/ai-humanizer/auditgit clone --depth 1 https://github.com/ofershap/ai-humanizerWhat 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 | $0.00020 | $0.00357 |
| Opus 5 | $0.00010 | $0.00179 |
| Sonnet 5 | $0.00004 | $0.00071 |
| Haiku 4.5 | $0.00002 | $0.00036 |
Grade A, and why
audit 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 2d 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
Scan the current project for AI fingerprints that detectors and experienced developers would flag.
Check these file types: README.md, CHANGELOG.md, docs/, *.md, code comments, package.json descriptions, PR templates.
For each file, look for:
- Em dashes (—) used as separators
- Flagged vocabulary: delve, tapestry, leverage, utilize, facilitate, streamline, paramount, pivotal, meticulous, holistic, robust, comprehensive, multifaceted, harness, foster, bolster, seamless, cutting-edge, game-changing, revolutionary, groundbreaking, nuanced, intricate, elevate, empower, unleash
- AI opening/closing cliches: "In today's...", "It's worth noting...", "In summary...", "Happy coding!"
- Narrating code comments: comments that describe what the next line does instead of why
- Over-formatting: bold-label bullets, uniform list lengths, excessive markdown
- Low burstiness: 4+ consecutive sentences of similar length
- AI git metadata: Co-authored-by trailers for AI tools in recent commits
For each finding:
- Show the file and line
- Quote the problematic text
- Suggest a human-sounding replacement
- Rate: high (em dashes, flagged words, git trailers) / medium (cliches, over-formatting) / low (burstiness, minor style)
After the scan, show a summary count by category.
Use the ai-humanizer skill for the full reference of patterns to check.
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.
- 2d ago First seen · 36 lines · 20 tokens per session scan A 699763cc22af
audit is a command published in the GitHub repository ofershap/ai-humanizer (4 stars, last pushed 6mo ago), licensed MIT. It adds 20 tokens to every session and 357 once invoked, about $0.0001 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 commands, from other repositories
deai-fix
中文书稿去 AI 味 · 按诊断报告执行修改.
deai
中文书稿去 AI 味 · 全流程精修（砍→改→调→验→读）.
deai-scan
中文书稿去 AI 味 · 只体检不改（生成诊断报告）.
audit
Аудит текста на признаки AI без правки (сканер + разбор по скиллу).
review
Review the current diff for violations of the conventions in AGENTS.md and .cursor/rules/. Report findings ordered by severity; do not fix anything unless asked.
humanize
Очеловечить русский ИИ-текст: найти следы машинной генерации и переписать естественным языком.