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 instructions/fendouai/huorengan/agents-mdgit clone --depth 1 https://github.com/fendouai/huorenganWrote 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/instructions/fendouai/huorengan/agents-md)<a href="https://agentmods.dev/instructions/fendouai/huorengan/agents-md"><img src="https://agentmods.dev/badge/instructions/fendouai/huorengan/agents-md.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 | $0.00576 | $0.00576 |
| Opus 5 | $0.00288 | $0.00288 |
| Sonnet 5 | $0.00115 | $0.00115 |
| Haiku 4.5 | $0.00058 | $0.00058 |
Grade A, and why
huorengan AGENTS.md 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 6d 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
活人感 huorengan is a bilingual (Chinese + English) AI-writing skill: it
removes AI tone (subtraction) and pulls the result toward a target human
voice (addition). Built on the engineering standard of
avoid-ai-writing with the Chinese completeness of shuorenhua.
What lives where
SKILL.md— the only rule entry point + mode contract. Bilingual prose.detector/— zero-dependency detection engine (Node ≥18 + browser).core/language-agnostic:router,stylometry,fingerprints,voice(addition layer),scoring(the ONE scorer).zh/anden/— symmetric per-language modules.CATEGORIES.md— anti-drift contract mappingtype↔ SKILL.md section.
references/— human-readable rule source (protected-spans, phrases, structures, scene-packs, voice-contract).policy/— scene × tier × voice as auditable.tomldata, not prose.evals/— benchmark (SF/SNF), real samples, voice samples, fixtures.plugins/,cursor-rules/,install/— platform packaging..refs/— local snapshots of the two parent projects for cross-checking (git-ignored).
Three contracts that must never drift
- One scorer.
scoreis computed only incore/scoring.js.fidelityis a gate, not a score.voice.driftis an independent dimension. Never mix them. - Count consistency. README's "N pattern categories" must equal the
detectable
###count in SKILL.md, and every detectortypemust be documented inCATEGORIES.md. CI (check-counts.sh,categories.test.js) enforces both. - Policy ↔ engine alignment. Names referenced in
policy/*.tomlmust exist in the engine enums;matrix.tomlmust cover every scene×tier cell. CI (check-policy.js) enforces this.
Modes (same as avoid-ai-writing, plus voice injection)
rewrite (default) / detect / edit. Every mode runs protected-spans
detection FIRST. voiceMode ≠ none injects voice-pull suggestions.
Related work
avoid-ai-writing(conorbronsdon) — engineering template + English rules.shuorenhua(MrGeDiao) — Chinese-first rule completeness.
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.
- 6d ago First seen · 46 lines · 576 tokens per session scan A 6eeff8fa222c
huorengan AGENTS.md is an instructions file published in the GitHub repository fendouai/huorengan (5 stars, last pushed 2mo ago), licensed MIT. It adds 576 tokens to every session, about $0.0029 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 instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.