agentmods.dev

huorengan: Instructions file for Codex

AGENTS.md

huorengan AGENTS.md is an instructions file for Codex, OpenCode from fendouai/huorengan. It costs 576 tokens per session, scanned A, original, MIT.

A project instruction file for huorengan, a bilingual writing tool that removes machine-like wording and adapts text toward a chosen human voice.

In plain words
What is it for?
Use it to guide work on the huorengan project, including its English and Chinese writing rules, detection engine, voice handling, scoring, tests, and integrations.
Why use it?
It explains where the project's code, rules, language files, tests, and platform packages belong, and which internal agreements must stay consistent.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md.

This is fendouai/huorengan's own configuration. It tells Codex and OpenCode how to work on huorengan itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything huorengan configures →

not rated 5repo 4mo ago A scan 576 tokens original MIT
View source ↗ fendouai/huorengan
Reuse

Borrowing it

Nothing to install: this file belongs to fendouai/huorengan. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/fendouai/huorengan/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/fendouai/huorengan

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for huorengan AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/fendouai/huorengan/agents-md/github.svg)](https://agentmods.dev/instructions/fendouai/huorengan/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/fendouai/huorengan/agents-md"><img src="https://agentmods.dev/badge/instructions/fendouai/huorengan/agents-md/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.

agentmods 80×15 button for huorengan AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/fendouai/huorengan/agents-md"><img src="https://agentmods.dev/badge/instructions/fendouai/huorengan/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 576 This file is loaded in full into every session.
When invoked 576 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00576 $0.00576
Opus 5.5 $0.00230 $0.00230
Sonnet 5.5 $0.00115 $0.00115
Haiku 4.5 $0.00058 $0.00058

Measured 2mo ago against content hash 6eeff8fa222c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 2mo 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.

AGENTS.md · 46 lines

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/ and en/ — symmetric per-language modules.
    • CATEGORIES.md — anti-drift contract mapping type ↔ SKILL.md section.
  • references/ — human-readable rule source (protected-spans, phrases, structures, scene-packs, voice-contract).
  • policy/ — scene × tier × voice as auditable .toml data, 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

  1. One scorer. score is computed only in core/scoring.js. fidelity is a gate, not a score. voice.drift is an independent dimension. Never mix them.
  2. Count consistency. README's "N pattern categories" must equal the detectable ### count in SKILL.md, and every detector type must be documented in CATEGORIES.md. CI (check-counts.sh, categories.test.js) enforces both.
  3. Policy ↔ engine alignment. Names referenced in policy/*.toml must exist in the engine enums; matrix.toml must 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.

  • avoid-ai-writing (conorbronsdon) — engineering template + English rules.
  • shuorenhua (MrGeDiao) — Chinese-first rule completeness.

Read the full file on GitHub · 46 lines

Changes

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.

  1. 2mo ago First seen · 46 lines · 576 tokens per session scan A 6eeff8fa222c

Subscribe to this mod's changes

huorengan AGENTS.md is an instructions file published in the GitHub repository fendouai/huorengan (5 stars, last pushed 4mo ago), licensed MIT. It adds 576 tokens to every session, about $0.0023 per session on Opus 5.5. 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.

Writing and docs
Related

huorengan AGENTS.md compared with instructions from other repositories

huorengan AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
huorengan AGENTS.mdfendouai/huorenganInstructions file54mo agoMITA576Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file275k3d agoMITA4,313Codex, OpenCode