agentmods.dev

humanize-text-skill: Instructions file for Codex

AGENTS.md

humanize-text-skill AGENTS.md is an instructions file for Codex, OpenCode from lynote-ai/humanize-text-skill. It costs 389 tokens per session, scanned A, original, MIT.

A bilingual writing skill for making text sound more human and matching a requested voice. It includes rules, policies, examples, and an analysis tool for detecting patterns associated with AI-written prose.

In plain words
What is it for?
Use it to revise English or Chinese writing, remove templated phrasing, apply a target voice, and check whether the revision has drifted from the source.
Why use it?
It helps reduce formulaic wording while preserving the original meaning and keeping the chosen style consistent.

Instructions file for CodexOpenCode

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

This is lynote-ai/humanize-text-skill's own configuration. It tells Codex and OpenCode how to work on humanize-text-skill 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 humanize-text-skill configures →

not rated 242repo 4mo ago A scan 389 tokens original MIT
View source ↗ lynote-ai/humanize-text-skill lynote.ai
Reuse

Borrowing it

Nothing to install: this file belongs to lynote-ai/humanize-text-skill. 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/lynote-ai/humanize-text-skill/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/lynote-ai/humanize-text-skill

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 humanize-text-skill AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/lynote-ai/humanize-text-skill/agents-md/github.svg)](https://agentmods.dev/instructions/lynote-ai/humanize-text-skill/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/lynote-ai/humanize-text-skill/agents-md"><img src="https://agentmods.dev/badge/instructions/lynote-ai/humanize-text-skill/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 humanize-text-skill AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/lynote-ai/humanize-text-skill/agents-md"><img src="https://agentmods.dev/badge/instructions/lynote-ai/humanize-text-skill/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 389 This file is loaded in full into every session.
When invoked 389 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 $0.00389 $0.00389
Opus 5.5 $0.00156 $0.00156
Sonnet 5.5 $0.00078 $0.00078
Haiku 4.5 $0.00039 $0.00039

Measured 2mo ago against content hash 2cb511425ef3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

humanize-text-skill 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 · 33 lines

What it actually says

AGENTS.md

humanize-text-skill is a bilingual AI-writing skill for two linked tasks:

  • subtraction: remove AI-shaped tone and templated phrasing
  • addition: pull the result toward a target human voice

The project combines the engineering discipline of avoid-ai-writing with the Chinese coverage depth inspired by shuorenhua.

Repository layout

  • SKILL.md is the single rule entry point and mode contract.
  • detector/ contains the zero-dependency engine for Node >=18 and browser use.
  • references/ stores the human-readable rule source.
  • policy/ stores scene, tier, and voice policy as auditable .toml data.
  • evals/ stores benchmark cases, fixtures, and voice samples.
  • plugins/, cursor-rules/, and install/ hold platform packaging and setup guidance.

Non-drifting contracts

  1. One scorer: score is computed only in detector/core/scoring.js. fidelity is a gate, not a score. voice.drift is independent.
  2. Count consistency: the README pattern-category count must match the detectable ### count in SKILL.md, and every detector type must be documented in detector/CATEGORIES.md.
  3. Policy alignment: names referenced in policy/*.toml must exist in engine enums, and matrix.toml must cover every scene-by-tier cell.

Modes

rewrite is the default mode. detect audits without rewriting. edit performs minimal in-place changes. Every mode runs protected-span detection first. Any voiceMode other than none enables voice-pull suggestions.

  • avoid-ai-writing by conorbronsdon
  • shuorenhua by MrGeDiao
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 · 33 lines · 389 tokens per session scan A 2cb511425ef3

Subscribe to this mod's changes

humanize-text-skill AGENTS.md is an instructions file published in the GitHub repository lynote-ai/humanize-text-skill (242 stars, last pushed 4mo ago), licensed MIT. It adds 389 tokens to every session, about $0.0016 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 2026-08-30.

Writing and docsai-content-humanizerai-detection-bypasserai-humanizerai-toolshumanizehumanize-text
Related

humanize-text-skill AGENTS.md compared with instructions from other repositories

humanize-text-skill AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
humanize-text-skill AGENTS.mdlynote-ai/humanize-text-skillInstructions file2424mo agoMITA389Codex, OpenCode
vibetags com-example-config-AsyncTestConfig.instructions.mdPIsberg/vibetagsInstructions file25yesterdayMITA82GitHub Copilot
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot