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/nisus74/humanise/claude-mdgit clone --depth 1 https://github.com/Nisus74/humaniseWrote 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/nisus74/humanise/claude-md)<a href="https://agentmods.dev/instructions/nisus74/humanise/claude-md"><img src="https://agentmods.dev/badge/instructions/nisus74/humanise/claude-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 | $0.01130 | $0.01130 |
| Opus 5 | $0.00565 | $0.00565 |
| Sonnet 5 | $0.00226 | $0.00226 |
| Haiku 4.5 | $0.00113 | $0.00113 |
Grade A, and why
humanise CLAUDE.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 5d 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Guidance for Claude (and contributors) working on humanise: an open-source skill that strips AI tells from writing and drafts in a specific person's voice. Cross-platform (Claude Code, Codex, Gemini, Cursor and more), shipped as a skill plus an npm CLI.
The one rule: body vs soul
- Body (engine):
skill/SKILL.md,skill/references/,skill/evals/,skill/agents/,skill/commands/,skill/scripts/. Universal and shared. Improve this. - Soul (profile):
skill/profile/holds a user's own soul, plus the voice corpus (flatsample-*.mdfiles) and fingerprint. Personal. Never commit aprofile/. Never put one person's voice into the engine. The repo shipsskill/profile.template/andskill/profile.example/only.
If a change only helps one person's writing, it's a profile change (their fork). If it helps everyone, it's an engine change (a PR).
Repo map
skill/: the source skill. This is what ships and installs.cli/: the zero-dependency Node CLI (bin/cli.js) and the provider map (providers.mjs).scripts/build.mjs: compilesskill/intodist/<provider>/.dist/is generated; never hand-edit it. Editskill/and rebuild.docs/:getting-started.md,claude-desktop.md,SETUP.md,body-and-soul.md,platforms.md,DEVELOP.md.- The detector is Python (
skill/evals/assertions/writing_checks.py), standard library only. The CLI shells to it; it is not ported to JS. - Tests and evals live in
skill/evals/assertions/:selftest.pyis the held-in battery (npm test);run_all.pyruns the fullevals.jsonsuite intobenchmark.json. (Top-leveltests/is a placeholder.) skill/config.example.yml: the per-user engine config to copy toskill/config.yml(gitignored). Sets dialect, register, channels and a custom slop overlay..claude-plugin/plugin.json: the plugin manifest. Release-critical; verify it and the per-harness skill paths before publishing.
The acceptance gate (read before changing the engine)
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.
- 5d ago First seen · 51 lines · 1,130 tokens per session scan A f7273b7bccc9
humanise CLAUDE.md is an instructions file published in the GitHub repository Nisus74/humanise (1 stars, last pushed 3d ago), licensed MIT. It adds 1,130 tokens to every session, about $0.0056 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
gortex CLAUDE.md
Claude Code instructions for zzet/gortex, covering gortex, build & test, codebase overview, discovery (read once, then keep using) and llm provider (powers ask and searchsymbols assist: modes).
ChatCrystal AGENTS.md
AGENTS.md instructions for ZengLiangYi/ChatCrystal, covering agents.md, project overview, commands, development (server port 3721 + client port 13721) and build for production.
agent-toolkit AGENTS.md
AGENTS.md instructions for ulises-jeremias/agent-toolkit, covering agents.md — ai agent contract, what this toolkit does, repository structure, operating rules and how to add a skill.
core-ai CLAUDE.md
Claude Code instructions for helius-labs/core-ai, covering core ai, compiler-managed sync, mcp server pin, skill versioning and router surface maintenance.
core-ai AGENTS.md
AGENTS.md instructions for helius-labs/core-ai, covering core ai — agent instructions, repository overview, mcp server setup, api key setup and public tool surface.
cursor-studio copilot-instructions.md
Copilot instructions for DearLicy/cursor-studio, a project described as: Local-first Windows control center for Cursor: manage AI providers, balances, usage and costs, sessions, prompts, MCP, Skills, appearance, and integrations. | Cursor 本地桌面管理工具.