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/naituw/askhuman/agents-mdgit clone --depth 1 https://github.com/Naituw/AskHumanWhat 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 | $0.00897 | $0.00897 |
| Opus 5 | $0.00449 | $0.00449 |
| Sonnet 5 | $0.00179 | $0.00179 |
| Haiku 4.5 | $0.00090 | $0.00090 |
Grade A, and why
AskHuman 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 3d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Before a complex task
Read docs/overview.md first to understand the architecture and project layout.
Its “文档边界” section defines what belongs in the main overview versus supplementary overview, spec, and plan documents.
When the task is complete, check whether the change made any overview or referenced spec inaccurate and update only the appropriate document; do not edit the main overview when the repository-wide map and invariants are unchanged.
Git worktree / parallel development
If the task needs a new or existing git worktree for parallel feature work on this repo (so install/AskHuman do not share the main daemon or overwrite another agent’s binary), read docs/agent-worktree-setup.md first and follow it—including asking the human via AskHuman whether to attach a channel preset—before coding. After dev enable, verification is still ./scripts/install.sh then AskHuman (auto-routed into that worktree’s Dev Instance).
Tracking unfinished work in docs/PROGRESS.md
docs/PROGRESS.md tracks durable unfinished or deferred work and concrete next steps across sessions. Read it before starting work. When a tracked item is completed, delete its section — history stays in git.
Verifying your changes
After making any change to this project's functionality or logic, verify the result by running the install script to compile the new code directly into your environment, then use the newly installed AskHuman for subsequent prompts:
# macOS / Linux
./scripts/install.sh
# Windows
./scripts/install-windows.cmd
Code comments
Write code comments in English.
Commit messages
Follow Conventional Commits. Release notes shown to end users are generated
automatically from these messages (git-cliff, see docs/specs/self-update.md), so
write them carefully — a sloppy feat/fix subject becomes a sloppy user-facing
changelog line.
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.
- 3d ago First seen · 77 lines · 897 tokens per session scan A 9514cdcb11af
AskHuman AGENTS.md is an instructions file published in the GitHub repository Naituw/AskHuman (140 stars, last pushed 13d ago), licensed MIT. It adds 897 tokens to every session, about $0.0045 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 2026-08-30.
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).
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.
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.