Borrowing it
Nothing to install: this file belongs to Naituw/AskHuman. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Naituw/AskHuman/main/AGENTS.mdgit clone --depth 1 https://github.com/Naituw/AskHumanWrote 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/naituw/askhuman/agents-md)<a href="https://agentmods.dev/instructions/naituw/askhuman/agents-md"><img src="https://agentmods.dev/badge/instructions/naituw/askhuman/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.
<a href="https://agentmods.dev/instructions/naituw/askhuman/agents-md"><img src="https://agentmods.dev/badge/instructions/naituw/askhuman/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.01304 | $0.01304 |
| Opus 5.5 | $0.00522 | $0.00522 |
| Sonnet 5.5 | $0.00261 | $0.00261 |
| Haiku 4.5 | $0.00130 | $0.00130 |
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 — 95 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, run ./scripts/install.sh and verify through the project askhuman-dev MCP’s dev_ask (or node scripts/dev.mjs ask for CLI). Ordinary discussion, approvals and handoff continue through the normal AskHuman connection.
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:
For an enabled Dev Instance, use the explicit verification flow above; ordinary discussion continues through the normal AskHuman connection.
# macOS / Linux
./scripts/install.sh
# Windows
./scripts/install-windows.cmd
Before a long build or test
Before ./scripts/install.sh, cargo test, cargo clippy or xcodebuild, run node scripts/machine-health.mjs. If it exits 2 (the machine is thrashing) the same job takes 10–25 minutes instead of 1–3, so tell the human through AskHuman with its report and ask them to free memory, run the job in the background and poll it in short slices that say what is being waited on, and never wait silently.
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 Changed · +4 lines · +110 tokens per session 6c9f8dbd555e
- 5d ago Changed · +3 lines · +51 tokens per session bcc1ddced61c
- 7d ago Changed · +7 lines · +81 tokens per session baec486ddb5f
- 15d ago Changed · +4 lines · +165 tokens per session c2d6147ab97f
- 2mo 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 (148 stars, last pushed yesterday), licensed MIT. It adds 1,304 tokens to every session, about $0.0052 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.
AskHuman AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| AskHuman AGENTS.mdNaituw/AskHuman | Instructions file | 148 | yesterday | MIT | A | 1,304 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |