Borrowing it
Nothing to install: this file belongs to hack-dance/hack. 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/hack-dance/hack/main/AGENTS.mdgit clone --depth 1 https://github.com/hack-dance/hackWrote 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/hack-dance/hack/agents-md)<a href="https://agentmods.dev/instructions/hack-dance/hack/agents-md"><img src="https://agentmods.dev/badge/instructions/hack-dance/hack/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/hack-dance/hack/agents-md"><img src="https://agentmods.dev/badge/instructions/hack-dance/hack/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 | $0.01155 | $0.01155 |
| Opus 5.5 | $0.00462 | $0.00462 |
| Sonnet 5.5 | $0.00231 | $0.00231 |
| Haiku 4.5 | $0.00115 | $0.00115 |
Grade A, and why
hack 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- hack CLAUDE.md — 92% identical, 92 lines differ
How it starts
The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Contributing to Hack
Scope and authority
Hack's supported product is the local-first CLI: project setup, container runtime, routing/TLS, environment management, host commands, lifecycle processes, sessions, diagnostics, daemon, and optional agent integrations.
Hosted account/auth/team flows, the web dashboard, Hack Tickets, and built-in GitHub/Linear integrations are retired. Remote/gateway/node/dispatch and the retained macOS app are unsupported; work on them only when explicitly requested. Do not add them to onboarding, default workflows, or core release requirements.
Preserve existing user changes. Infer routine details from the request and code; ask only when a gap blocks correctness or authority. Existing authorization covers the same action and scope. Honor read-only requests and native credential approvals. Publishing, production changes, destructive operations, and broader configuration changes still need authorization for their actual scope. Never bypass a protected branch or publishing gate merely to finish a task.
Source and conventions
src/,index.ts,packages/cli/: CLI and runtime code.src/agents/instruction-source.ts: canonical consumer guidance. Onboarding prompts live insrc/agents/onboarding-prompt.ts; client renderers own framing only.plugins/hack/: generated optional plugin bundle.docs/contains product docs.packages/db/andservices/: retained internal code; not default hosted dependencies.- For explicitly requested native work, read
apps/macos/AGENTS.md.
Use the Bun version pinned in package.json, and bun install --frozen-lockfile.
Use strict TypeScript, named option objects where they improve call clarity, and
unknown plus narrowing for untrusted values. Follow the repository's Biome/Ultracite
configuration rather than maintaining a second formatting specification here.
Prefer existing patterns and Bun APIs; do not migrate unrelated dependencies.
Keep src/commands/project.ts and src/commands/global.ts small: extract decision
logic into focused helpers with meaningful tests when complexity grows.
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 · +6 lines · +103 tokens per session 176863e4d99f
- 1mo ago Changed · -310 lines · -5,012 tokens per session bee77bf26fa5
- 2mo ago Changed · +1 lines · +31 tokens per session e1e2c6fcb31f
- 2mo ago First seen · 395 lines · 6,033 tokens per session scan A 734b6f02bc5a
hack AGENTS.md is an instructions file published in the GitHub repository hack-dance/hack (9 stars, last pushed today), licensed MIT. It adds 1,155 tokens to every session, about $0.0046 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.
hack AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| hack AGENTS.mdhack-dance/hack | Instructions file | 9 | today | MIT | A | 1,155 | 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 |