Borrowing it
Nothing to install: this file belongs to paleo/alignfirst. 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/paleo/alignfirst/main/AGENTS.mdgit clone --depth 1 https://github.com/paleo/alignfirstWrote 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/paleo/alignfirst/agents-md)<a href="https://agentmods.dev/instructions/paleo/alignfirst/agents-md"><img src="https://agentmods.dev/badge/instructions/paleo/alignfirst/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/paleo/alignfirst/agents-md"><img src="https://agentmods.dev/badge/instructions/paleo/alignfirst/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 | $0.00869 | $0.00869 |
| Opus 5.5 | $0.00348 | $0.00348 |
| Sonnet 5.5 | $0.00174 | $0.00174 |
| Haiku 4.5 | $0.00087 | $0.00087 |
Grade A, and why
alignfirst 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 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.
Repository Guidelines
Start every session with the project context
Run npx -y alignfirst context from the repository root as your first command in the session. It prints the project conventions (ticket IDs, branch names, commits), the documentation map, and the AlignFirst protocols.
Tooling
Package manager: npm workspaces (root package.json declares "workspaces": ["packages/*"]).
Runtime: Node 26 (.nvmrc). ESM only ("type": "module").
Language: TypeScript with strict: true, module: NodeNext. Each package has a tsconfig.build.json (emits dist/) and a tsconfig.json (noEmit, includes src + test).
Linter / formatter: Biome (biome.json at root). npm run lint / npm run lint:fix.
Test runner: Vitest (vitest run). Per-package: npm test --workspace <name>. All packages: npm test. Suites that build and spawn real CLIs run separately through npm run test:integration.
Model-test policy: OpenClaw conversation-model scenarios are opt-in validation only when changed code, playbook, fixtures, dependencies or an upgrade has a concrete reason to affect AlignDev behavior with OpenClaw. They are not routine build/test hygiene for unrelated workspace, CLI or docs-only changes. Record the expected impact and reason before running a few representative targeted scenarios; never run the full matrix by default. Investigate and fix unexpected errors before any justified expansion of scenarios, surfaces or iterations. Use only Terra for conversation-model tests and Haiku through OpenRouter for the judge. The Anthropic and Z.AI keys are not provisioned; their providers stay in the test config as examples. Ordinary automated unit/integration tests and manual CLI checks remain unaffected. See Running the OpenClaw Tests.
Releases: Changesets (.changeset/). Base branch: main. Default access: public. Stable releases publish from CI through npm trusted publishing — see docs/releasing.md. For local opt-in previews, see docs/publishing-previews.md.
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 Changed · -8 lines · -199 tokens per session 75eb40c7621f
- 7d ago Changed · -56 tokens per session f3b77a7eb038
- 9d ago Changed · +2 lines · +147 tokens per session d2e058cebe7b
- 15d ago Changed · +65 tokens per session 23f4cbe00f57
- 17d ago Changed · -2 lines · +86 tokens per session fa5dca255799
- 19d ago Changed · -1 tokens per session 9a3e77397e61
- 21d ago Changed · +16 tokens per session 285503f42797
- 27d ago Changed · -2 tokens per session 3d494a9b0150
- 1mo ago Changed · +8 tokens per session 79dc02261595
- 1mo ago First seen · 59 lines · 805 tokens per session scan A fbf8d664ea38
alignfirst AGENTS.md is an instructions file published in the GitHub repository paleo/alignfirst (89 stars, last pushed 5d ago), licensed CC0-1.0. It adds 869 tokens to every session, about $0.0035 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.
alignfirst AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| alignfirst AGENTS.mdpaleo/alignfirst | Instructions file | 89 | 5d ago | CC0-1.0 | A | 869 | 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 |