Borrowing it
Nothing to install: this file belongs to CorvidLabs/agent-3md. 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/CorvidLabs/agent-3md/main/AGENTS.mdgit clone --depth 1 https://github.com/CorvidLabs/agent-3mdWrote 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/corvidlabs/agent-3md/agents-md)<a href="https://agentmods.dev/instructions/corvidlabs/agent-3md/agents-md"><img src="https://agentmods.dev/badge/instructions/corvidlabs/agent-3md/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/corvidlabs/agent-3md/agents-md"><img src="https://agentmods.dev/badge/instructions/corvidlabs/agent-3md/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 | $0.00442 | $0.00442 |
| Opus 5.5 | $0.00177 | $0.00177 |
| Sonnet 5.5 | $0.00088 | $0.00088 |
| Haiku 4.5 | $0.00044 | $0.00044 |
Grade A, and why
agent-3md 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 2mo 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.
What it actually says
agent-3md
One 3md file is a whole agent (identity plus on-demand skills). See README.md for the pitch and SPEC.md for the agent3md/1 format definition. The reference implementation is the TypeScript loader; Rust and Swift loaders prove the format ports.
Project map
src/runtime.ts- the reference loader (Agent: manifest / route / get / resolve).src/validate.ts- the agent3md/1 conformance validator.src/threemd.ts- the canonical 3md parser, vendored.src/cli.ts,src/mcp.ts,src/export.ts- CLI, MCP server, JSON projection.loaders/rust- the nativeagent3mdCLI (published to crates.io).loaders/swift- the Swift loader on the canonical ThreeMD package.specs/- the spec-sync contracts for the source modules.examples/conformance/- labeled valid/invalid vectors for any implementation.SPEC.md- the authoritative agent3md/1 specification.
Conventions
TypeScript is the reference and the package you embed; Rust is the default native
CLI. Default to Bun for the TypeScript toolchain (bun test, bun build,
bun install). Keep the three loaders behaviorally identical: routing,
validation, and dependency resolution must not diverge across languages.
CorvidLabs trust toolchain
This repository uses one trust gate. Every session must use it and must not bypass or weaken it.
- Run
fledge trust verifybefore calling a change complete. - Keep module specs synchronized with implementation changes.
- Treat an Augur block verdict as a hard stop that must be surfaced and de-risked.
- Record and verify provenance with Attest after the repository's verification lane passes.
- Keep generated trust configuration and this managed block in place.
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.
- 2mo ago First seen · 39 lines · 442 tokens per session scan A 9a8a470042e1
agent-3md AGENTS.md is an instructions file published in the GitHub repository CorvidLabs/agent-3md (1 stars, last pushed 5d ago), licensed MIT. It adds 442 tokens to every session, about $0.0018 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.
agent-3md AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| agent-3md AGENTS.mdCorvidLabs/agent-3md | Instructions file | 1 | 5d ago | MIT | A | 442 | 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 |