agentmods.dev

agent-3md AGENTS.md

Project instructions for agent-3md, a format where one Markdown file describes an AI agent and its on-demand skills. The project includes TypeScript, Rust, and Swift loaders, which read and validate that format.

In plain words
What is it for?
Use it when working on the agent-3md loader, validator, command-line tool, MCP server, examples, or its specification and tests.
Why use it?
It gives coding agents a map of the project, its conventions, and the requirement that the different loaders behave alike.

Instructions file for CodexOpenCode

1 1mo ago A scan 442 tokens original MIT
View the source file CorvidLabs/agent-3md
Install

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.

agentmods
npx agentmods add instructions/corvidlabs/agent-3md/agents-md
Clone the repo
git clone --depth 1 https://github.com/CorvidLabs/agent-3md

Made for: Codex, OpenCode.

Per session 442 This file is loaded in full into every session.
When invoked 442 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00442 $0.00442
Opus 5 $0.00221 $0.00221
Sonnet 5 $0.00088 $0.00088
Haiku 4.5 $0.00044 $0.00044

Measured 2d ago against content hash 9a8a470042e1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 2d 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.

AGENTS.md · 39 lines

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 native agent3md CLI (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 verify before 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.
Changes

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.

  1. 2d ago First seen · 39 lines · 442 tokens per session scan A 9a8a470042e1

Subscribe to this mod's changes

agent-3md AGENTS.md is an instructions file published in the GitHub repository CorvidLabs/agent-3md (1 stars, last pushed 1mo ago), licensed MIT. It adds 442 tokens to every session, about $0.0022 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 2026-08-31.

Building agentsLLMagent-frameworkagentsai-agentsbunfile-format
Related

Other instructions, from other repositories

agent-framework copilot-instructions.md

Instructions for microsoft/agent-framework, covering github copilot instructions, repository structure and architectural decision records (adrs).

microsoft/agent-framework · 211 tokens

agent-framework python.instructions.md

Instructions for microsoft/agent-framework: See AGENTS.md for project structure and package documentation. Detailed conventions are in the agent skills under .github/skills/.

microsoft/agent-framework · 110 tokens

opengeni AGENTS.md

Instructions for Cloudgeni-ai/opengeni, covering agent / automation notes (opengeni), full local stack, architecture notes, pull-request delivery across moving main and keeping these notes current.

Cloudgeni-ai/opengeni · 21,782 tokens

LeAgent AGENTS.md

Instructions for vixues/LeAgent, covering leagent development guidelines, project overview, architecture, execution topology (one kernel, many ingresses) and surface map (where things live).

vixues/LeAgent · 6,799 tokens

semantix CLAUDE.md

Instructions for Gnosil/semantix, covering 项目规则（claude code） and 1. 改动须经用户过目；由 claude 提交到分支 + pr，用户 review 后合并.

Gnosil/semantix · 301 tokens

sixb AGENTS.md

Instructions for sixb-ai/sixb, covering agents.md, scope, repo map, toolchain and core commands.

sixb-ai/sixb · 3,044 tokens