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.
npx agentmods add instructions/microsoft/agentrc/agents-mdgit clone --depth 1 https://github.com/microsoft/agentrcWhat 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 | $0.00868 | $0.00868 |
| Opus 5 | $0.00434 | $0.00434 |
| Sonnet 5 | $0.00174 | $0.00174 |
| Haiku 4.5 | $0.00087 | $0.00087 |
Grade A, and why
agentrc 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.
How it starts
The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AgentRC Copilot Instructions
@microsoft/agentrc is a CLI tool (and VS Code extension) that sets up repositories for AI-assisted development. It analyzes repos, generates instruction files, evaluates AI responses, and runs readiness reports.
Architecture
src/ # CLI entry point and commands
cli.ts # Commander program, withGlobalOpts helper
commands/ # Thin command wrappers (parse args → call services)
ui/ # Ink/React TUI components
packages/core/src/ # Shared services and utilities (bundled into dist)
services/ # analyzer, generator, instructions, readiness, policy, ...
utils/ # fs, output, logger, repo, pr
plugin/skills/ # Built-in skill markdown files (copied to dist/skills/ on build)
vscode-extension/ # See .github/instructions/vscode-extension.instructions.md
@agentrc/core (in packages/core/) is bundled into the CLI output — it is not an external npm package. Use the @agentrc/core/* path alias for all cross-package imports.
Build & Test
npm run build # tsup → dist/index.js (ESM, Node 20)
npm run dev # tsx src/index.ts (run from source)
npm run typecheck # tsc --noEmit
npm run lint # eslint
npm test # vitest run
npm run test:coverage # vitest run --coverage
Output is ESM ("type": "module"). All node_modules are external except @agentrc/core, @github/copilot-sdk, and vscode-jsonrpc (bundled via noExternal in tsup.config.ts).
SDK shim:
tsup.config.tspatchesgetBundledCliPath()in the Copilot SDK. An identical shim lives invscode-extension/esbuild.mjs— update both together if SDK internals change.
Command Pattern
Commands in src/commands/ are thin wrappers:
- Resolve paths and options
- Call services from
@agentrc/core/services/* - Write output using the output utilities
Wrap every command action with withGlobalOpts (from src/cli.ts) so --json, --quiet, and --accessible are merged into the options object.
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.
- 2d ago First seen · 68 lines · 868 tokens per session scan A 76c58039219b
agentrc AGENTS.md is an instructions file published in the GitHub repository microsoft/agentrc (1,035 stars, last pushed 6d ago), licensed MIT. It adds 868 tokens to every session, about $0.0043 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 2026-08-30.
Other instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
buildNext
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
Instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
Instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.