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/nerds-odd-e/doughnut/agents-mdgit clone --depth 1 https://github.com/nerds-odd-e/doughnutWhat 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 | $0.01471 | $0.01471 |
| Opus 5 | $0.00736 | $0.00736 |
| Sonnet 5 | $0.00294 | $0.00294 |
| Haiku 4.5 | $0.00147 | $0.00147 |
Grade A, and why
doughnut 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Index for Codex and other AI coding agents. Skill contracts: .agents/skills/; rules: .cursor/rules/.
Donut is a Personal Knowledge Management tool combining zettelkasten-style note capture, spaced repetition, and knowledge sharing.
Start with .cursor/agent-map.md for repo navigation, generated API guidance, focused commands, service assumptions, and default indexing notes.
Run repo tooling with CURSOR_DEV=true nix develop -c … unless documented otherwise (e.g. Cloud VM). Git commands do not need the Nix prefix — run git directly.
Repo conventions live in .cursor/rules/. Cursor injects alwaysApply: true rules automatically. Codex / Claude Code: read these always-applied rules before coding — general.mdc, error-handling.mdc, unit-testing.mdc, planning.mdc, gsd-coexistence.mdc, architecture-decisions.mdc — then the stack file for the area you touch: frontend → frontend.mdc; backend → backend.mdc; E2E → e2e-authoring.mdc; lint → linting_formating.mdc; migrations → db-migration.mdc; MCP → mcp-server.mdc; CLI → cli.mdc. Do not search for other names first. Cursor auto-attaches globbed detail files when matching files are in context.
For local MySQL or Redis failures, inspect mysql/mysql.log or redis/redis.log; the Nix shell setup is defined by process-compose.yaml and scripts/shell_setup.sh.
Planning lives under .planning/ (GSD + local). Canonical coexistence:
.cursor/rules/gsd-coexistence.mdc. Slice quality: .cursor/rules/planning.mdc.
Do not put new plans under ongoing/. Test-optimization candidates live in .planning/test-optimization-blacklist.md.
Principles
Portable digest (details live in the cited always-applied rules — keep AGENTS.md and CLAUDE.md in sync):
- High cohesion — one concept, one place (
general.mdc) - Keep it simple — minimum code; no defensive programming (
general.mdc) - Capability naming — no GSD phase numbers in product artifacts (
general.mdc,planning.mdc) - Test observables via high-level entry points (
unit-testing.mdc) - Never silently swallow failures — prevent → propagate → enrich → deliberate catch (
error-handling.mdc)
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 · 54 lines · 1,471 tokens per session scan A 5abd322a49d5
doughnut AGENTS.md is an instructions file published in the GitHub repository nerds-odd-e/doughnut (49 stars, last pushed 2d ago), licensed MIT. It adds 1,471 tokens to every session, about $0.0074 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
spec-kit AGENTS.md
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.
vscode buildNext.instructions.md
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).
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.
langchain AGENTS.md
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.
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).
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.