Borrowing it
Nothing to install: this file belongs to nerds-odd-e/doughnut. 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/nerds-odd-e/doughnut/main/CLAUDE.mdgit clone --depth 1 https://github.com/nerds-odd-e/doughnutWrote 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/nerds-odd-e/doughnut/claude-md)<a href="https://agentmods.dev/instructions/nerds-odd-e/doughnut/claude-md"><img src="https://agentmods.dev/badge/instructions/nerds-odd-e/doughnut/claude-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/nerds-odd-e/doughnut/claude-md"><img src="https://agentmods.dev/badge/instructions/nerds-odd-e/doughnut/claude-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 | $0.02203 | $0.02203 |
| Opus 5.5 | $0.00881 | $0.00881 |
| Sonnet 5.5 | $0.00441 | $0.00441 |
| Haiku 4.5 | $0.00220 | $0.00220 |
Grade A, and why
doughnut CLAUDE.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 18d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Repository instructions for Claude Code and other AI coding agents.
Donut is a Personal Knowledge Management tool combining zettelkasten-style note capture, spaced repetition, and knowledge sharing.
Consult .agents/agent-map.md when you need repository entry points, generated API guidance, focused commands, service assumptions, or 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 .agents/skills/ as Agent Skills. Always-on skills for every coding session: unit-testing. Then the stack skill for the area you touch: frontend → frontend; backend → backend; E2E → e2e-authoring; lint → linting_formating; migrations → db-migration; MCP → mcp-server; CLI → cli. Do not search for other names first. Path-scoped skills (frontend-component, backend-testing, and so on) attach 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/. Decomposition and slice quality:
.agents/skills/dough-story-decomposition/references/problem-decomposition.md; planning artifacts and lifecycle:
.agents/skills/dough-story-refinement/references/planning.md.
Do not put new plans under ongoing/. Test-optimization candidates live in .planning/test-optimization-candidates.md.
Principles
Portable digest (details live in the cited skills — keep AGENTS.md and CLAUDE.md in sync):
- High cohesion — one concept, one place (
dough-post-change-refactorskill) - Keep it simple — minimum code; no defensive programming (
dough-post-change-refactorskill) - Capability naming — no planning sequence numbers in product artifacts (
dough-story-refinementplanning reference) - Test observables via high-level entry points (
unit-testingskill) - Failure handling — fail loudly is legitimate; catch for a business outcome or a clearer message (ADR 0006)
- Prefer committing all changes and leaving none local; partial commits are deliberate exceptions, not forbidden
- Removals leave no trace — when removing something:
- Delete it outright and transitively: the thing, its tests, and everything only it used (services, endpoints, DTOs, columns, helpers, fixtures, prompts, mocks, ratchet entries), repeated until nothing is orphaned. Shared code that other callers use stays.
- Sweep the whole product: backend, frontend, CLI, MCP, docs, code comments, agent guidance, and generated artifacts read as if the thing never existed.
- Leave no trace: no check that it is absent, no "never happens" test, no runtime guard against its return, no "no longer" or "used to" note. Git history is the record.
- Proof of a removal: the retained or replacement tests of the behavior that survives, plus a one-time sweep reading at acceptance (a search for the removed names over the product returns nothing), recorded in the plan as a reading, not as a test. Apart from that reading, the proof names nothing about the removed thing (
unit-testingskill). - Proof-item handoff: classify each item by the surviving behavior or active refusal it proves; carry that proof consistently through the proof table, slice Proof, and implementation brief, with the sweep separate. Correct inherited removal assertions before delegation; a scope paragraph alone does not correct them (
unit-testingskill). - Dated evidence: preserve the provenance (including dates and revisions), inputs, actions, results, and limitations of retained observations. Delete obsolete dependent evidence and repair its consumers under an accepted disposition; never rename an observed action solely to clear a sweep. An unresolved retention decision stays with its owner.
- Every role: refinement and planning state a removal as deletion plus sweep, never as a promise that something will not happen; an implementer, refactor agent, or coordinator who meets a step that asks for a trace skips it and reports that; a retrospective treats a trace as a finding.
- A refusal the product actively enforces (for example, a non-owner cannot edit a notebook) is not a removal; its tests stay.
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.
- 18d ago Changed · +2 lines · +122 tokens per session 9d65fed6cf98
- 19d ago Changed · +1 lines · +71 tokens per session 66f71211bfe0
- 26d ago Changed · +6 lines · +239 tokens per session 58513135fd06
- 1mo ago Changed · +8 tokens per session 85072109f73e
- 1mo ago Changed · +41 tokens per session 7d82d92962b6
- 1mo ago Changed · +2 lines · +59 tokens per session 5f511ede463e
- 1mo ago Changed · +13 lines · +386 tokens per session 42139f53f2d7
- 1mo ago Changed · +33 tokens per session 2e55d9a71106
- 1mo ago Changed · +8 tokens per session e3c67a6b6b61
- 1mo ago First seen · 46 lines · 1,236 tokens per session scan A 0fe181f1be61
doughnut CLAUDE.md is an instructions file published in the GitHub repository nerds-odd-e/doughnut (50 stars, last pushed today), licensed MIT. It adds 2,203 tokens to every session, about $0.0088 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.
Other instructions, from other repositories
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).
next.js AGENTS.md
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, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.