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/jaredglaser/donetick-mcp/claude-mdgit clone --depth 1 https://github.com/jaredglaser/donetick-mcpWrote 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/jaredglaser/donetick-mcp/claude-md)<a href="https://agentmods.dev/instructions/jaredglaser/donetick-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/jaredglaser/donetick-mcp/claude-md.svg" alt="Measured on agentmods" 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 | $0.03193 | $0.03193 |
| Opus 5 | $0.01597 | $0.01597 |
| Sonnet 5 | $0.00639 | $0.00639 |
| Haiku 4.5 | $0.00319 | $0.00319 |
Grade A, and why
donetick-mcp 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 5d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Operating rules for an agent working in donetick-mcp, a stdio MCP server on Bun that manages chores on a self-hosted Donetick instance.
Critical rules
-
Imports. Use
@/for anything undersrc/. Inside a__tests__/directory, use a relative import for a sibling under test (../index,../read) and@/for anything outside that directory. Never mix the two styles in a single non-test file; production code always uses@/. -
Testing. Tests live in
__tests__/co-located with the source they cover, usebun:test, and run withbun test --isolate. Never sleep in a test. Every module that depends on time takes an injected clock (anow: () => Dateornow: () => number) precisely so a test can pass a fixed instant instead of waiting on a real one. A test that cannot fail is worse than none, because it reports coverage that does not exist. After writing one, revert the behavior it covers and confirm it fails. -
I/O boundaries, under
src/.src/client.tsis the only module that touches the network.src/cache.tsandsrc/probe.tsare the only ones that hold state, and both hold it in an instance created once at startup, never at module scope. Every other module takes its clock and its data as arguments and holds nothing.scripts/is outside this: it fetches and keeps state directly, because it is a CLI and not the server. -
MCP boundary. Only
src/index.tsmay import@modelcontextprotocol/server. Tool definitions elsewhere are plain data: a name, a description, a zod raw shape for the input, and a handler function. Anything constructed inside the server factory insrc/index.tshas per-connection lifetime, so theDonetickServiceand its caches are built once outside the factory and closed over, not rebuilt per connection. -
Never guess a wire field name. Donetick's internal
/api/v1ships a swaggo spec atdocs/swagger.json, with abasePathof/api/v1and its Swagger UI mounted by default on a self-hosted instance, but the spec lies: it omitsincludeSubtasks,syncVersion,actionOptionsanddraftId; it marksisPrivaterequired when Donetick accepts its absence; and it states a 0..5 priority bound onPUT /choreswhile missing the real 0..4 bound Donetick enforces onPUT /chores/:id/priority. It carries no behavioral semantics at all. A wrong field name on a write often produces a 200 with the wrong effect rather than an error, so checksrc/types.ts,src/endpoints.ts, and, when in doubt, the live instance before trusting a guess. A bound enforced on input is not enforced on data already stored. Whatever the input schema refuses, the checks that read a stored shape must refuse too.
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.
- 5d ago First seen · 84 lines · 3,193 tokens per session scan A fc4790a5330f
donetick-mcp CLAUDE.md is an instructions file published in the GitHub repository jaredglaser/donetick-mcp (0 stars, last pushed 27d ago), licensed Apache-2.0. It adds 3,193 tokens to every session, about $0.0160 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.
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).
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.
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
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.
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.
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.