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/teamnickhart/md2do/claude-mdgit clone --depth 1 https://github.com/TeamNickHart/md2doWrote 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/teamnickhart/md2do/claude-md)<a href="https://agentmods.dev/instructions/teamnickhart/md2do/claude-md"><img src="https://agentmods.dev/badge/instructions/teamnickhart/md2do/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 | $0.00787 | $0.00787 |
| Opus 5 | $0.00394 | $0.00394 |
| Sonnet 5 | $0.00157 | $0.00157 |
| Haiku 4.5 | $0.00079 | $0.00079 |
Grade A, and why
md2do 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
md2do — Claude Instructions
Repository
pnpm monorepo. Packages: core, cli, config, todoist, mcp, vscode, obsidian.
pnpm build # build all packages
pnpm -r run test:run # run all tests
pnpm lint # lint all packages
pnpm typecheck # typecheck all packages
Release Process
The only correct release flow is via publish.yml + changesets. Do not create GitHub Releases manually.
Steps
-
Include a changeset in every feature PR that changes published packages:
pnpm changeset # select affected packages, choose bump type, write summary # commit the generated .changeset/*.md file with the PR -
Merge the feature PR to main. The
publish.ymlworkflow runs automatically and opens a "chore: version packages" PR with all version bumps and CHANGELOG entries applied. -
Merge the version PR.
publish.ymldetects no changeset files remain and runs:pnpm release # = pnpm build && changeset publish --provenancePackages are published to npm via OIDC Trusted Publishing — no token required.
What NOT to do
- Do not create GitHub Releases to trigger publishing —
release.ymlhas been deleted. - Do not use
NPM_TOKEN— Trusted Publishing is configured on npmjs.com for all@md2do/*packages. - Do not manually run
changeset versionorchangeset publishlocally unless debugging. - Do not bump versions in
package.jsonmanually — changesets manages this.
Linked packages (always same version)
@md2do/cli, @md2do/core, @md2do/config, @md2do/todoist, @md2do/mcp
If changesets doesn't bump all of them (e.g. only touched packages move), manually align the others to the same version and add a CHANGELOG entry: "Version bump to stay in sync with linked packages".
Independent versioning
@md2do/vscode— VSCode Marketplace, own version inpackages/vscode/package.json@md2do/obsidian— GitHub releases inTeamNickHart/md2do-obsidian, own version inpackages/obsidian/manifest.json
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 · 87 lines · 787 tokens per session scan A 42e004d1dae3
md2do CLAUDE.md is an instructions file published in the GitHub repository TeamNickHart/md2do (2 stars, last pushed 27d ago), licensed MIT. It adds 787 tokens to every session, about $0.0039 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
mq copilot-instructions.md
Copilot instructions for harehare/mq, covering mq development guide, project overview, coding conventions, rust code conventions and commit message conventions.
mq commit.instructions.md
Instructions for harehare/mq: Use the following format for commit messages.
mq general.instructions.md
Instructions for harehare/mq, covering general coding conventions for mq, directory structure, feature requests and bug reports.
mq rust-crate.instructions.md
Instructions for harehare/mq, a project described as: A jq-like Markdown query language for command-line processing.
mq testing.instructions.md
Instructions for harehare/mq: Use just test-all to run tests instead of cargo test.
mq cli.instructions.md
Instructions for harehare/mq, a project described as: A jq-like Markdown query language for command-line processing.