Borrowing it
Nothing to install: this file belongs to davertor/take-notes. 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/davertor/take-notes/main/AGENTS.mdgit clone --depth 1 https://github.com/davertor/take-notesWrote 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/davertor/take-notes/agents-md)<a href="https://agentmods.dev/instructions/davertor/take-notes/agents-md"><img src="https://agentmods.dev/badge/instructions/davertor/take-notes/agents-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/davertor/take-notes/agents-md"><img src="https://agentmods.dev/badge/instructions/davertor/take-notes/agents-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 | $0.00779 | $0.00779 |
| Opus 5 | $0.00390 | $0.00390 |
| Sonnet 5 | $0.00156 | $0.00156 |
| Haiku 4.5 | $0.00078 | $0.00078 |
Grade A, and why
take-notes 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Notes for AI agents working in this repo. The full contributor guide is CONTRIBUTING.md — this file is the short list of things that are easy to get wrong from the outside.
Cut the release, or the version never moves
A feature branch does not touch the version by hand, and neither do you.
.github/workflows/release.yml runs cz bump when a PR is merged into main,
and only then: it reads the Conventional Commits since the last tag, decides
patch / minor / major, rewrites the version in all five places that mirror it,
commits chore(release): X.Y.Z, tags, and pushes. A PR carrying only docs,
chore, ci, style, refactor or test releases nothing and passes — those
changes ship with the next feat or fix.
Put the CHANGELOG entry in the PR itself, under the version the merge will
produce. The bot cuts the version but cannot write prose, so an entry written
after the fact lands in a commit the tag does not contain.
uvx --from commitizen cz bump --dry-run --yes prints the number the merge will
produce, and cz changelog --dry-run groups the commits to write from.
A commit pushed straight to main does not get a release of its own. It
stays unreleased and rides the bump that follows the next merged PR, which is
why the increment is read from a range of commits and not from the last one.
If the workflow is ever wrong, the same bump by hand is:
uvx --from commitizen cz bump --yes && git push --follow-tags
Every release is tagged. The increment is read from the commits since the
last tag, so a release that ships without one widens the range the next bump
reads and can turn a feat! from two releases ago into an unwanted major.
git push --follow-tags is part of the command above for that reason.
cz deliberately writes no CHANGELOG of its own: the entries here are prose
that explains what changed and why, not a list of commit subjects.
The rest, in one line each
- Stdlib only for anything under
scripts/— it runs on the user's machine throughuvwith no dependencies. Dev-time tools invoked withuvx(like commitizen above) are not a dependency and are fine. - There is no test suite. Each script carries its own asserts behind
--selftest, and CI runs exactly that loop. A behaviour change needs an assert; if you cannot write one, say so and explain how you checked by hand. - Conventional Commits, no exceptions —
featfixdocsstylerefactorperftestbuildcichore. The release tooling reads them to work out the version, so a sloppy type silently produces the wrong bump. - The rendered notes are the database.
gallery.pyandexport.pyparse them back throughnotes.py, so the classes listed in CONTRIBUTING.md § 3 are a contract, not styling. - Colour and type come from
scripts/themes.py. A template never hard-codes a hex or a font family. - Verify in a browser, not only in asserts. The selftests prove the values reach the HTML; they cannot tell you the result is legible.
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 · 59 lines · 779 tokens per session scan A 814511060bde
take-notes AGENTS.md is an instructions file published in the GitHub repository davertor/take-notes (18 stars, last pushed 3d ago), licensed MIT. It adds 779 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 2026-09-10.
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.
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.
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 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).
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).