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/nrslib/takt/agents-mdgit clone --depth 1 https://github.com/nrslib/taktWhat 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 | $0.00977 | $0.00977 |
| Opus 5 | $0.00489 | $0.00489 |
| Sonnet 5 | $0.00195 | $0.00195 |
| Haiku 4.5 | $0.00098 | $0.00098 |
Grade A, and why
takt 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 3d 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
src/: main TypeScript source. CLI entrypoints live insrc/app/cli/, core workflow execution insrc/core/, shared helpers insrc/shared/, and feature modules insrc/features/.src/__tests__/: Vitest unit and integration tests, typically named*.test.ts.e2e/: end-to-end specs, helpers, fixtures, mock workflows, and provider scenarios.builtins/: builtin workflows, facets, templates, prompts, and runtime config assets shipped with the CLI.docs/: user and design documentation.bin/contains executable wrappers.dist/is generated output and should not be edited by hand.
Build, Test, and Development Commands
npm install: install project dependencies.npm run build: compile TypeScript and copy runtime prompts, i18n files, and presets intodist/.npm run watch: run the TypeScript compiler in incremental watch mode.npm run lint: run ESLint onsrc/.npm test: run the fast unit gate in an adaptive number of concurrent shards during development (based on available parallelism, capped at 8). Integration tests are excluded; targeted source tests are routed to their classified runner.npm run test:it: run the light integration gate after implementation. It covers real filesystem, bounded storage, and multi-component contracts.npm run test:it:heavy: run all child-process, Git, full-engine, and measured resource-heavy integration tests locally with one worker. Pull-request CI splits it across isolated runners; do not run it routinely during development.npm test -- <test-file>: run a classified test through its unit, light-IT, or heavy-IT runner. When adding or changing an IT, also runnpm test -- src/__tests__/releaseVerificationWiring.test.tsby itself. Always run an added or changed heavy IT before handoff; the PR-wide heavy gate is not its first execution.npm run test:e2e:smoke: run the focused mock E2E suite during development.npm run check:release: run the full release verification path locally: build, lint, fast unit (adaptive local shards), light IT, heavy IT, and all E2E suites. The 8-runner unit matrix is a separate path in the main pull-request CI workflow.
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.
- 3d ago First seen · 46 lines · 977 tokens per session scan A 42e8339022c3
takt AGENTS.md is an instructions file published in the GitHub repository nrslib/takt (1,321 stars, last pushed 3d ago), licensed MIT. It adds 977 tokens to every session, about $0.0049 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
oh-my-subagents AGENTS.md
Instructions for ringlochid/oh-my-subagents, covering oh my subagents coding agent contract, product purpose, design philosophy, principles and authority split.
dos-kernel AGENTS.md
Instructions for anthony-chaudhary/dos-kernel, covering what dos is (the 30-second version), run it yourself first — the 60-second proof, when the user asks you about dos (the consumer moves), build, test, and check your work and the layout in one screen.
PuPu AGENTS.md
Instructions for haoxiang-xu/PuPu, covering gitnexus — code intelligence, always do, never do, resources and cli.
PuPu CLAUDE.md
Instructions for haoxiang-xu/PuPu, covering gitnexus — code intelligence, always do, never do, resources and cli.
rondoflow CLAUDE.md
Instructions for rondoflow/rondoflow, covering rondoflow, project overview, tech stack, development and setup.
comis CLAUDE.md
Instructions for comisai/comis, covering claude.md, generic runtime check — before every code change, tests-first, docs-current and root-cause before patching.