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/paulbrav/cosmikase/agents-mdgit clone --depth 1 https://github.com/paulbrav/cosmikaseWrote 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/paulbrav/cosmikase/agents-md)<a href="https://agentmods.dev/instructions/paulbrav/cosmikase/agents-md"><img src="https://agentmods.dev/badge/instructions/paulbrav/cosmikase/agents-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 | $0.00698 | $0.00698 |
| Opus 5 | $0.00349 | $0.00349 |
| Sonnet 5 | $0.00140 | $0.00140 |
| Haiku 4.5 | $0.00070 | $0.00070 |
Grade A, and why
cosmikase 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 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 — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Use these conventions to keep contributions consistent and easy to review.
Project Structure & Module Organization
- Place runtime code in
src/; keep entrypoints or CLIs incmd/orapp/and shared helpers inscripts/. - Mirror modules with tests in
tests/(e.g.,src/example.py→tests/test_example.py, orsrc/example.rs→tests/example_tests.rs). - Store docs in
docs/and assets inassets/. Keep configuration in versioned files (e.g.,.editorconfig,pyproject.toml,package.json,Cargo.toml) and provide.env.examplefor environment keys.
Build, Test, and Development Commands
- Prefer Make targets or wrapper scripts so everyone runs the same steps. Suggested defaults:
make setup(install deps),make dev(run locally),make test(full suite),make fmtandmake lint(format + static checks). - If Make targets are absent, use the stack’s native commands (e.g.,
pip install -r requirements.txt/npm install,pytest/npm test), and add the wrappers to aMakefilefor repeatability.
Coding Style & Naming Conventions
- Default to 4-space indentation and a 100-character line guide unless a formatter enforces otherwise.
- Use
snake_casefor files, functions, and variables;PascalCasefor classes/types;UPPER_SNAKE_CASEfor constants and env vars. - Run formatters and linters before committing (e.g.,
ruff/black,eslint/prettier, orcargo fmt/cargo clippybased on language). Do not introduce lint warnings.
Testing Guidelines
- Keep tests close to the code they cover under
tests/and name them after the module under test. - Prefer fast, deterministic tests; avoid network calls or system mutations. Use fakes/mocks for external services.
- Add regression tests when fixing bugs. Target high coverage on critical paths; required checks must pass.
Documentation Guidelines
- Pair every “do X” with “undo/restore/verify X” (e.g., backups need restore steps; config changes need rollback notes).
- Call out safety rails for operational steps (mount checks before writing, fallbacks/recovery users for auth changes).
- Include quick validation or troubleshooting snippets so readers can confirm behavior and debug common breakages.
- Note platform-specific limits or conflicts (e.g., Timeshift scope, AppArmor/Firejail stacking).
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 · 38 lines · 698 tokens per session scan A c42480a6024d
cosmikase AGENTS.md is an instructions file published in the GitHub repository paulbrav/cosmikase (2 stars, last pushed 1mo ago), licensed MIT. It adds 698 tokens to every session, about $0.0035 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
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).
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.
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).