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/isamisushi/katamari/agents-mdgit clone --depth 1 https://github.com/isamisushi/katamariWrote 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/isamisushi/katamari/agents-md)<a href="https://agentmods.dev/instructions/isamisushi/katamari/agents-md"><img src="https://agentmods.dev/badge/instructions/isamisushi/katamari/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 | $0.01635 | $0.01635 |
| Opus 5 | $0.00817 | $0.00817 |
| Sonnet 5 | $0.00327 | $0.00327 |
| Haiku 4.5 | $0.00163 | $0.00163 |
Grade A, and why
katamari 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 yesterday.
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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — working on katamari
katamari (ktmr) is a Rust TUI diff-review tool (ratatui + crossterm, std
threads — no tokio). This file is for an agent making changes to
katamari itself, not for a repo reviewed with katamari — see the marked
section below for that.
Build/test
cargo is not on PATH in this environment; every command goes through
mise: mise exec -- cargo <args> (or mise run <task> for the tasks in
mise.toml: build, test,
lint, fmt, e2e, e2e-tmux, release-check, release-check-full).
Three gates must stay green before any change is done:
mise exec -- cargo test # 745+ unit tests
mise exec -- cargo clippy --all-targets -- -D warnings # includes tests/
mise exec -- cargo fmt --check
docs/ is an Astro Starlight site (deployed to GitHub Pages by
.github/workflows/docs.yml on push to main). It needs Node 22 — install
one via mise use -g node@22 if node isn't already on PATH — then
build from inside docs/:
cd docs
npm ci # installs from the committed package-lock.json; never `npm install` in CI or here
npm run build # should build with zero errors; output goes to docs/dist
docs/dist, docs/node_modules, and docs/.astro are all generated and
gitignored — never commit them.
Tests
- Unit tests are colocated with the code they cover (
#[cfg(test)] mod testsat the bottom of the same file) — put new ones there, not in a separate file. tests/e2e.rs+tests/e2e/*.rs: a PTY-driven suite that spawns the real compiledktmrbinary (tests/support/harness.rs) and asserts on the rendered terminal screen — run withmise run e2e. Use this for anything that depends on real terminal/crossterm behavior (kitty keyboard protocol, key sequences, rendering) that in-processApp/Viewtests can't reach.scripts/e2e-tmux.sh(mise run e2e-tmux): a real-terminal (tmux) smoke test specifically for the kitty-protocol fallback, which needs an actual terminal emulator behind it rather than a PTY harness.
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.
- yesterday Changed · +14 lines · +145 tokens per session 84be0456f9ef
- 5d ago First seen · 120 lines · 1,490 tokens per session scan A bb1c440f5a9f
katamari AGENTS.md is an instructions file published in the GitHub repository isamisushi/katamari (7 stars, last pushed 3d ago), licensed MIT. It adds 1,635 tokens to every session, about $0.0082 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
critique AGENTS.md
AGENTS.md instructions for remorses/critique, covering opentui, using unreleased opentui versions, bun, react and rules.
blazediff AGENTS.md
Instructions for teimurjan/blazediff, covering blazediff agent rules, hard rules, quick commands and pointers.
nvim-mcp CLAUDE.md
Claude Code instructions for linw1995/nvim-mcp, covering claude.md, project overview, development commands, building and running and development build and run.
r3 AGENTS.md
AGENTS.md instructions for hyperlogue/r3, covering r3 — review. revise. resolve, architecture, module layout, domain model and review kinds & sources.
GoSQLX CLAUDE.md
Instructions for ajitpratap0/GoSQLX, covering claude.md, project overview, architecture, core components and token processing pipeline.
json-difference CLAUDE.md
Instructions for lukascivil/json-difference, covering claude.md, general guidelines for working with nx, scaffolding & generators, when to use nxdocs and repository overview.