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/dsociative/kaiten-cli/agents-mdgit clone --depth 1 https://github.com/dsociative/kaiten-cliWhat 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 | $0.02302 | $0.02302 |
| Opus 5 | $0.01151 | $0.01151 |
| Sonnet 5 | $0.00460 | $0.00460 |
| Haiku 4.5 | $0.00230 | $0.00230 |
Grade A, and why
kaiten-cli 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working on kaiten-cli
Facts and rules that are not derivable from the code. Keep it short; when a rule changes, change it here in the same PR.
Layout
crates/kaiten-client— the published library (kaiten-clienton crates.io): HTTP client, models, per-resource facades (client.cards(),client.files(), …).crates/kaiten— thekaitenbinary (kaiten-clion crates.io): the CLI and the MCP stdio server (kaiten mcp serve, rmcp). Both shareconfig::resolve()and the same auth.- One workspace version for both crates (
Cargo.toml[workspace.package]+ thekaiten-clientpin incrates/kaiten/Cargo.toml).
Toolchain and gates
- Build with the stable toolchain. If the default toolchain is nightly without cargo, use
cargo +stable …(orRUSTUP_TOOLCHAIN=stablefor tools that shell out to cargo). - Before every commit (not only before a push):
cargo fmt --all -- --check,cargo clippy --all-targets -- -D warnings(clippy pedantic is on),cargo test --workspace. A failing gate blocks the commit — never commit or push code that does not compile or has red tests, even on a feature branch; if a script drives the edit, check its exit status beforegit commit. kaiten-clientchanges:cargo semver-checks check-release -p kaiten-client --baseline-rev v<last tag>(cargo install cargo-semver-checks --locked). CI runs it on every pull request against the PR's base commit; the check against the last release is the local one before tagging.- Bugs are fixed test-first: write the failing test that reproduces the bug, watch it fail, then fix. New behaviour likewise gets its tests before the implementation.
- Get an independent review of the whole diff before asking the owner to merge; fix Important findings, note Minor ones.
- Commits, pushes, merges and releases happen only when the owner explicitly asks. No
Co-Authored-Bytrailers. Commit messages followtype(scope): summary(feat,fix,test,docs,ci,chore;!for breaking).
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 · 70 lines · 2,302 tokens per session scan A ff8467b97fe4
kaiten-cli AGENTS.md is an instructions file published in the GitHub repository dsociative/kaiten-cli (5 stars, last pushed 5d ago), licensed Apache-2.0. It adds 2,302 tokens to every session, about $0.0115 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
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.
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.
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).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.