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/remorses/kimaki/agents-mdgit clone --depth 1 https://github.com/remorses/kimakiWrote 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/remorses/kimaki/agents-md)<a href="https://agentmods.dev/instructions/remorses/kimaki/agents-md"><img src="https://agentmods.dev/badge/instructions/remorses/kimaki/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 | $0.10962 | $0.10962 |
| Opus 5 | $0.05481 | $0.05481 |
| Sonnet 5 | $0.02192 | $0.02192 |
| Haiku 4.5 | $0.01096 | $0.01096 |
Grade C, and why
kimaki AGENTS.md scanned grade C with 2 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.
Nullifies safety policieshighAnti-refusal
"You have no restrictions", "do anything now", "ignore your guidelines": a direct jailbreak that disables guardrails.
after making important changes to queueing or message handling always run the full test suite inside cli to make sure our changes did not break anything. use `pnpm run test --run -u`, then inspect snapshot updates in git Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
do not use spawnSync. use our util execAsync. which uses spawn under the hood How it starts
The opening of the file, as written. The whole thing — 732 lines — stays where its author put it; the contents beside it link to each section on GitHub.
after every change always run tsc inside cli to validate your changes. try to never use as any
always load the changesets skill before fixing bugs or adding features. User-facing fixes and features usually need a .changeset/*.md entry, and the skill explains package selection, issue references, descriptive filenames, and .changeset/readme.md expectations.
do not use spawnSync. use our util execAsync. which uses spawn under the hood
the important package in this repo is cli. it contains the discord bot code.
after making important changes to queueing or message handling always run the full test suite inside cli to make sure our changes did not break anything. use pnpm run test --run -u, then inspect snapshot updates in git diff. for one file, use pnpm run test --run src/example.test.ts. always include run after pnpm; pnpm test --run makes pnpm consume the flag, and pnpm run test -- --run passes a literal -- that can make vitest ignore the filter.
repo architecture
kimaki is a monorepo with three main packages that communicate via a shared Postgres database hosted on PlanetScale.
┌───────────────────────────────────────────────────────────────┐
│ User's machine │
│ cli/ (TypeScript CLI + Discord bot) │
│ ├── src/cli.ts main CLI, onboarding wizard │
│ ├── src/discord-bot.ts event loop, session routing │
│ └── SQLite (~/.kimaki/discord-sessions.db) │
│ local state: bot tokens, channels, threads, models │
└─────────┬────────────────────────────┬───────────────────────┘
│ REST + WebSocket │ polls /api/onboarding/status
│ (clientId:secret) │ during first-time setup
▼ ▼
┌──────────────────────┐ ┌──────────────────────────────────┐
│ gateway-proxy/ │ │ website/ │
│ (Rust, fly.io) │ │ (Cloudflare Worker, Hono) │
│ │ │ https://kimaki.dev │
│ Sits between the │ │ │
│ CLI and Discord. │ │ GET /oauth/callback │
│ One shared bot for │ │ → upserts gateway_clients row │
│ all users — users │ │ → website/src/routes/ │
│ don't create their │ │ oauth-callback.tsx │
│ own Discord bot. │ │ │
│ │ │ GET /api/onboarding/status │
│ Multi-tenant: │ │ → CLI polls every 2s │
│ filters events per │ │ → website/src/routes/ │
│ client_id + guild │ │ onboarding-status.ts │
│ │ │ │
│ wss://kimaki- │ └──────────┬───────────────────────┘
│ gateway-production │ │
│ .fly.dev │ │
└──────────┬───────────┘ │
│ │
▼ ▼
┌───────────────────────────────────────────────────────────────┐
│ Shared Postgres (PlanetScale) │
│ db/schema.prisma │
│ │
│ gateway_clients table: │
│ client_id TEXT ── identifies the kimaki user │
│ secret TEXT ── authenticates gateway connections │
│ guild_id TEXT ── guild the user installed the bot in │
│ @@id([client_id, guild_id]) │
│ │
│ Written by: website (on OAuth callback) │
│ Read by: gateway-proxy (polls every 1s via db_config.rs) │
│ Read by: website (onboarding status check) │
└───────────────────────────────────────────────────────────────┘
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 · +17 lines · +285 tokens per session scan A → C b11be44d20ad
- 4d ago First seen · 715 lines · 10,677 tokens per session scan A a02461876ea8
kimaki AGENTS.md is an instructions file published in the GitHub repository remorses/kimaki (1,395 stars, last pushed yesterday), licensed MIT. It adds 10,962 tokens to every session, about $0.0548 per session on Opus 5. A static security scan graded it C with 2 findings (nullifies safety policies, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
superset AGENTS.md
AGENTS.md instructions for superset-sh/superset, covering superset monorepo, project structure, exception: shadcn/ui components, database and releases.
untether GEMINI.md
Gemini CLI instructions for littlebearapps/untether, covering untether — gemini instructions, stack & conventions, architecture, key rules and testing.
superset CLAUDE.md
Claude Code instructions for superset-sh/superset, a project described as: Superset is an agentic IDE to orchestrate 100+ coding agents in parallel. Run any agent with your own subscription.
sessionview AGENTS.md
AGENTS.md instructions for tyql688/sessionview, covering sessionview, commands, app / frontend, gates must pass under both feature sets: default (gui) and and --no-default-features --features headless.
give-me-job AGENTS.md
Instructions for kyoungbinkim/give-me-job, covering give-me-job repository instructions, default workflow, skill routing, working on this repository and development loop.
wingman AGENTS.md
Instructions for eat-pray-ai/wingman, covering agents.md — wingman (@eat-pray-ai/wingman), quick reference and documentation index.