getkimchi/kimchi is a terminal-based coding agent that helps with software development through Kimchi’s language-model infrastructure. It can run tasks with one selected model or coordinate multiple models, with model roles chosen by its orchestration system.
Borrowing it
Nothing to install: this file belongs to getkimchi/kimchi. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/getkimchi/kimchi/master/AGENTS.mdgit clone --depth 1 https://github.com/getkimchi/kimchiWrote 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/getkimchi/kimchi/agents-md)<a href="https://agentmods.dev/instructions/getkimchi/kimchi/agents-md"><img src="https://agentmods.dev/badge/instructions/getkimchi/kimchi/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/getkimchi/kimchi/agents-md"><img src="https://agentmods.dev/badge/instructions/getkimchi/kimchi/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.03652 | $0.03652 |
| Opus 5.5 | $0.01461 | $0.01461 |
| Sonnet 5.5 | $0.00730 | $0.00730 |
| Haiku 4.5 | $0.00365 | $0.00365 |
Grade A, and why
kimchi 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 4d 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 — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent guidelines for Kimchi
You are editing the kimchi coding harness. This repo extends the pi-mono SDK (@earendil-works/pi-coding-agent) — core agent loop lives upstream; this repo adds extensions in src/extensions/.
Environment
- Package manager: pnpm (NEVER use npm/yarn)
- Runtime: Bun for dev (
pnpm run dev), Node 22+ for built binaries - Test runner: vitest (
pnpm run test— unit,pnpm run test:smoke,pnpm run test:e2e:tui,pnpm run test:e2e:acp— e2e) - Linter: biome (
pnpm run lint,pnpm run lint:fix) - Type check: TypeScript (
pnpm run typecheck)
Hard constraints
- NEVER modify
patches/files directly — patches apply at install; changes here don't affect runtime - NEVER touch
src/core/export-html/HTML templates — bundled JS is auto-generated from source - Test files: Co-locate as
*.test.tsalongside source (NOT in a separate test/ folder) - Use
ctx.cwdinstead ofprocess.cwd()for session-relative paths — the ACP server is a long-lived process whose cwd is unrelated to any session. ThreadExtensionContext/ExtensionCommandContextthrough tool factories, delegates, and anything anchoring to the project, and pass the cwd as a required parameter (an optional fallback silently reintroduces the bug).
Org policy (resources, modes, usage reporting)
Org policy is fetched at startup and held for the session; each field has one enforcement module — route all consumption through it:
- Resources —
isResourceEnabled()insrc/resources/store.ts. - Permission modes —
src/extensions/permissions/policy.ts. - Usage reporting (telemetry) —
isTelemetryEnabled()/readEffectiveTelemetryConfig()insrc/telemetry-policy.ts. RawreadTelemetryConfig()is only for surfaces showing or persisting the user's raw preference (config telemetry, the wizard consent prompt,cli.tsstartup).
Development patterns
- Auto-formatting:
lint:fixruns automatically after file edits (PostToolUse hook) — don't run manually - Pre-commit:
.husky/pre-commitrunspnpm run lint— CI runs fullcheck(lint + typecheck) - README changes: Run
./scripts/copy-resources.js --devafter editing to propagate to dist/
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.
- 4d ago Changed · +25 lines · +608 tokens per session 5fe7d7969890
- 9d ago Changed · +8 lines · +131 tokens per session e5e932d1e58a
- 16d ago Changed · +1 lines · +79 tokens per session b4acae475ed9
- 22d ago Changed · +24 lines · +391 tokens per session ee1c2c549e73
- 23d ago Changed · +10 lines · +242 tokens per session daeacc525438
- 1mo ago Changed · +4 lines · +40 tokens per session c72e069cfa40
- 1mo ago First seen · 160 lines · 2,161 tokens per session scan A a1f1939d58f3
kimchi AGENTS.md is an instructions file published in the GitHub repository getkimchi/kimchi (2,276 stars, last pushed today), licensed Apache-2.0. It adds 3,652 tokens to every session, about $0.0146 per session on Opus 5.5. 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
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.