What is kim AGENTS.md?

A project instruction guide explains how to work on Kim, a local AI-agent platform with a desktop interface, a Python coordinator, and an MCP server. It points to the project architecture and directory-specific guides.

It is for guiding development of the Kim project, including where changes may be made, which providers the code tab may use, how to handle CSS and prompts, and when Rust changes require a restart.

It prevents changes that violate project boundaries, security rules, authentication limits, or important build behavior.

How AdamMagued/kim configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to AdamMagued/kim. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/AdamMagued/kim/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/AdamMagued/kim

Made for: Codex, OpenCode.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/adammagued/kim/agents-md/github.svg)](https://agentmods.dev/instructions/adammagued/kim/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/adammagued/kim/agents-md"><img src="https://agentmods.dev/badge/instructions/adammagued/kim/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/adammagued/kim/agents-md"><img src="https://agentmods.dev/badge/instructions/adammagued/kim/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 645 This file is loaded in full into every session.

When invoked 645 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00645	$0.00645
Opus 5.5	$0.00258	$0.00258
Sonnet 5.5	$0.00129	$0.00129
Haiku 4.5	$0.00064	$0.00064

Measured 2mo ago against content hash ba79327632d6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

kim 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 2mo 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

kim CLAUDE.md — 97% identical, 2 lines differ

AGENTS.md · 47 lines

How it starts

The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — Kim Agent Platform (root router)

What this is

Kim is a local AI agent platform (Tauri + React frontend, Python orchestrator, MCP server). Real app root is kim-pro/. Never modify anything outside kim-pro/.

Standing constraints (never violate)

Code tab must NEVER use OpenAI auth or gpt-5.5 — only ollama cloud or browser provider.
CSS import order in desktop/src/index.css is load-bearing (cascade). Do not reorder.
System-prompt f-strings: examples inside f-strings need doubled braces {{ }}.
After any Rust change, tauri dev needs a restart (hot-reload does not apply to Rust).
Secret-file sandbox: mcp_server/config.validate_path() denies secret files (.env, .env.*, *.pem, *.key, id_rsa*, id_ed25519*, credentials, .npmrc, .pypirc) at any depth and sensitive dirs (.ssh, .aws, browser profiles, cloud SDKs, …). Don't weaken these globs/paths. Note: enforcement is filename/dir-based, not a content scanner — secrets pasted into a normally-named file are not caught.

Architecture pointer

See ARCHITECTURE.md for the full layer diagram and IPC protocol spec. See ROADMAP.md for the current work backlog and sequencing (it points at the active plan, docs/ROADMAP_TO_10.md).

Per-directory guides (load only the one you need)

Directory	Guide	What's there
`orchestrator/`	`orchestrator/CLAUDE.md`	Agent loop, providers, session store
`mcp_server/`	`mcp_server/CLAUDE.md`	50+ OS-control tools, tool registry
`desktop/src/`	`desktop/src/CLAUDE.md`	React UI, IPC event consumers
`desktop/src-tauri/`	`desktop/src-tauri/CLAUDE.md`	Rust shell, subprocess mgmt

How-to recipes

HOW_TO.md — exact minimal file sets for common change patterns.

Finding things fast

Know which file → open it directly.
Don't know → grep/find with a targeted pattern.
Never do a broad full-repo sweep as a first move.

Test commands (all four suites — cli/ is a separate crate, easy to forget)

python -m pytest tests/            # Python tests (venv required)
cd desktop && npx tsc --noEmit && npm run test  # Vitest tests
cd desktop/src-tauri && cargo test # Rust tests (desktop)
cd cli && cargo test               # Rust tests (kim CLI)

After every push, confirm the remote CI run is green: gh run list --limit 1.

Read the full file on GitHub · 47 lines

Changes

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.

2mo ago First seen · 47 lines · 645 tokens per session scan A ba79327632d6

Subscribe to this mod's changes

kim AGENTS.md is an instructions file published in the GitHub repository AdamMagued/kim (6 stars, last pushed 3mo ago), licensed MIT. It adds 645 tokens to every session, about $0.0026 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 2026-08-31.

Building agents

kim AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
kim AGENTS.mdAdamMagued/kim	Instructions file	6	3mo ago	MIT	A	645	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	275k	2d ago	MIT	A	4,313	Codex, OpenCode

kim: Instructions file for Codex