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/shareai-lab/kode-cli/agents-mdgit clone --depth 1 https://github.com/shareAI-lab/Kode-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 | $0.00719 | $0.00719 |
| Opus 5 | $0.00360 | $0.00360 |
| Sonnet 5 | $0.00144 | $0.00144 |
| Haiku 4.5 | $0.00072 | $0.00072 |
Grade A, and why
Kode-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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Kode repository guide
This file is the stable, always-on contract for contributors and coding agents.
Keep durable repository rules here; implementation details belong beside the
code they describe or in maintained documents under docs/**.
Product direction
- Keep Kode terminal-native, fast, and predictable.
- Prefer intent-driven workflows with verifiable outcomes over setup menus.
.kode/**is the canonical write surface;.claude/**is read/import compatibility only.- Keep compatibility aliases in
packages/core/src/compat/**.
Repository map
apps/cli/: CLI entrypoints, commands, and Ink TUI.apps/server/: local daemon and Web UI host.apps/web/: React/Vite Web UI source.packages/core/: orchestration, permissions, model wiring, and sessions.packages/tools/: built-in tool definitions and implementations.packages/runtime/: shell/runtime primitives and background tasks.packages/config/: configuration, schemas, and data roots.packages/protocol/: session and transport protocols.packages/client/: daemon client helpers.packages/builtin-skills/: skills shipped in the npm package.
Required workflow
bun install --frozen-lockfile
bun run format:check
bun run architecture:check
bun run security:audit
bun run typecheck
bun test
bun run build
Run the smallest relevant check while iterating; run the full sequence before a
release. Do not commit generated output (dist/**, wrappers, Web UI builds,
platform binaries, coverage, or node_modules/**).
Architecture rules
- UI belongs in
apps/cli/src/ui/**orapps/web/**. - Orchestration belongs in
packages/core/**. - Tool behavior belongs in
packages/tools/**and must remain permission-aware. - OS/process behavior belongs in
packages/runtime/**. - Protocol and persisted formats must not depend on a UI host.
Do not add a new seam for a hypothetical implementation. When a seam is real, keep transport and host adapters outside the owning domain module.
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 · 87 lines · 719 tokens per session scan A 1073d803c9db
Kode-CLI AGENTS.md is an instructions file published in the GitHub repository shareAI-lab/Kode-CLI (5,210 stars, last pushed 4d ago), licensed Apache-2.0. It adds 719 tokens to every session, about $0.0036 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 2026-08-30.
Other instructions, from other repositories
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.
buildNext
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
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, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit 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.
langchain 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.