Borrowing it
Nothing to install: this file belongs to chocks/locode. 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/chocks/locode/main/AGENTS.mdgit clone --depth 1 https://github.com/chocks/locodeWrote 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/chocks/locode/agents-md)<a href="https://agentmods.dev/instructions/chocks/locode/agents-md"><img src="https://agentmods.dev/badge/instructions/chocks/locode/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/chocks/locode/agents-md"><img src="https://agentmods.dev/badge/instructions/chocks/locode/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 | $0.00928 | $0.00928 |
| Opus 5.5 | $0.00371 | $0.00371 |
| Sonnet 5.5 | $0.00186 | $0.00186 |
| Haiku 4.5 | $0.00093 | $0.00093 |
Grade A, and why
locode AGENTS.md scanned grade A with 1 finding 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 1mo 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- `src/tools/git.ts` uses `execFileSync` (not `execSync`) to prevent shell injection How it starts
The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Locode — Agent Guidelines
This file describes how AI agents (Claude Code, Locode itself, or any other coding agent) should work within this repository.
Project Overview
Locode is a TypeScript/Node.js CLI that routes coding tasks between a local Ollama LLM and Claude based on task complexity. The core value prop is token cost reduction — simple tasks (grep, file reads, shell) go to the local model; complex tasks (refactoring, code generation) go to Claude.
Architecture
User Input → Orchestrator → Router → LocalAgent (Ollama) or ClaudeAgent (Anthropic SDK)
↓
TokenTracker → session stats
Key files:
src/orchestrator/orchestrator.ts— main entry point for task processingsrc/orchestrator/router.ts— rule-based + LLM fallback routingsrc/agents/local.ts— Ollama clientsrc/agents/claude.ts— Anthropic SDK clientsrc/tools/— safe read-only tools (shell allow-list, git allow-list)src/config/schema.ts— Zod config schema (source of truth for config shape)src/cli/setup.ts— first-run wizard, API key storage
Development Rules
Testing
- Always follow TDD: write failing test → run to confirm → implement → confirm pass
- Run
npm testbefore every commit — all tests must pass - Run
npm run buildto catch TypeScript errors before committing - Never mock real behavior away in tests; mock only external I/O (Ollama, Anthropic API)
- Tests must call the real function, not reimplement its logic — if a function is hard to test, make it accept parameters (e.g.,
loadEnvFile(path)) rather than duplicating its internals - Mock names must match the actual registry (e.g., use
run_commandnotshell) - Assert behavior and outcomes, not implementation details
Security
src/tools/shell.tsuses an allow-list (ALLOWED_COMMANDSSet) — do NOT switch to a deny-listsrc/tools/git.tsusesexecFileSync(notexecSync) to prevent shell injection- API keys are stored in
~/.locode/.envwith mode0600— never log or expose them - Never pass user input directly to shell commands
- Path containment checks must use
path === base || path.startsWith(base + path.sep)— barestartsWith(base)allows sibling-directory traversal - Avoid regex patterns with overlapping alternations — CodeQL flags these as backtracking vulnerabilities on every PR
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.
- 1mo ago First seen · 76 lines · 928 tokens per session scan A 5e5a2e36342a
locode AGENTS.md is an instructions file published in the GitHub repository chocks/locode (23 stars, last pushed 4mo ago), licensed MIT. It adds 928 tokens to every session, about $0.0037 per session on Opus 5.5. A static security scan graded it A with 1 finding (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
create-trimble-app typescript.instructions.md
Instructions for julianoczkowski/create-trimble-app, covering typescript patterns for modus components, event type casting, common event types, component ref types and modal ref pattern.
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).