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/imbue-ai/latchkey/agents-mdgit clone --depth 1 https://github.com/imbue-ai/latchkeyWrote 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/imbue-ai/latchkey/agents-md)<a href="https://agentmods.dev/instructions/imbue-ai/latchkey/agents-md"><img src="https://agentmods.dev/badge/instructions/imbue-ai/latchkey/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 | $0.00164 | $0.00164 |
| Opus 5 | $0.00082 | $0.00082 |
| Sonnet 5 | $0.00033 | $0.00033 |
| Haiku 4.5 | $0.00016 | $0.00016 |
Grade A, and why
latchkey 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.
What it actually says
For information about the high-level goal and motivations, see README.md.
You are a highly intelligent and experienced software creator that codes in a straightforward way, prefers simplicity and avoids overengineering.
Typescript style guide:
- Use modern Typescript code.
- Prefer functional, stateless logic as much as possible.
- Use immutable data structures as much as possible.
- Do not use abbreviations in variable (class, function, ...) names. It's fine for names to be somewhat verbose.
- Omit docstrings if they don't add any value beyond what can be obviously inferred from the function signature / class name.
- Avoid locale dependent selectors in Playwright code.
- Do not throw builtin errors; always replace them with dedicated error subclasses.
- When done, validate your changes by running
npm lintandnpm test.
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 First seen · 15 lines · 164 tokens per session scan A 8b0dc6bc4bb1
latchkey AGENTS.md is an instructions file published in the GitHub repository imbue-ai/latchkey (124 stars, last pushed 6d ago), licensed MIT. It adds 164 tokens to every session, about $0.0008 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
mcp-nixos CLAUDE.md
Claude Code instructions for utensils/mcp-nixos, covering claude.md, project overview, project structure & module organization, key architecture and data sources.
mcp-nixos copilot-instructions.md
Copilot instructions for utensils/mcp-nixos, covering github copilot instructions for mcp-nixos, project context, core development workflows, build & test commands (nix flake required) and testing strategy.
gh-mcp CLAUDE.md
Claude Code instructions for shuymn/gh-mcp, covering claude.md, project overview, common development commands, build and build the extension.
server copilot-instructions.md
Instructions for mcpambassador/server, covering mcp ambassador server — copilot instructions, repo context, monorepo package structure, architecture patterns and spi (service provider interface).
server AGENTS.md
Instructions for mcpambassador/server, covering project instructions, current state, working agreements, definition of done — ci gate (mandatory) and common gotchas.
mcp-toolkit CLAUDE.md
Instructions for Sagargupta16/mcp-toolkit, covering claude.md, project, stack, run and test.