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/mo-tunn/openguider/agents-mdgit clone --depth 1 https://github.com/mo-tunn/OpenGuiderWrote 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/mo-tunn/openguider/agents-md)<a href="https://agentmods.dev/instructions/mo-tunn/openguider/agents-md"><img src="https://agentmods.dev/badge/instructions/mo-tunn/openguider/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 | $0.00573 | $0.00573 |
| Opus 5 | $0.00287 | $0.00287 |
| Sonnet 5 | $0.00115 | $0.00115 |
| Haiku 4.5 | $0.00057 | $0.00057 |
Grade A, and why
OpenGuider 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 3d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file helps both human contributors and agentic coding AIs work safely and consistently in OpenGuider.
Project Snapshot
- Stack: Electron + Node.js (CommonJS), vanilla HTML/CSS/JS renderer.
- Entry points:
main.js(main process),preload.js(IPC bridge),renderer/(UI). - Core domains:
src/ai/provider integrations and streaming logicsrc/agent/planning, orchestration, structured tool flowssrc/session/session state and persistencesrc/tts/text-to-speech providerssrc/store.js+src/secure-store.jsapp settings and secret handling
Local Development
- Install deps:
npm install - Run app:
npm run start - Run tests:
npm test - Build artifacts:
npm run dist:winnpm run dist:macnpm run dist:linux
Contribution Rules
- Keep changes focused; avoid unrelated refactors in the same PR.
- Preserve backward compatibility for existing settings keys whenever possible.
- Do not commit secrets, tokens, personal data, or local machine artifacts.
- If touching provider logic, keep fallback defaults explicit and robust.
- Update docs/UI text when behavior changes (especially settings and provider fields).
AI Agent Guardrails
- Read nearby code before editing; follow existing naming and style conventions.
- Prefer minimal, surgical changes over broad rewrites.
- Do not remove existing user-facing features unless explicitly requested.
- Do not run destructive git commands (
reset --hard, force push, history rewrite). - Respect current branch/worktree state; do not revert unrelated local changes.
- Validate impacted flows with tests or targeted manual verification steps.
Testing Expectations
- At minimum, run
npm testafter meaningful code changes. - When modifying provider behavior, ensure AI provider tests still pass.
- If tests fail due to environment/dependency setup rather than your change, state that clearly in PR notes.
PR Checklist
- Clear title and short "why" summary.
- List user-visible changes (settings, provider behavior, UI, shortcuts, permissions).
- Mention validation performed (
npm test, manual checks). - Call out any limitations, follow-ups, or non-blocking risks.
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.
- 3d ago First seen · 67 lines · 573 tokens per session scan A fe441c7b7ff3
OpenGuider AGENTS.md is an instructions file published in the GitHub repository mo-tunn/OpenGuider (170 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 573 tokens to every session, about $0.0029 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
serpentine CLAUDE.md
Claude Code instructions for serpentine-parser/serpentine, covering project, dev environment, features, reading files and key conventions & patterns.
gmail-mcp-server CLAUDE.md
Instructions for ihiteshgupta/gmail-mcp-server, covering gmail mcp server, tech stack, available tools (19 total), email operations and drafts.
vite-react-best-practices AGENTS.md
AGENTS.md instructions for claudiocebpaz/vite-react-best-practices, covering vite react best practices, vite spa requirements, configure static host rewrites for spa routing, why it matters and incorrect.
appwrite AGENTS.md
AGENTS.md instructions for appwrite/appwrite, covering appwrite, commands, stack, layout and libraries.
Hermes3D AGENTS.md
Instructions for iamlukethedev/Hermes3D, covering agent instructions, development environment instructions, service overview, running the app and lint, typecheck, and tests.
Silex AGENTS.md
AGENTS.md instructions for silexlabs/Silex, covering agents.md, tech stack, run it locally, building the desktop app and when writing code for silex (editing source).