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/aditya251610/opentool/copilot-instructionsgit clone --depth 1 https://github.com/Aditya251610/opentoolWrote 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/aditya251610/opentool/copilot-instructions)<a href="https://agentmods.dev/instructions/aditya251610/opentool/copilot-instructions"><img src="https://agentmods.dev/badge/instructions/aditya251610/opentool/copilot-instructions.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 | $0.00819 | $0.00819 |
| Opus 5 | $0.00409 | $0.00409 |
| Sonnet 5 | $0.00164 | $0.00164 |
| Haiku 4.5 | $0.00082 | $0.00082 |
Grade A, and why
opentool copilot-instructions.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.
How it starts
The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copilot Instructions — OpenTool
Project Overview
OpenTool is an open-source, self-hosted MCP (Model Context Protocol) server that provides 26 tools across 10 providers (GitHub, Gmail, Slack, Notion, Linear, Google Calendar, Stripe, Vercel, Resend, Postgres/Neon). It's the open-source alternative to Arcade.dev and Composio.
Code Rules
- NEVER commit or push — the maintainer handles that manually.
- TypeScript strict mode throughout.
- All tools use Zod schemas for input validation.
- Monorepo structure:
packages/server,packages/cli,packages/sdk,apps/dashboard.
Design Context
Users
Primary audience: Backend and full-stack developers building AI agents who need tool integrations (GitHub, Slack, Gmail, Notion, etc.) without vendor lock-in. They're evaluating OpenTool against Arcade.dev and Composio — they'll pick the one that looks like it was built by someone who actually ships.
Context of use: Developers discover OpenTool from a GitHub README, a tweet, or a search for "open source MCP server." They land on the marketing site to evaluate it, then move to the dashboard to connect tools and manage API keys. They interact with OpenTool primarily through the CLI or SDK — the dashboard is for setup and monitoring.
Job to be done: Wire up third-party APIs (GitHub, Slack, Stripe, etc.) as MCP-compatible tools for their AI agents, without writing OAuth flows, token refresh logic, or API wrappers themselves. Self-hosted, own their data, no recurring SaaS bill.
Brand Personality
Three words: Sharp. Owned. Uncompromising.
Voice: Direct and technical. No filler, no buzzwords, no "supercharge your workflow." Slightly aggressive when calling out bad patterns — this is the tool senior engineers wish existed. Talks to developers as peers, not prospects.
Emotional goals (all four, weighted):
- "This is serious infrastructure" — trust, reliability, production-grade (primary)
- "This dev gets it" — sharp, opinionated, built by someone who felt the pain
- "This is beautiful AND works" — polished craft that signals quality
- "Finally, something I can own" — freedom, self-hosted pride
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 · 58 lines · 819 tokens per session scan A 0cecb4bf2c34
opentool copilot-instructions.md is an instructions file published in the GitHub repository Aditya251610/opentool (5 stars, last pushed 4mo ago), licensed MIT. It adds 819 tokens to every session, about $0.0041 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 2026-08-31.
Other instructions, from other repositories
urantia-dev-api CLAUDE.md
Claude Code instructions for urantia-hub/urantia-dev-api, covering urantia-dev-api, scope of this service, tech stack, dependency and toolchain pins and testing against production.
openscreen AGENTS.md
AGENTS.md instructions for getopenscreen/openscreen, covering agents.md, setup commands, development principles, project layout and code style.
Claw3D AGENTS.md
Instructions for iamlukethedev/Claw3D, covering agent instructions, cursor cloud specific instructions, service overview, running the app and lint, typecheck, and tests.
commonly CLAUDE.md
Claude Code instructions for Team-Commonly/commonly, covering claude.md / agents.md, 🧠 product vision & architecture philosophy, what commonly is, the architecture model and key concepts.
claude-ads CLAUDE.md
Instructions for AgriciDaniel/claude-ads, covering claude ads repository instructions, architecture, development and verification.
openstatus AGENTS.md
AGENTS.md instructions for openstatusHQ/openstatus, covering agents.md, verify your change, toolchain, architecture and tests.