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/burugo/one-mcp/agents-mdgit clone --depth 1 https://github.com/burugo/one-mcpWrote 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/burugo/one-mcp/agents-md)<a href="https://agentmods.dev/instructions/burugo/one-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/burugo/one-mcp/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 | $0.00611 | $0.00611 |
| Opus 5 | $0.00305 | $0.00305 |
| Sonnet 5 | $0.00122 | $0.00122 |
| Haiku 4.5 | $0.00061 | $0.00061 |
Grade A, and why
one-mcp 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.
How it starts
The opening of the file, as written. The whole thing — 23 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
The Go backend lives under backend/ with request handlers in api/handler, shared utilities in common/, data access in data/, and business logic in service/. The React frontend sits in frontend/src with translations in frontend/public/locales and build artifacts generated into frontend/dist. Persistent assets such as the SQLite database and uploads are stored in data/ and upload/, while deployment aides live in deploy/, Dockerfile, and docker-compose.yaml.
Build, Test, and Development Commands
./run.sh— launches the backend on:3000and the Vite dev server on:5173with hot reload.PORT=8080 ./build.sh— produces a production binary and bundles the frontend.go test ./...— executes the Go unit tests across the backend.cd frontend && npm run build— type-checks, lints, and compiles the React app.
Coding Style & Naming Conventions
Go code must pass gofmt (tabs for indentation) and follow idiomatic package naming (lower_case for directories, CamelCase for exported types). Keep API handlers in backend/api/handler named *_handler.go and tests as *_test.go. TypeScript and JSX files use two-space indentation, TypeScript strict mode, and Tailwind utility ordering as emitted by shadcn. Run npm run lint before pushing to ensure ESLint (flat config) passes.
Testing Guidelines
Backend features require table-driven tests under matching *_test.go files; ensure new logic is covered by go test ./... and update coverage.out when reporting coverage. Frontend components should use Vitest with Testing Library—add specs under frontend/src/**/__tests__/ or alongside components with .test.tsx suffix. For UI flows, prefer npm run test:coverage to exercise V8 coverage and attach results in PRs touching critical paths.
Commit & Pull Request Guidelines
Follow the Conventional Commits style visible in git log (e.g., feat(proxy): add SSE support). Keep messages scoped, written in the imperative, and limited to 72 characters in the subject. Pull requests should link related issues, summarize behavior changes, note migrations or env needs, and include before/after screenshots for UI updates. Confirm both go test ./... and npm run test results in the PR description before requesting review.
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 · 23 lines · 611 tokens per session scan A 29d2bd23d527
one-mcp AGENTS.md is an instructions file published in the GitHub repository burugo/one-mcp (412 stars, last pushed 17d ago), licensed MIT. It adds 611 tokens to every session, about $0.0031 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
suse-ai-up AGENTS.md
AGENTS.md instructions for SUSE/suse-ai-up, covering agents.md, architecture overview, build commands, kubernetes deployment commands and test commands.
ida-pro-mcp CLAUDE.md
Instructions for mrexodia/ida-pro-mcp, covering claude.md, what this project is, core implementation rules, ida thread safety and api conventions.
obot CLAUDE.md
Claude Code instructions for obot-platform/obot, covering claude.md, project overview, tech stack, common commands and development.
agent CLAUDE.md
Claude Code instructions for 1mcp-app/agent, covering claude.md, repository information, development commands, setup and build & run.
tableau-mcp CLAUDE.md
Claude Code instructions for tableau/tableau-mcp, covering claude.md, build & development commands, building, running the server and testing.
meilisearch-mcp CLAUDE.md
Instructions for meilisearch/meilisearch-mcp, covering claude.md, 🚨 important: development workflow guidelines, 🔄 fresh start protocol, 🎯 focused development rules and 📋 task assessment phase.