Borrowing it
Nothing to install: this file belongs to real-limitless/mcp-flow. 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/real-limitless/mcp-flow/CORE/AGENTS.mdgit clone --depth 1 https://github.com/real-limitless/mcp-flowWrote 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/real-limitless/mcp-flow/agents-md)<a href="https://agentmods.dev/instructions/real-limitless/mcp-flow/agents-md"><img src="https://agentmods.dev/badge/instructions/real-limitless/mcp-flow/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/real-limitless/mcp-flow/agents-md"><img src="https://agentmods.dev/badge/instructions/real-limitless/mcp-flow/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 | $0.02526 | $0.02526 |
| Opus 5.5 | $0.01010 | $0.01010 |
| Sonnet 5.5 | $0.00505 | $0.00505 |
| Haiku 4.5 | $0.00253 | $0.00253 |
Grade A, and why
mcp-flow 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 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.
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 — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mcp-flow: agent guide
Self-hosted MCP workspace gateway + official-registry catalog + static GitHub Pages gallery. OpenFlow and Everflow consume the catalog.
Stack: TypeScript / Node ≥ 22, Hono HTTP, MCP SDK, SQLite (node:sqlite), AES-256-GCM vault.
What this repo is
| Surface | Role |
|---|---|
| Gateway | One /mcp URL + agent API keys (mf_*); proxies namespaced tools; upstream secrets sealed |
| Catalog | Normalized McpGalleryEntry shards from MCP Registry + factory enrichment |
| Site | Campaign-styled static HTML that fetches catalog JSON (no 20k prebuilt pages) |
| Consumers | Agents/IDEs → gateway; OpenFlow → gallery palette; Everflow → marketplace allowlist → backends |
Priority: gateway-first. Catalog and site support the consumers. Do not block gateway fixes for gallery polish.
Hard rules
- Never commit secrets: no live API keys, master keys, decrypted headers/env, or
.env. Redact in logs and tool results. - Catalog never stores secret values: header names,
valueTemplate(e.g.Bearer {api_key}), env names only. - Schema bumps: changing
McpGalleryEntryrequirescatalog/schema.json+CATALOG_SCHEMA_VERSIONinsrc/catalog/types.ts(and consumer awareness). Current: 1.2.0. - Stable allowlist id = registry
server.name→ entryid. - Placement is first-class:
remote|central-sandbox|edge-sandbox|edge-bare. Edge-bare requires workspaceallowEdgeBare. - Enterprise defaults: deny edge-bare; no unrestricted enable-any-URL in enterprise mode.
- Do not scrape competitor marketplaces (e.g. mcpmarket) as catalog SoT: official registry + public GitHub/GitLab + live MCP probe only.
- Do not commit
catalog/entries/,catalog/index.json, orsite/out/(gitignored). Publish data viacatalog-databranch or CI. - No force-push
main, no commit unless the user asks. - Prefer shared contracts/fixtures with OpenFlow over silent drift.
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 Changed · +13 lines · +240 tokens per session 7cb2c605c6bb
- 2mo ago Changed · +6 lines · +146 tokens per session edc4deac496d
- 2mo ago First seen · 179 lines · 2,140 tokens per session scan A cb864fb61b31
mcp-flow AGENTS.md is an instructions file published in the GitHub repository real-limitless/mcp-flow (1 stars, last pushed 7d ago), licensed Apache-2.0. It adds 2,526 tokens to every session, about $0.0101 per session on Opus 5.5. 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
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).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.