Borrowing it
Nothing to install: this file belongs to scottconfusedgorilla/sncro-relay. 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/scottconfusedgorilla/sncro-relay/master/CLAUDE.mdgit clone --depth 1 https://github.com/scottconfusedgorilla/sncro-relayWrote 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/scottconfusedgorilla/sncro-relay/claude-md)<a href="https://agentmods.dev/instructions/scottconfusedgorilla/sncro-relay/claude-md"><img src="https://agentmods.dev/badge/instructions/scottconfusedgorilla/sncro-relay/claude-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/scottconfusedgorilla/sncro-relay/claude-md"><img src="https://agentmods.dev/badge/instructions/scottconfusedgorilla/sncro-relay/claude-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 | $0.00635 | $0.00635 |
| Opus 5 | $0.00318 | $0.00318 |
| Sonnet 5 | $0.00127 | $0.00127 |
| Haiku 4.5 | $0.00064 | $0.00064 |
Grade A, and why
sncro-relay CLAUDE.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 9d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
sncro-relay
This is the open-source half of sncro. It contains the MCP relay, the browser-side agent, and the framework plugins.
Repo layout
relay/— FastAPI app. Mounts an MCP server at/tools/mcp, exposes long-poll endpoints for agent.js under/session/{key}/*, servesagent.jsfrom/static/.middleware/— framework plugins that customers install into their apps.sncro_middleware.py(FastAPI) andsncro_flask.py(Flask).trysncro/—try.sncro.net, a deliberately-broken demo app used for end-to-end testing.tests/— pytest suite. 44 tests covering the relay, both plugins, and end-to-end flows.
The dashboard, auth, admin, billing, and landing page live in a separate private repo.
Tech stack
- Python 3.11+, FastAPI, Starlette
- MCP server via the
mcpPython SDK - Flask (for the Flask plugin and its tests)
- slowapi for rate limiting
- pytest for tests
Running locally
pip install -r requirements.txt
pytest # 44 tests should pass
uvicorn relay.main:app --reload # run the relay on localhost:8000
Running the demo
pip install -r trysncro/requirements.txt
DEBUG=true uvicorn trysncro.app:app --port 8001
# Browse to http://localhost:8001
Testing
pytest at the repo root. The suite is fast (< 5s). No integration tests that hit real services.
Commit style
Commits that deploy a new relay build are prefixed with the build number, e.g. (build 093) Advertise tools/listChanged on the MCP server. Security-related work is labeled with a phase letter (A through I so far). See git log --oneline for the shape.
Security
Every Critical/High from the blackhat/2 static review has a line-verified fix. See SECURITY.md for the reporting path and the threat model.
Guidelines when adding new features:
- If it touches the enable flow, the CSRF / clickjacking defences apply
- If it adds an endpoint, consider whether it needs a rate limit
- If it handles user-supplied strings, validate them against a regex at the boundary
- If it renders user-supplied content, use DOM APIs (not
innerHTML + string) on the client side and autoescape on the server side
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.
- 9d ago First seen · 59 lines · 635 tokens per session scan A 14540a4e8790
sncro-relay CLAUDE.md is an instructions file published in the GitHub repository scottconfusedgorilla/sncro-relay (0 stars, last pushed 3mo ago), licensed MIT. It adds 635 tokens to every session, about $0.0032 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
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.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
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.
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.