Borrowing it
Nothing to install: this file belongs to Studio-Moser/Shelby-MCP. 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/Studio-Moser/Shelby-MCP/main/AGENTS.mdgit clone --depth 1 https://github.com/Studio-Moser/Shelby-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/studio-moser/shelby-mcp/agents-md)<a href="https://agentmods.dev/instructions/studio-moser/shelby-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/studio-moser/shelby-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 5.1 | $0.00579 | $0.00579 |
| Opus 5 | $0.00290 | $0.00290 |
| Sonnet 5 | $0.00116 | $0.00116 |
| Haiku 4.5 | $0.00058 | $0.00058 |
Grade A, and why
Shelby-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 7d 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ShelbyMCP
ShelbyMCP is a Rust workspace that ships a local knowledge-graph memory engine, an MCP server, reusable client integrations, and a dependency-free npm launcher.
Repository map
crates/shelby-memory/— SQLite migrations, thoughts, search, vectors, edges, project identity, trust, repair, and tool-domain handlers.crates/shelby-integrations/— current client catalog and safe fallback configuration.crates/shelby-mcp/— MCP schemas, prompts, stdio/HTTP transports, OAuth, CLI, and public library surface.bin/andnpm/— npm launcher and native platform package manifests.integrations/— source manifests for client-native packages; canonical skills are copied during assembly.skills/andassets/— canonical skill and prompt sources.tests/fixtures/— shared JSON fixtures and the immutable TypeScript-v18 SQLite compatibility fixture.scripts/— dependency-free package, workflow, and documentation checks.
Required gates
cargo fmt --check
cargo clippy --workspace --all-targets -- -D warnings
cargo test --workspace
npm ci
npm test
npm audit
For distribution changes, also build the binary and run the package checks documented in Development.
Invariants
- The server performs no inference and never accepts model-provider credentials. Embeddings are caller-supplied vectors.
- Existing schema-v18 databases must open without conversion. The committed TypeScript fixture is mandatory compatibility evidence.
- Stdout is reserved for MCP JSON-RPC or the requested CLI payload. Diagnostics go to stderr.
- Every MCP tool has static descriptions, bounded inputs/results, actionable errors, and all four tool annotations.
- Project-scoped work resolves through immutable project UUIDs and aliases; ambiguous scope fails closed.
- Untrusted memory text remains fenced at every retrieval boundary.
- Client setup preserves malformed files byte-for-byte, preserves unrelated configuration, writes atomically, and never edits global instruction files.
skills/shelby-forageandskills/shelby-onboardare canonical. Generated client packages copy them byte-for-byte.- OAuth and bearer checks are security boundaries; changes require focused tests and full workspace verification.
- Do not add a Node runtime dependency to the server or npm launcher.
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.
- 7d ago First seen · 45 lines · 579 tokens per session scan A f97ef0df591d
Shelby-MCP AGENTS.md is an instructions file published in the GitHub repository Studio-Moser/Shelby-MCP (0 stars, last pushed 11d ago), licensed MIT. It adds 579 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 2026-08-31.
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.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.