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/ayhammouda/obd-mcp-server/agents-mdgit clone --depth 1 https://github.com/ayhammouda/obd-mcp-serverWrote 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/ayhammouda/obd-mcp-server/agents-md)<a href="https://agentmods.dev/instructions/ayhammouda/obd-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/ayhammouda/obd-mcp-server/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 | $0.00489 | $0.00489 |
| Opus 5 | $0.00244 | $0.00244 |
| Sonnet 5 | $0.00098 | $0.00098 |
| Haiku 4.5 | $0.00049 | $0.00049 |
Grade A, and why
obd-mcp-server 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository instructions
This repository implements a safety-critical boundary between AI clients and vehicle diagnostic interfaces.
Non-negotiable safety rules
- Vehicle access is read-only. Never add fault clearing, ECU resets, session changes, security access, routine control, coding, flashing, actuator tests, write-by-identifier, raw command passthrough, or gateway bypass features.
- Enforce safety in the diagnostic core before a request reaches a driver. Descriptions, prompts, UI warnings, and MCP annotations are defense in depth; they are not policy enforcement.
- New protocol operations are denied unless a reviewed policy explicitly allowlists the operation and tests prove mutable operations remain blocked.
- AI-facing tools operate on normalized capabilities. Never expose raw CAN frames, arbitrary service IDs, adapter AT commands, or profile-defined tool code.
- Do not claim that a vehicle is safe to drive. Return observations, uncertainty, and a recommendation to consult a qualified professional.
Data and licensing rules
- Do not commit OEM manuals, diagnostic databases, screenshots, proprietary identifiers, copied standards text, vehicle captures, VINs, or user logs.
- External profiles must declare provenance, scope, license, confidence, and redistribution status. Bundled data must have affirmative redistribution permission.
- Community-derived data is untrusted configuration, never authoritative truth. Validate it before use and label it in every result.
- Keep full VINs out of tool results and logs. Use a local fingerprint unless a future, separately reviewed feature requires explicit disclosure.
Network and runtime rules
- Stdio stdout is protocol-only. Send diagnostics to stderr.
- Streamable HTTP is loopback-only until authenticated remote access is designed, implemented, and reviewed.
- Raw capture is disabled by default. Do not weaken local file permissions.
- Preserve cancellation, bounded timeouts, per-vehicle concurrency, and response-size limits when adding drivers or tools.
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 · 60 lines · 489 tokens per session scan A db6992720219
obd-mcp-server AGENTS.md is an instructions file published in the GitHub repository ayhammouda/obd-mcp-server (0 stars, last pushed 2d ago), licensed Apache-2.0. It adds 489 tokens to every session, about $0.0024 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
neurostack CLAUDE.md
Instructions for raphasouthall/neurostack, covering neurostack - claude code guide, quick reference, installation, mcp server (recommended for claude code) and openai-compatible api.
Vault-Agent-Memory AGENTS.md
Instructions for zycaskevin/Vault-Agent-Memory, covering agent instructions for vault agent memory, common install architecture, second decision: optional features, first decision: database scope and safe agent workflow.
rag-rat AGENTS.md
Instructions for cq27-dev/rag-rat, covering agents.md, prefer the rag-rat mcp for code browsing, record durable learnings as rag-rat memories, repo orientation and worktree correctness.
codex-image-context-runtime AGENTS.md
Instructions for shixinnt/codex-image-context-runtime, covering agents.md, public boundary, runtime contract and changes.
blz AGENTS.md
Instructions for outfitter-dev/blz, covering blz repository instructions for ai agents, important, working memory, use blz and 🚀 quick start for agents.
unified-ai-system AGENTS.md
AGENTS.md instructions for happy520ai/unified-ai-system, covering repository guidance, ownership, language and module policy, public repository rules and safety.