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/bouchecousue/logitech-sync-mcp/agents-mdgit clone --depth 1 https://github.com/bouchecousue/logitech-sync-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/bouchecousue/logitech-sync-mcp/agents-md)<a href="https://agentmods.dev/instructions/bouchecousue/logitech-sync-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/bouchecousue/logitech-sync-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 | $0.00635 | $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
logitech-sync-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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository instructions
These instructions apply to the entire repository.
Development environment
- Use Python 3.12 or newer.
- Use
uvfor dependency management, environments, and command execution. Do not usepip,pip-tools, Poetry, or manually edited lockfile entries. - Keep
uv.locksynchronized withpyproject.tomland use locked installs in CI. - Prefer the source-tree launcher during development:
uv run --no-editable python run_server.py.
Security boundary
- This MCP server is read-only. The targeted Logitech Sync Cloud API version exposes only
GET /org/{orgId}/place; do not add mutation tools, generic HTTP proxy tools, or hidden write behavior. - A future write capability requires an official API specification, a separate security review, precise tool-level confirmation semantics, and explicit documentation.
- Never commit
.env, organization-specific configuration, certificates, private keys, credential exports, tokens, or real API payloads. - Never print, copy, inspect, or include private-key contents in logs, tests, issues, or pull requests. It is acceptable to inspect file metadata and permissions without reading the key.
- Keep the vendor OpenAPI file local and ignored unless Logitech provides an explicit redistribution license.
- Use sanitized synthetic fixtures. Do not copy production inventory into
tests/fixtures/.
MCP contracts
- Keep public MCP inputs flat and task-oriented. Do not expose deeply nested request objects or arbitrary upstream API parameters.
- Reject unknown input fields (
extra="forbid") and retainadditionalProperties: falsein generated input schemas. - Keep annotations accurate: all current tools are read-only, non-destructive, and idempotent.
- Return bounded human-readable content together with validated structured content. Do not leak certificate paths, key paths, credentials, or internal exception details.
Tests and verification
Run the same checks as CI before submitting a change:
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 · 65 lines · 635 tokens per session scan A aeaa784f50d7
logitech-sync-mcp AGENTS.md is an instructions file published in the GitHub repository bouchecousue/logitech-sync-mcp (0 stars, last pushed 1mo 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
openrouter-mcp-multimodal AGENTS.md
AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).
llm-context.py CLAUDE.md
Instructions for cyberchitta/llm-context.py, covering claude.md, working notes (gitignored) and draining the field notes.
seekstone CLAUDE.md
Instructions for shaqmughal/seekstone, covering claude.md, what this repo is, commands, the harness itself (run after npm install) and architecture.
Plonk AGENTS.md
AGENTS.md instructions for ostapondo/Plonk, covering agent rules, layout, adding a module, build & verify and code style.
mcp-dockhand copilot-review.instructions.md
Copilot instructions for strausmann/mcp-dockhand: When reviewing pull requests in this repository.
second-brain AGENTS.md
Instructions for LindaHaviv/second-brain, covering instructions for ai coding agents, what to read first, the rules (non-negotiable), common tasks, the sanctioned way and enforcement, not just instructions.