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/harehare/mq/lspgit clone --depth 1 https://github.com/harehare/mqWhat 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 | $0.00112 | $0.00112 |
| Opus 5 | $0.00056 | $0.00056 |
| Sonnet 5 | $0.00022 | $0.00022 |
| Haiku 4.5 | $0.00011 | $0.00011 |
Grade A, and why
mq lsp.instructions.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 yesterday.
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.
What it actually says
Language Server Protocol (LSP) Coding Rules
- Follow LSP specification and conventions for all protocol handling.
- Clearly separate protocol, transport, and business logic.
- Document all public types and functions, especially those exposed to LSP clients.
- Write integration tests for LSP features and message handling.
- Use
miettefor error reporting to the user where possible. - Avoid blocking operations in async handlers.
- Ensure robust handling of invalid or unexpected LSP messages.
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.
- yesterday First seen · 15 lines · 112 tokens per session scan A cacf1a90a83c
mq lsp.instructions.md is an instructions file published in the GitHub repository harehare/mq (1,023 stars, last pushed 2d ago), licensed MIT. It adds 112 tokens to every session, about $0.0006 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 2026-08-30.
Other instructions, from other repositories
webclaw CLAUDE.md
Claude Code instructions for 0xMassi/webclaw, covering webclaw, architecture, core modules (webclaw-core), fetch modules (webclaw-fetch) and llm modules (webclaw-llm).
speclens CLAUDE.md
Instructions for dansreis/speclens, covering claude.md, what it is, stack decisions, gates and file map.
HwpForge CLAUDE.md
Instructions for ai-screams/HwpForge, covering claude.md, project overview, architecture (forge metaphor), development commands and build & test.
scraps CLAUDE.md
Instructions for boykush/scraps, covering scraps development with claude code, project structure and development workflow.
kimun CLAUDE.md
Instructions for nico2sh/kimun, covering kimun, docs and rules.
mdscript CLAUDE.md
Instructions for dean0x/mdscript, covering mds (markdown script), build and test, release, land the bump on main via pr (ci-gated), then and gotchas.