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/longbridge/longbridge-mcp/claude-mdgit clone --depth 1 https://github.com/longbridge/longbridge-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/longbridge/longbridge-mcp/claude-md)<a href="https://agentmods.dev/instructions/longbridge/longbridge-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/longbridge/longbridge-mcp/claude-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 | $0.00327 | $0.00327 |
| Opus 5 | $0.00163 | $0.00163 |
| Sonnet 5 | $0.00065 | $0.00065 |
| Haiku 4.5 | $0.00033 | $0.00033 |
Grade A, and why
longbridge-mcp 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 5d 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.
What it actually says
Code formatting
Use cargo +nightly fmt for code formatting.
Code style
Generic bounds
Place generic bounds in where clauses rather than inline.
Imports
- Use
crate::instead ofsuper::in non-test code.use super::*is acceptable in#[cfg(test)]modules. - Declare imports at the top with
useso the body uses short names. Avoid long inline paths.
Comments
Do not use decorative divider comments (e.g. // ── Section name ───────). If a file needs clearer structure, split it into separate modules or files instead.
Panic messages
panic!(), unreachable!(), debug_assert!(), and assert!() must always include a descriptive message string.
Error handling
- Prefer
Resultover panics. - Use
thiserrorfor custom error types.
Clippy
Run cargo clippy --all-features --all-targets and fix all warnings before committing.
Documentation
- Public items should have doc comments.
- Use
//!for module-level documentation,///for item documentation. - Store connector submissions, review materials, test credentials, and other non-public submission documents under
docs/internal/. - Never commit or publish files under
docs/internal/; the directory is intentionally excluded by.gitignore.
Commit messages
Follow Conventional Commits: <type>(<scope>): <description>
Types: feat, fix, docs, style, refactor, test, chore
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.
- 5d ago First seen · 45 lines · 327 tokens per session scan A b355f74550fd
longbridge-mcp CLAUDE.md is an instructions file published in the GitHub repository longbridge/longbridge-mcp (13 stars, last pushed yesterday), licensed Apache-2.0. It adds 327 tokens to every session, about $0.0016 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
TWSEMCPServer CLAUDE.md
Instructions for twjackysu/TWSEMCPServer, covering claude.md, project overview, development commands, code architecture and high-level structure.
lunchmoney-mcp CLAUDE.md
Instructions for akutishevsky/lunchmoney-mcp, covering claude.md, project overview, commands, architecture and tool implementation pattern.
robinhood-mcp AGENTS.md
Instructions for verygoodplugins/robinhood-mcp, covering agents.md, project overview, read-only is a hard invariant, build & development and install with dev dependencies (editable).
apra-mcp CLAUDE.md
Claude Code instructions for Bigred97/apra-mcp, covering apra-mcp, source, curated datasets (13), repo-specific module set and repo-specific gotchas.
horizon-shield GEMINI.md
Gemini CLI instructions for ogasurfproject-jpg/horizon-shield: You have the HORIZON SHIELD tools available. HORIZON SHIELD audits Japanese construction and renovation cost estimates against the open JCCDB dataset (95,403 line items) and returns fair-price references as tamper-evident, independently recomputable…
mcp-server AGENTS.md
AGENTS.md instructions for NannyKeeper/mcp-server, covering nannykeeper mcp server — agent instructions, purpose, tools available, when to use and key facts.