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/skills/claude-mdgit clone --depth 1 https://github.com/longbridge/skillsWrote 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/skills/claude-md)<a href="https://agentmods.dev/instructions/longbridge/skills/claude-md"><img src="https://agentmods.dev/badge/instructions/longbridge/skills/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 | $0.03106 | $0.03106 |
| Opus 5 | $0.01553 | $0.01553 |
| Sonnet 5 | $0.00621 | $0.00621 |
| Haiku 4.5 | $0.00311 | $0.00311 |
Grade A, and why
skills 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 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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — repo conventions for Claude Code
This file briefs Claude Code when working inside this repo (adding new skills, editing existing ones, fixing docs). It's not for end-users — they install via the methods in docs/install.md.
What this repo is
~22 Agent Skills that wrap the Longbridge Securities platform — quotes, charts, fundamentals, valuation, news, watchlist, account analytics, etc. Multilingual triggers (Simplified Chinese / Traditional Chinese / English). The default style is prompt-only (SKILL.md tells the LLM what longbridge ... command to run); scripts/ and commands/ subfolders are allowed but should be opt-in for clear runtime needs (DOCX generation, chart helpers, slash commands), not as a wrapper-by-default.
Layout
longbridge-skills/
├── .claude-plugin/marketplace.json # plugin marketplace entry
├── skills/ # ~22 skill folders
│ ├── <slug>/
│ │ ├── SKILL.md # required
│ │ ├── references/ # optional — on-demand detail loaded by the LLM
│ │ ├── scripts/ # optional — Python helpers (e.g. DOCX, charts) when there's a clear runtime need
│ │ └── commands/ # optional — Claude Code slash commands (`/<command>`)
│ └── ...
├── docs/
│ ├── architecture.md # multilingual + CLI/MCP routing design
│ └── install.md # install / verify / FAQ
├── CLAUDE.md # this file
├── README.md
├── LICENSE # MIT
└── .gitignore
Conventions for adding or editing a skill
1. Slug + directory
- Directory name must match
^[a-z0-9]+(-[a-z0-9]+)*$(lowercase ASCII + hyphens). - It MUST equal the
name:value in the SKILL.md frontmatter. - Existing skills are namespaced
longbridge-*(e.g.longbridge-quote). The single base skill is justlongbridge. - Slugs are immutable once published. Never rename or delete a published skill's slug. Installers (
npx skills update) match by slug, so a rename does not upgrade the old install — it orphans it on every user's machine (stale + competing for the same triggers) while the new name is never picked up byupdate. Reorganize by adding/editing content under the existing slug. If a new slug is genuinely unavoidable, it is a breaking change: note it in the release notes and direct users to the full reinstall (scripts/update.sh), the only thing that clears orphaned slugs.
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 · 181 lines · 3,106 tokens per session scan A 3122321c0f3a
skills CLAUDE.md is an instructions file published in the GitHub repository longbridge/skills (52 stars, last pushed 8d ago), licensed MIT. It adds 3,106 tokens to every session, about $0.0155 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
shinkoku CLAUDE.md
Instructions for kazukinagata/shinkoku, covering shinkoku, 対象ペルソナ, 対象外の機能, アーキテクチャ and コマンド.
rodya-caijing-studio AGENTS.md
AGENTS.md instructions for nekopunch11/rodya-caijing-studio, covering rodya-caijing-studio · 给 ai agent 的使用说明, 入口与路由, 不可破的硬约束(合规灵魂,破了整套工具就失效), docx 渲染路由(财经内容台例外) and 在 codex 中安装.
openalgo-claude-plugin CLAUDE.md
Instructions for marketcalls/openalgo-claude-plugin, covering openalgo marketplace - claude code plugin marketplace, repository structure, philosophy: unified trading api for indian markets, working with this repository and adding a new skill.
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).
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.
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.