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 skills/langbot-app/langbot/langbot-devnpx skills add langbot-app/LangBot --skill langbot-devgit clone --depth 1 https://github.com/langbot-app/LangBotWhat 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 | $0.00136 | $0.01378 |
| Opus 5 | $0.00068 | $0.00689 |
| Sonnet 5 | $0.00027 | $0.00276 |
| Haiku 4.5 | $0.00014 | $0.00138 |
Grade A, and why
langbot-dev 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.
How it starts
The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LangBot Core Development
This skill covers developing the LangBot core (the main repo), distinct from
plugin development (see langbot-plugin-dev) and deployment (langbot-deploy).
Stack
- Backend: Python
>=3.11,<4.0, deps viauv. Framework: Quart (async Flask). Serves the HTTP API + pre-built web UI onhttp://127.0.0.1:5300. - Frontend (
web/): Vite + React Router 7 + shadcn/ui + Tailwind, managed bypnpm. Dev server on:3000. (NOT Next.js —devscript isvite.)
Dev environment
# Backend
pip install uv
uv sync --dev
uv run main.py # API + UI on http://127.0.0.1:5300
# Frontend (separate terminal)
cd web
cp .env.example .env
pnpm install
pnpm dev # http://127.0.0.1:3000 (reads VITE_API_BASE_URL)
# Lint/format hooks (CI runs the same checks)
uv run pre-commit install
First run generates data/config.yaml; DB defaults to SQLite (PostgreSQL
supported). Migrations run automatically on startup.
Repo layout (key paths)
src/langbot/
├── __main__.py # entrypoint, CLI flags (--standalone-runtime/-box/--debug)
├── pkg/
│ ├── api/
│ │ ├── http/ # Quart controllers + services
│ │ │ ├── controller/groups/ # route groups (@group.group_class)
│ │ │ └── service/ # business logic (called by controllers AND MCP)
│ │ └── mcp/ # MCP server (server.py = tools, mount.py = ASGI dispatch)
│ ├── core/ # app bootstrap, stages, task manager
│ ├── platform/ provider/ pipeline/ plugin/ box/ skill/ rag/ vector/
│ ├── command/ persistence/ storage/ config/ entity/ telemetry/
│ └── templates/config.yaml # config template (top-level: api, system, plugin, box, space...)
├── web/ # Vite SPA
└── docker/ # compose deployment
HTTP API auth model
Route auth is declared per-route via AuthType in
pkg/api/http/controller/group.py:
NONE— public.USER_TOKEN— web UI JWT (Authorization: Bearer <jwt>).API_KEY—X-API-KeyorAuthorization: Bearer <key>.USER_TOKEN_OR_API_KEY— either.
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 · 130 lines · 136 tokens per session scan A 7f26d992b57a
langbot-dev is a skill published in the GitHub repository langbot-app/LangBot (17,616 stars, last pushed 2d ago), licensed Apache-2.0. It adds 136 tokens to every session and 1,378 once invoked, about $0.0007 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 skills, from other repositories
html-artifacts
Author the HTML for a plan artifact, dashboard iframe, or Slack attachment — structure, design plan, available runtime, theming, and craft. Read this before writing HTML for saveplan, outputiframe, or slackattachhtml.
bootstrap-repo-analysis
First-time analysis of a repository with no prior reviewer outcomes. Crawl historical merged-PR review feedback with the gh CLI (plus any preloaded samples), extract the team's review norms, and synthesize the initial per-repo review-style prompt. Use this for a cold-start repo; use continual-learning instead once the…
baby-sit
Monitor a GitHub pull request until CI is green, diagnose failures, and rerun only evidence-backed flaky GitHub Actions jobs.
continual-learning
Nightly refinement of an existing per-repo review-style prompt using this reviewer's own finding outcomes. Read confirmed (resolved-by-commit / thumbs-up) and dismissed (thumbs-down) findings, promote the bug patterns the team actually fixes, demote the false-positive patterns, reconcile against the current prompt…
gzh_article
公众号图文创作 / 推文 / 官方号文章 (official account article) — 端到端：选题→搜集→成文→配图→去AI化→公众号内联样式排版→交付/草稿箱。honors user persona & style memory.
search
Search 2500+ curated ChatGPT and LLM open-source repositories. Use when the user asks to find tools, libraries, or repos related to ChatGPT, LLMs, RAG, agents, langchain, NLP, AI development, or any open-source AI tooling.