LangBot is an open-source platform for connecting language models to instant-messaging services so developers can build chatbots that converse, use tools, and execute tasks. It supports bot management, knowledge bases, plugins, and multiple chat platforms, and the catalogue entries provide skills, MCP tools, and instructions for working with it.
Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/langbot-app/LangBotnpx agentmods add skills/langbot-app/langbot/langbot-devWrote 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/skills/langbot-app/langbot/langbot-dev)<a href="https://agentmods.dev/skills/langbot-app/langbot/langbot-dev"><img src="https://agentmods.dev/badge/skills/langbot-app/langbot/langbot-dev/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/langbot-app/langbot/langbot-dev"><img src="https://agentmods.dev/badge/skills/langbot-app/langbot/langbot-dev.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 28 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
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 | $0.00136 | $0.01449 |
| Opus 5.5 | $0.00054 | $0.00580 |
| Sonnet 5.5 | $0.00027 | $0.00290 |
| Haiku 4.5 | $0.00014 | $0.00145 |
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 18d 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 — 133 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.
- 18d ago Changed · +3 lines 4745c8c782e5
- 1mo ago First seen · 130 lines · 136 tokens per session scan A 7f26d992b57a
langbot-dev is a skill published in the GitHub repository langbot-app/LangBot (18,191 stars, last pushed yesterday), licensed Apache-2.0. It adds 136 tokens to every session and 1,449 once invoked, about $0.0005 per session on Opus 5.5. 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
capture-api-response-test-fixture
For provider response parsing tests, we aim at storing test fixtures with the true responses from the providers (unless they are too large in which case some cutting that does not change semantics is advised).
nextjs-expert
Next.js expert for App Router, SSR/SSG, API routes, middleware, and deployment.
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.
data-leakage-detection
Detect sensitive information disclosure via escalating dialogue probes. Covers system prompt extraction, credential/API key leakage, PII, and internal configuration exposure.
browserwing-executor
Control browser automation through HTTP API. Supports page navigation, element interaction (click, type, select), data extraction, accessibility snapshot analysis, screenshot, JavaScript execution, and batch operations.
baby-sit
Monitor a GitHub pull request until CI is green, diagnose failures, and rerun only evidence-backed flaky GitHub Actions jobs.