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 skills add RasaHQ/rasa-agent-skills --skill rasa-searching-docsgit clone --depth 1 https://github.com/RasaHQ/rasa-agent-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/skills/rasahq/rasa-agent-skills/rasa-searching-docs)<a href="https://agentmods.dev/skills/rasahq/rasa-agent-skills/rasa-searching-docs"><img src="https://agentmods.dev/badge/skills/rasahq/rasa-agent-skills/rasa-searching-docs/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/rasahq/rasa-agent-skills/rasa-searching-docs"><img src="https://agentmods.dev/badge/skills/rasahq/rasa-agent-skills/rasa-searching-docs.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00166 | $0.02282 |
| Opus 5.5 | $0.00066 | $0.00913 |
| Sonnet 5.5 | $0.00033 | $0.00456 |
| Haiku 4.5 | $0.00017 | $0.00228 |
Grade A, and why
rasa-searching-docs 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 28d 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 — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rasa documentation lookup
rasa tools init bundles the full Rasa documentation into .rasa/ at the project
root, as two files:
.rasa/llms.txt— the page index. One line per page: title, link, and a one-line description..rasa/llms-full.txt— the full text of every page, one after another.
Always use the index first. Find the page in llms.txt, then read only that
page — or one section of it — from llms-full.txt.
Answer from the docs, not from memory
Rasa has changed a lot across releases. What you recall is often NLU-based Rasa
(intents, stories, rules, NLU pipelines) or an early version of CALM, and config
keys, defaults, and step types have moved since. Read the page first. Then state
the page path you used (e.g. Source: /reference/primitives/flow-steps) so the
user can check it. If you answer without reading a page, say so explicitly rather
than implying the answer came from the docs.
Make sure these are the right docs
These docs cover Rasa Pro with CALM, plus Rasa Studio and the older NLU-based
system. If the project has agent.yml and integrations.yml instead of
config.yml and domain.yml, or has .rasa/docs/mantle/, it is a Mantle project —
use the mantle-docs skill instead.
Within these docs:
- Mantle pages (
/mantle/..., if your copy has them) describe a different engine. Never use them to answer about a CALM project. - NLU-based pages (intents, entities, stories, rules, NLU components,
coexistence) apply only if the project uses NLU, e.g. it has
data/nlu.ymlor NLU components inconfig.yml. A CALM assistant uses flows and an LLM command generator instead. - Studio pages (
/studio/...for Studio 1.x,/studio/2.x/...for Studio 2.x) describe the no-code UI. For a project on disk, answer from the/pro/...and/reference/...pages, which describe the YAML and Python files.
Check the version
The docs describe the latest Rasa Pro release; the project may run an older one.
Find its version with rasa --version, or from the rasa-pro pin in
pyproject.toml or requirements*.txt.
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.
- 28d ago First seen · 180 lines · 166 tokens per session scan A c578e0747888
rasa-searching-docs is a skill published in the GitHub repository RasaHQ/rasa-agent-skills (6 stars, last pushed 29d ago), licensed Apache-2.0. It adds 166 tokens to every session and 2,282 once invoked, about $0.0007 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 2026-10-01.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…