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/firecrawl/firecrawl-workflows/firecrawl-knowledge-basenpx skills add firecrawl/firecrawl-workflows --skill firecrawl-knowledge-basegit clone --depth 1 https://github.com/firecrawl/firecrawl-workflowsWhat 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 | $0.00050 | $0.00554 |
| Opus 5 | $0.00025 | $0.00277 |
| Sonnet 5 | $0.00010 | $0.00111 |
| Haiku 4.5 | $0.00005 | $0.00055 |
Grade A, and why
firecrawl-knowledge-base 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 3d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- firecrawl-knowledge-base — 100% identical, 0 lines differ
What it actually says
Firecrawl Knowledge Base
Use this to turn URLs or topics into organized LLM-ready content.
Onboarding Interview
Infer the source, goal, depth, and output location from context. If the source and goal are clear, proceed immediately.
Ask at most 1-3 concise questions only if blocked, such as the source URL/topic, whether the output is reference/RAG/training/docs, or training format if training is requested.
Firecrawl Collection Plan
Use Firecrawl map for documentation sites, search for topic-based corpora, scrape pages into markdown, and preserve code examples and tables.
For files, follow the Firecrawl download-style convention:
.firecrawl/
<hostname>/
<path>/
index.md
Parallel Work
If appropriate, use sub-agents or equivalent parallel task runners:
- one docs section per researcher
- official docs, tutorials, community discussions, and references by source type
- source scraping vs chunk generation vs manifest generation
Output Modes
- Reference: markdown files,
index.md, andsources.json. - RAG: markdown files plus chunk files and
manifest.json. - Training: scraped source files plus
training-data.jsonlandtraining-metadata.json. - Docs mirror: complete markdown mirror with a table of contents.
Final Deliverable
# Knowledge Base: [Source]
## Summary
[What was collected and why]
## Output Structure
[Files/directories created]
## Coverage
[Sections, source types, counts]
## Usage Notes
[How to use in RAG, docs, training, or agent context]
## Sources
[URLs collected]
## Rerun Inputs
workflow: firecrawl-knowledge-base
source: [url/topic]
goal: [reference/rag/train/docs]
depth: [quick/thorough/exhaustive]
output_dir: [.firecrawl/]
Quality Bar
- Preserve code examples and formatting.
- Remove boilerplate navigation where possible.
- Include source URLs in frontmatter or metadata.
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.
- 3d ago First seen · 87 lines · 50 tokens per session scan A 33ec3a6223b0
firecrawl-knowledge-base is a skill published in the GitHub repository firecrawl/firecrawl-workflows (146 stars, last pushed 12d ago), licensed ISC. It adds 50 tokens to every session and 554 once invoked, about $0.0003 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
agent-platform-rag-engine-management
Manage and query Agent Platform RAG Engine Corpora and retrieve grounded contexts using the Google GenAI SDK. Use when listing RAG corpora or files, inspecting a corpus, retrieving contexts, or generating content grounded in a RAG corpus. Do not use for standard database queries (use SQL/Spanner skills), Google…
9router-embeddings
Generate vector embeddings via 9Router /v1/embeddings using OpenAI / Gemini / Mistral / Voyage / Nvidia / GitHub embedding models for RAG, semantic search, similarity. Use when the user wants embeddings, vectors, RAG, semantic search, or to embed text.
potpie-source-ingestion
Use when the user explicitly asks to ingest, refresh, or deeply understand a repository, PR, issue, ticket, runbook, incident report, document, or web link into Potpie. The harness performs todo-driven discovery, uses local/GitHub/integration tools and read-only subagents when available, builds evidence-backed…
embedding-strategies
Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.
generate-rag-dataset
Generate a synthetic evaluation dataset from your RAG knowledge base. Creates diverse Q&A pairs with expected answers and relevant context, ready for LangWatch experiments and platform import. Use when you need test data for your RAG pipeline.
embeddings
Vector embeddings configuration and semantic search.