OpenGAP is a framework-independent standard for defining AI agents as Git repositories, using files such as an agent manifest and identity document. It is intended for portable, version-controlled agents that can be adapted to systems such as Claude Code, OpenAI, LangChain, CrewAI, and AutoGen. The catalogue skills represent workflows and extensions built around this agent format.
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 open-gitagent/opengap --skill knowledge-retrievalgit clone --depth 1 https://github.com/open-gitagent/opengapWrote 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/open-gitagent/opengap/knowledge-retrieval)<a href="https://agentmods.dev/skills/open-gitagent/opengap/knowledge-retrieval"><img src="https://agentmods.dev/badge/skills/open-gitagent/opengap/knowledge-retrieval/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/open-gitagent/opengap/knowledge-retrieval"><img src="https://agentmods.dev/badge/skills/open-gitagent/opengap/knowledge-retrieval.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00028 | $0.00336 |
| Opus 5.5 | $0.00011 | $0.00134 |
| Sonnet 5.5 | $0.00006 | $0.00067 |
| Haiku 4.5 | $0.00003 | $0.00034 |
Grade A, and why
knowledge-retrieval 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 1mo 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.
What it actually says
Knowledge Retrieval
Perform semantic search over a pre-ingested document collection using Retrieval-Augmented Generation (RAG). Backed by LlamaIndex with ChromaDB or NVIDIA Foundational RAG.
When to Use
- Searching internal or pre-ingested documents and reports
- Finding information in PDFs, whitepapers, or technical documentation
- Retrieving domain-specific knowledge not available on the open web
- This is the highest priority source — check the knowledge base first before web or paper searches
How to Use
- Formulate a semantic search query describing the information needed
- Call
knowledge_retrievalwith the query - Review returned chunks for relevance
- Note the citation metadata (filename, page number) for sourcing
Result Format
Results are returned as text chunks with citation metadata:
Relevant text passage from the ingested document...
Citation: filename.pdf, p.12
Constraints
- Searches only over documents that have been ingested into the knowledge index
- Returns ranked chunks based on semantic similarity
- Citation format:
Citation: filename.ext, p.X - Each call counts toward the researcher's 8-call limit per task
Backend Options
- LlamaIndex + ChromaDB — Local vector store with LlamaIndex orchestration
- NVIDIA Foundational RAG — NVIDIA-hosted RAG service with NeMo Retriever
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.
- 1mo ago First seen · 46 lines · 28 tokens per session scan A b15b4ea2aa0b
knowledge-retrieval is a skill published in the GitHub repository open-gitagent/opengap (2,979 stars, last pushed 3mo ago), licensed MIT. It adds 28 tokens to every session and 336 once invoked, about $0.0001 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
data-analyzer
Guidance for analyzing structured data, generating statistics and producing data-driven insights. Use when the user asks to analyze data, compute statistics, find patterns, or generate analytical reports.
dspy
Build complex AI systems with declarative programming, optimize prompts automatically, create modular RAG systems and agents with DSPy - Stanford NLP's framework for systematic LM programming.
langchain
Framework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, Anthropic, Google), 500+ integrations, ReAct agents, tool calling, memory management, and vector store retrieval. Use for building chatbots, question-answering systems, autonomous agents, or RAG…
local-rag-mcp
Use when querying, ingesting, or maintaining a local RAG MCP corpus for semantic document retrieval with privacy controls.
agenticforge-memory
Expert at setting up AgenticFORGE memory systems — WorkingMemory, EpisodicMemory, SemanticMemory, MemoryManager, and RAGPipeline. Use when the user wants to add memory to an agent, set up RAG, persist conversation history, or store and retrieve knowledge.
evaluating-llms-harness
Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs.