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 agents/paulbreuler/limps/000_agent_semantic-infragit clone --depth 1 https://github.com/paulbreuler/limpsWrote 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/agents/paulbreuler/limps/000_agent_semantic-infra)<a href="https://agentmods.dev/agents/paulbreuler/limps/000_agent_semantic-infra"><img src="https://agentmods.dev/badge/agents/paulbreuler/limps/000_agent_semantic-infra.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00937 |
| Opus 5 | $0.00000 | $0.00468 |
| Sonnet 5 | $0.00000 | $0.00187 |
| Haiku 4.5 | $0.00000 | $0.00094 |
Grade A, and why
000_agent_semantic-infra 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 6d 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent 0: Semantic Infra
Plan Location: plans/0041-limps-improvements/0041-limps-improvements-plan.md
Scope
Features: #1, #2
Own: packages/limps/src/config.ts, packages/limps/src/indexer.ts, packages/limps/src/semantic/*, packages/limps/src/server-main.ts
Depend on: none
Block: Agent 1 waiting on semantic storage + embeddings
Interfaces
Export
- semantic config block in config loader with validation
- semantic storage schema with model metadata
- chunker (character-based) + embed pipeline with error handling
Receive
- None
Features
#1: Semantic Config + Storage Layer
TL;DR: Add semantic config defaults, validation, and vec storage schema with model metadata.
Status: GAP
Test IDs: semantic-config-defaults, semantic-storage-schema, semantic-startup-validation
Files: packages/limps/src/config.ts, packages/limps/src/semantic/storage.ts
TDD:
semantic-config-defaults→ impl config with validation → refactorsemantic-storage-schema→ impl vec tables with model_name, model_dim columns → refactorsemantic-startup-validation→ impl Ollama connectivity check → refactor
#2: Embedding Pipeline + Chunker
TL;DR: Chunk markdown by characters (2000 char chunks, 200 char overlap), embed locally, handle errors gracefully.
Status: GAP
Test IDs: semantic-chunker-headings, semantic-embed-local, semantic-embed-skip-on-same-hash, semantic-embed-error-handling
Files: packages/limps/src/semantic/chunker.ts, packages/limps/src/semantic/embedder.ts, packages/limps/src/indexer.ts
Chunking Rules:
- Split by markdown headers (h1, h2, h3)
- If section > 2000 characters, split by paragraphs
- If paragraph > 2000 characters, split by sentences
- Overlap: 200 characters between chunks
Error Handling:
- Ollama timeout (>5s): retry once, then skip chunk with error logged
- Ollama bad response: log error with response body, skip chunk
- Rate limits: exponential backoff (100ms, 200ms, 400ms, max 3 retries)
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.
- 6d ago First seen · 122 lines · 0 tokens per session scan A cc86a777b0dd
000_agent_semantic-infra is an agent published in the GitHub repository paulbreuler/limps (10 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 937 tokens. 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 2026-08-31.
Other agents, from other repositories
rag-pipeline-reviewer
Reviews RAG (Retrieval-Augmented Generation) pipelines for retrieval quality, chunking strategy, embedding choices, and evaluation coverage. Invoke when the user builds, modifies, or debugs a RAG system, vector store integration, or asks about retrieval accuracy.
ai-engineer
Build LLM applications, RAG systems, and prompt pipelines. Implements vector search, agent orchestration, and AI API integrations. Use PROACTIVELY for LLM features, chatbots, or AI-powered applications.
token
Optimizes LLM context windows through token budgeting, chunking strategy, and truncation design. Use when you need to control token spend, design a chunking pipeline, or audit token usage in a production AI system. Trigger with "design my token budget", "fix my context overflow".
ai-engineer
Build LLM applications, RAG systems, and prompt pipelines. Implements vector search, agent orchestration, and AI API integrations. Use PROACTIVELY for LLM features, chatbots, or AI-powered applications.
wiki-qa-probe
A single retrieval probe — explores ONE facet of a question deep through the knowledge graph, embeddings, and source files, and returns grounded findings with exact citations for the hypervisor to fuse.
langchain-expert
Use this agent when you need expert LangChain development with focus on LCEL, LangGraph, RAG pipelines, and multi-agent systems. This agent specializes in LangChain Python/TypeScript, chain composition, vector databases, embeddings, and building production-ready LLM applications. Examples: Context: User needs to build…