001_agent_semantic-tools

001_agent_semantic-tools is an agent for coding agents from paulbreuler/limps. It costs 0 tokens per session (739 once invoked), scanned A, original, MIT.

A project plan for adding semantic search tools that find code or documents by meaning, along with similar-item lookup and vector-index rebuilding.

In plain words
What is it for?
Use it to implement MCP tools for semantic search, finding similar items, and reindexing stored vectors within selected plans or paths.
Why use it?
It addresses cases where exact keyword searches miss related code or documents and adds logging for search and indexing operations.

Agent

Install

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.

agentmods
npx agentmods add agents/paulbreuler/limps/001_agent_semantic-tools
Clone the repo
git clone --depth 1 https://github.com/paulbreuler/limps

Wrote 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.

agentmods badge for 001_agent_semantic-tools

README.md
[![agentmods](https://agentmods.dev/badge/agents/paulbreuler/limps/001_agent_semantic-tools.svg)](https://agentmods.dev/agents/paulbreuler/limps/001_agent_semantic-tools)
Your own site
<a href="https://agentmods.dev/agents/paulbreuler/limps/001_agent_semantic-tools"><img src="https://agentmods.dev/badge/agents/paulbreuler/limps/001_agent_semantic-tools.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 739 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00739
Opus 5 $0.00000 $0.00369
Sonnet 5 $0.00000 $0.00148
Haiku 4.5 $0.00000 $0.00074

Measured 4d ago against content hash 9b1da5bb88ef, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

001_agent_semantic-tools 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 4d 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.

plans/0041-limps-improvements/agents/001_agent_semantic-tools.agent.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent 1: Semantic Tools

Plan Location: plans/0041-limps-improvements/0041-limps-improvements-plan.md

Scope

Features: #3 Own: packages/limps/src/tools/semantic-search.ts, packages/limps/src/tools/find-similar.ts, packages/limps/src/tools/reindex-vectors.ts, packages/limps/src/tools/index.ts Depend on: Agent 0 for semantic storage + embeddings Block: None (Agent 2 is now independent)

Interfaces

Export

  • semantic_search MCP tool
  • find_similar MCP tool
  • reindex_vectors MCP tool

Receive

  • Semantic storage + embeddings from Agent 0

Features

#3: Semantic Search Tools

TL;DR: Add semantic MCP tools with plan/path scoping and observability logging. Status: GAP Test IDs: semantic-search-basic, find-similar-basic, reindex-vectors-force, semantic-observability Files: packages/limps/src/tools/semantic-search.ts, packages/limps/src/tools/find-similar.ts, packages/limps/src/tools/reindex-vectors.ts

Observability Requirements: Log structured JSON for:

  • semantic.search: query_length, result_count, latency_ms, used_semantic
  • semantic.reindex: total_docs, indexed, skipped, errors, latency_ms
  • semantic.error: operation, error_type, message

Model Change Detection:

  • reindex_vectors should detect if config model differs from stored model_name
  • If mismatch, warn user and require force: true to reindex all

TDD:

  1. semantic-search-basic → impl search with structured logging → refactor
  2. find-similar-basic → impl similarity lookup → refactor
  3. reindex-vectors-force → impl rebuild with model detection → refactor
  4. semantic-observability → impl latency/usage logging → refactor

Done

  • semantic_search registered with logging
  • find_similar registered
  • reindex_vectors with model mismatch detection
  • Results include path + snippet + similarity + header context
  • Structured observability logs

Plan:

Read the full file on GitHub · 110 lines

Changes

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.

  1. 4d ago First seen · 110 lines · 0 tokens per session scan A 9b1da5bb88ef

Subscribe to this mod's changes

001_agent_semantic-tools 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 739 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.