agentmods.dev

004_agent_docs

A documentation workstream for a software project that uses semantic search, which finds related meaning rather than only exact words. It covers setup instructions, configuration, and troubleshooting.

In plain words
What is it for?
Use it to update the README, write the semantic setup guide, document configuration options and defaults, provide troubleshooting steps, and maintain an example config file.
Why use it?
It gives users one place to learn how to enable semantic search, check that it works, and understand available settings. It also explains technical terms such as text chunks and embedding-model compatibility.

Agent

10 6mo ago A scan 0 tokens original MIT
View the source file paulbreuler/limps
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/004_agent_docs
Clone the repo
git clone --depth 1 https://github.com/paulbreuler/limps
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 804 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 $0.00804
Opus 5 $0.00000 $0.00402
Sonnet 5 $0.00000 $0.00161
Haiku 4.5 $0.00000 $0.00080

Measured 2d ago against content hash c23104133452, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

004_agent_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 2d 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/004_agent_docs.agent.md · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent 4: Docs

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

Scope

Features: #5 Own: README.md, docs/semantic-setup.md, config.json.example Depend on: Agents 0, 1, 2 (need finalized tool names and config) Block: None

Interfaces

Export

  • Updated README sections
  • Semantic setup guide
  • Config reference
  • Troubleshooting guide

Receive

  • Finalized tool names, config keys, error messages from Agents 0-2

Features

#5: Documentation Updates

TL;DR: Document semantic setup, query tools, config reference, and troubleshooting. Status: GAP Test IDs: docs-semantic-setup, docs-config-reference, docs-troubleshooting Files: README.md, docs/semantic-setup.md, config.json.example

Documentation Sections:

  1. Semantic Setup Guide

    • Ollama installation (macOS, Linux, Windows)
    • Model download: ollama pull nomic-embed-text
    • Config enable: semantic.enabled: true
    • Verification: how to confirm it's working

  2. Config Reference

    • All semantic.* options with defaults and descriptions
    • Character-based chunking explanation (2000 chars ≈ 500 tokens)
    • Model compatibility notes (768-dim models recommended)

  3. Troubleshooting

    • "Ollama not running" — symptoms, fix
    • "Wrong model dimensions" — symptoms, fix
    • "Embeddings not updating" — hash caching + model_name explanation
    • "Slow indexing" — batching, background indexing tips
    • "Model changed, old embeddings" — reindex_vectors with force

  4. Tool Reference

    • semantic_search, find_similar, reindex_vectors signatures
    • query_docs with/without semantic
    • Example usage for each

TDD:

  1. docs-semantic-setup → impl Ollama setup guide → refactor
  2. docs-config-reference → impl config documentation → refactor
  3. docs-troubleshooting → impl common issues guide → refactor

Done

  • README updated with semantic overview
  • Semantic setup guide (Ollama install, model, config)
  • Config reference with all options
  • Troubleshooting guide
  • Tool reference with examples
  • config.json.example updated

Read the full file on GitHub · 128 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. 2d ago First seen · 128 lines · 0 tokens per session scan A c23104133452

Subscribe to this mod's changes

004_agent_docs 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 804 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.

Data and AIDebuggingLLMTestingai-agentsai-planningai-testing-best-practiceslimps/agentlimps/persona/coderlimps/status/gapmcpmcp-server
Related

Other agents, from other repositories

monitor

Reviews code for correctness, standards, security, and testability (MAP).

azalio/map-framework · 17 tokens

evaluator

Evaluates solution quality and completeness (MAP).

azalio/map-framework · 12 tokens

predictor

Predicts consequences and dependency impact of changes (MAP).

azalio/map-framework · 14 tokens

task-decomposer

Breaks complex goals into atomic, testable subtasks (MAP).

azalio/map-framework · 18 tokens

actor

Generates production-ready implementation proposals (MAP).

azalio/map-framework · 11 tokens

reflector

Extracts structured lessons from successes and failures.

azalio/map-framework · 11 tokens