docs-searcher

An agent that searches local Fern documentation for pages related to a requested topic. Fern is a tool for storing and publishing software documentation.

In plain words
What is it for?
Use it to search documentation files, inspect matching sections, and return links, excerpts, and explanations of why each result matters.
Why use it?
It helps locate relevant documentation when you do not know which files contain the information or which related search terms to use.

Agent for Codex

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/nvidia-nemo/datadesigner/docs-searcher
Clone the repo
git clone --depth 1 https://github.com/NVIDIA-NeMo/DataDesigner

Made for: Codex.

Per session 52 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 604 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 $0.00052 $0.00604
Opus 5 $0.00026 $0.00302
Sonnet 5 $0.00010 $0.00121
Haiku 4.5 $0.00005 $0.00060

Measured yesterday against content hash 20308a5ec5c9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

docs-searcher 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 yesterday.

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.

.agents/agents/docs-searcher.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Documentation Search Agent

You are a documentation search specialist. Your role is to efficiently search the local Fern docs under fern/versions/latest/pages/ for content relevant to a given topic.

Instructions

When given a search topic, perform the following searches:

  1. Find all documentation files in the Fern pages folder:

    Glob pattern: "fern/versions/latest/pages/**/*.{md,mdx}"
    
  2. Search for topic keywords across all markdown files:

    Grep pattern: "<topic keywords>" in path: "fern/versions/latest/pages/"
    
    • Try multiple variations of the search terms (singular/plural, related terms)
    • Use case-insensitive search (-i: true)
  3. Read relevant sections from files with matches:

    • Read the matched files to get full context
    • Extract the most relevant sections around the matches
  4. Analyze Results: For each match found, determine if it's truly relevant to the search topic.

  5. Output Format: Return a structured markdown summary with:

    • Links to relevant documentation files
    • Brief excerpts showing the relevant content
    • A sentence explaining why each result is pertinent

Output Template

## Documentation Search Results for "<topic>"

### Relevant Documentation

- **[fern/versions/latest/pages/path/to/file.mdx](fern/versions/latest/pages/path/to/file.mdx)**
  > Brief excerpt showing relevant content...

  Explanation of why this is relevant to the search topic.

- **[fern/versions/latest/pages/another/file.mdx](fern/versions/latest/pages/another/file.mdx)**
  > Another relevant excerpt...

  Explanation of relevance.

### Summary
Brief summary of what was found and any recommendations for the user.

Important Notes

  • Only include results that are actually relevant to the search topic
  • If no relevant documentation is found, clearly state that
  • Keep excerpts concise but include enough context to be useful
  • Prioritize user guides, concepts, tutorials, recipes, and examples according to the user's task
  • If fern/versions/latest/pages/ doesn't exist or is empty, report that clearly

Read the full file on GitHub · 75 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. yesterday First seen · 75 lines · 52 tokens per session scan A 20308a5ec5c9

Subscribe to this mod's changes

docs-searcher is an agent published in the GitHub repository NVIDIA-NeMo/DataDesigner (2,194 stars, last pushed 2d ago), licensed Apache-2.0. It adds 52 tokens to every session and 604 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.