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/nvidia-nemo/datadesigner/docs-searchergit clone --depth 1 https://github.com/NVIDIA-NeMo/DataDesignerWhat 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 | $0.00052 | $0.00604 |
| Opus 5 | $0.00026 | $0.00302 |
| Sonnet 5 | $0.00010 | $0.00121 |
| Haiku 4.5 | $0.00005 | $0.00060 |
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.
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:
-
Find all documentation files in the Fern pages folder:
Glob pattern: "fern/versions/latest/pages/**/*.{md,mdx}" -
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)
-
Read relevant sections from files with matches:
- Read the matched files to get full context
- Extract the most relevant sections around the matches
-
Analyze Results: For each match found, determine if it's truly relevant to the search topic.
-
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
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.
- yesterday First seen · 75 lines · 52 tokens per session scan A 20308a5ec5c9
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.
Other agents, from other repositories
codemap
Defines agent personalities (Orchestrator, Explorer, Librarian, etc.) and manages their configuration lifecycle. This directory implements the Agent Factory Pattern, where each agent is a specialized sub-agent with distinct capabilities, permissions, and routing rules. The Orchestrator agent (src/agents/index.ts)…
researcher
You stop coding and start investigating when the problem is unclear. Every problem can be solved with enough information.
research-agent
You are an autonomous research agent conducting systematic information gathering and analysis.
api-designer
REST and GraphQL API design - endpoint design, request/response schemas, versioning, and documentation. Use for designing new APIs or evolving existing ones.
agent-prompt-dream-memory-consolidation
Instructs an agent to perform a multi-phase memory consolidation pass — orienting on existing memories, gathering recent signal from logs and transcripts, merging updates into topic files, and pruning the index.
algorithm-expert
RL algorithm expert. Fire when working on GRPO/PPO/DAPO/GSPO/SAPO algorithms, reward functions, advantage normalization, loss computation, or training loop implementation.