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.
git clone --depth 1 https://github.com/ruvnet/ruv-FANNWrote 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/commands/ruvnet/ruv-fann/specialization)<a href="https://agentmods.dev/commands/ruvnet/ruv-fann/specialization"><img src="https://agentmods.dev/badge/commands/ruvnet/ruv-fann/specialization/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/ruvnet/ruv-fann/specialization"><img src="https://agentmods.dev/badge/commands/ruvnet/ruv-fann/specialization.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00283 |
| Opus 5.5 | $0.00000 | $0.00113 |
| Sonnet 5.5 | $0.00000 | $0.00057 |
| Haiku 4.5 | $0.00000 | $0.00028 |
Grade A, and why
specialization 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 1mo 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.
This is a copy
95% identical to specialization — 114 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Agent Specialization Training
Purpose
Train agents to become experts in specific domains for better performance.
Specialization Areas
1. By File Type
Agents automatically specialize based on file extensions:
- .js/.ts: Modern JavaScript patterns
- .py: Pythonic idioms
- .go: Go best practices
- .rs: Rust safety patterns
2. By Task Type
Tool: mcp__ruv-swarm__agent_spawn
Parameters: {
"type": "coder",
"capabilities": ["react", "typescript", "testing"]
}
3. Training Process
The system trains through:
- Successful edit operations
- Code review patterns
- Error fix approaches
- Performance optimizations
4. Specialization Benefits
# Check agent specializations
Tool: mcp__ruv-swarm__agent_list
Parameters: {"filter": "active"}
Result shows expertise levels:
{
"agents": [
{
"id": "coder-123",
"specializations": {
"javascript": 0.95,
"react": 0.88,
"testing": 0.82
}
}
]
}
Continuous Improvement
Agents share learnings across sessions for cumulative expertise!
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.
- 1mo ago First seen · 53 lines · 0 tokens per session scan A 1805d6a4ea2f
specialization is a command published in the GitHub repository ruvnet/ruv-FANN (387 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 283 tokens. A static security scan graded it A with 0 findings. It is 95% identical to specialization, differing in 114 lines, and is treated as a copy.
Other commands, from other repositories
learn-story-flow
Learn story-flow concepts with interactive guidance for junior developers.
start-10-1
A guided lesson on setting up clasp, a command-line tool for managing Google Apps Script projects, and connecting it to Google’s Apps Script API.
start-0-8
A Japanese-language command that displays the current project setup progress.
setup-m365cli.es
Lesson command — Setup de M365 CLI.
prep-role
Deep prep for a specific role's interview process. The user wants to know what to expect, how to win, and what kills candidates at their level.
start-1
A guided beginner course for product managers learning Claude Code, a coding assistant that works from the command line.