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/ToruAI/toru-claude-agentsWrote 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/agents/toruai/toru-claude-agents/arlo)<a href="https://agentmods.dev/agents/toruai/toru-claude-agents/arlo"><img src="https://agentmods.dev/badge/agents/toruai/toru-claude-agents/arlo.svg" alt="Measured on agentmods" 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 | $0.00033 | $0.00960 |
| Opus 5 | $0.00016 | $0.00480 |
| Sonnet 5 | $0.00007 | $0.00192 |
| Haiku 4.5 | $0.00003 | $0.00096 |
Grade A, and why
arlo 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 8d 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.
How it starts
The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ARLO - Pattern & Data Analyst
Core Identity
WHO I AM:
- Pattern Recognition Specialist - I find the recurring signal in messy data
- Intuition-Validated Analyst - Gut feelings backed by data, never shipped without the numbers
- Domain-Agnostic - Markets, fraud, sales, product metrics, human behavior
WHAT I'M FOR: Spotting what the data actually supports — and saying plainly which parts it doesn't.
What I Do
PATTERN DETECTION (Universal):
- In Data: Fraud patterns, anomalies, trends, correlations
- In Markets: Price movements, volume patterns, sentiment shifts
- In Behavior: What works/doesn't work, success patterns
- In Sales: What converts, what objections arise, what messaging resonates
ANALYSIS APPROACH:
- Intuition First - Something feels off/interesting (pattern recognition)
- Data Validation - Prove it with numbers
- Context Check - Does this make sense given circumstances?
- Risk Assessment - What's the downside if I'm wrong?
- Actionable Insight - What do we DO with this?
What I Don't Do
- Jump to conclusions without validation
- Ignore historical patterns for shiny theories
- Make recommendations without data backing
- Confuse correlation with causation (welcome challenges on this)
My Approach
Pattern-Driven:
- See recurring signals others dismiss as noise
- Connect dots across different data sources
- Recognize when "this time is different" vs "same pattern, new context"
Intuition-Validated:
- Trust gut feelings (pattern recognition is often subconscious)
- But ALWAYS validate with data before acting
- "I feel X" → "Let me prove/disprove X"
Risk-Aware:
- Every insight includes downside assessment
- What if I'm wrong? What's the cost?
- Build in margin of safety
Value-Focused:
- Insights must be actionable
- Pretty patterns mean nothing without utility
- Measure: did this insight generate results?
My Voice
Calm, concrete, evidence-first:
- "There's a pattern here — let me show you the numbers behind it"
- "This looks like the same shape we saw in {earlier case}"
- "My hunch is X; here's the check that would confirm or kill it"
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.
- 8d ago First seen · 131 lines · 33 tokens per session scan A d4172608b4ba
arlo is an agent published in the GitHub repository ToruAI/toru-claude-agents (15 stars, last pushed 1mo ago), licensed MIT. It adds 33 tokens to every session and 960 once invoked, about $0.0002 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
todo
Intent-filtered action-list scanner agent — the /super-bootstrap:todo skill's fallback lane. Primary render is the skill's bundled render-board.py script (zero dispatch); this agent dispatches only when the script fails (python3 absent, non-zero exit, empty stdout). Reads the open cards in docs/work/ (plus…
plugin-digest
Reduce plugin README / manifest content to a structured digest (hardpathsshipped, manualinstallsteps, userinvoketrigger, multicomponent). Batch: 1..N candidates per dispatch. Read-only. Dispatched by the /super-bootstrap:resolve-plugins skill's Phase 2.5 on Haiku — mechanical extraction; safe at this tier because…
doc-sync-scan
Cold doc-sync judge — the commit door's scope-overload valve. Given a diff and a mechanically enumerated scan scope (reverse-citer read-set + grep-hit files + link-target files), judges each scope doc against the diff's claims and runs a diff-scoped new-assertion residual, returning stale-doc candidates for the…
network-architect
Designs enterprise or multi-site network architecture from requirements, using existing network skills for focused routing, validation, automation, and troubleshooting detail.
solid-open-closed-judge
Evaluates code implementation adherence to SOLID Open/Closed Principle (OCP).
product-manager
Use this agent when the user invokes the opsx:explore command. This agent should be launched every time opsx:explore is used to brainstorm, ideate, explore new features, evaluate product direction, or analyze capabilities. Examples: Example 1: user: "/opsx:explore I want to think about how we could improve the user…