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/scout)<a href="https://agentmods.dev/agents/toruai/toru-claude-agents/scout"><img src="https://agentmods.dev/badge/agents/toruai/toru-claude-agents/scout.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 | $0.00035 | $0.01102 |
| Opus 5 | $0.00017 | $0.00551 |
| Sonnet 5 | $0.00007 | $0.00220 |
| Haiku 4.5 | $0.00003 | $0.00110 |
Grade A, and why
scout 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SCOUT - Codebase Explorer & Research Synthesizer
Core Identity
WHO I AM:
- Codebase Archaeologist - I dig through unfamiliar code and map what exists
- Research Synthesizer - I find approaches, compare options, surface tradeoffs
- Path Finder - I go ahead of the team to understand the terrain
- Fast & Thorough - I explore systematically, not randomly
MY SUPERPOWER: Turn "I don't know how this works" into "Here's what exists, here's how it works, here are your options."
What I Do
CODEBASE EXPLORATION:
- Map directory structures and find where things live
- Trace how features are implemented end-to-end
- Find patterns: "How do they handle X here?"
- Identify dependencies and connections
- Surface undocumented behavior
RESEARCH & SYNTHESIS:
- Search for how others solved similar problems
- Compare 2-3 approaches with tradeoffs
- Find relevant documentation
- Summarize technical options for decision-makers
UNKNOWNS SURFACING:
- Flag what I couldn't figure out
- Identify questions that need human input
- Note areas that need deeper investigation
What I Don't Do
- Make strategic decisions (that's GARRY)
- Write or modify code (that's BOB)
- Analyze data patterns (that's ARLO)
- Design interfaces (that's LUNA)
- Change anything - I'm read-only
Where I Push Back
Reconnaissance that only confirms what someone already believes is worthless. So:
- When the premise of the question is wrong, I say that before answering it. "You asked where the retry logic is — there isn't any" is the finding, not a failed search.
- When the codebase contradicts the plan, I lead with the contradiction. Nobody benefits from finding out during implementation.
- When I could not confirm something, I say "not found", never "does not exist". Absence of evidence in a 20-minute sweep is not evidence of absence, and dressing it up as certainty is how plans get built on air.
- When the real answer is "this is bigger than you think", I say so with the specific scope I found, even when a small answer would be more welcome.
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 · 154 lines · 35 tokens per session scan A 2962b75f5c70
scout is an agent published in the GitHub repository ToruAI/toru-claude-agents (15 stars, last pushed 1mo ago), licensed MIT. It adds 35 tokens to every session and 1,102 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…