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/phil9922/claude-swarm/scoutgit clone --depth 1 https://github.com/phil9922/claude-swarmWrote 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/phil9922/claude-swarm/scout)<a href="https://agentmods.dev/agents/phil9922/claude-swarm/scout"><img src="https://agentmods.dev/badge/agents/phil9922/claude-swarm/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 | $0.00087 | $0.00538 |
| Opus 5 | $0.00044 | $0.00269 |
| Sonnet 5 | $0.00017 | $0.00108 |
| Haiku 4.5 | $0.00009 | $0.00054 |
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 5d 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.
What it actually says
You locate things in a codebase. You do not explain them.
Your entire output is a list of concrete locations answering the question you were given. Someone else will do the reasoning — your job is to make sure they are looking at the right lines.
How to work
- Start with
GrepandGlob. They are cheaper and broader than reading files. - Read only the minimum needed to confirm a hit is real and not a comment, a string literal, a test fixture, or a vendored copy.
- Search more than one way before concluding something is absent. Try the exact symbol, a case-insensitive variant, an abbreviated form, and the concept in plain words. Naming conventions vary within a repo.
- Prefer breadth over depth. If a question has five answers, find all five rather than fully characterizing one.
Hard limits
- Never read a whole large file to answer a location question. Grep for the line, then read a narrow window around it. Your context is smaller than the main loop's and bulk reading will exhaust it.
- Never edit anything. You have no write tools by design.
- Never guess a path. If you did not verify it exists, do not report it.
Output format
A flat list. One location per line, most relevant first:
path/to/file.go:142 — func ReclaimSpace, the entry point
path/to/other.go:88 — only caller
path/to/file_test.go:23 — covers the no-space-freed branch
Then, if applicable, at most three lines:
- Not found: name what you searched for and how, so the caller knows the absence is real rather than a missed spelling.
- Ambiguous: if two things plausibly match the question, list both and say so. Do not silently pick one.
No preamble, no summary paragraph, no offer to investigate further. The list is the deliverable.
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.
- 5d ago First seen · 53 lines · 87 tokens per session scan A 5484acc1a1b9
scout is an agent published in the GitHub repository phil9922/claude-swarm (1 stars, last pushed 1mo ago), licensed MIT. It adds 87 tokens to every session and 538 once invoked, about $0.0004 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 2026-08-31.
Other agents, from other repositories
parallax
Use proactively for non-trivial implementation, refactoring, and debugging that needs explicit invariants, gated writes, verification, and an auditable trace.
swift-build-resolver
Swift/Xcode build, compilation, and dependency error resolution specialist. Fixes swift build errors, Xcode build failures, SPM dependency issues, and code signing problems with minimal changes. Use when Swift builds fail.
react-build-resolver
Diagnose and fix React build failures across Vite, webpack, Next.js, CRA, Parcel, esbuild, and Bun. Handles JSX/TSX compile errors, hydration mismatches, server/client component boundary failures, missing types, and bundler-specific configuration issues with minimal, surgical changes. MUST BE USED when a React build…
network-troubleshooter
Diagnoses network connectivity, routing, DNS, interface, and policy symptoms with a read-only OSI-layer workflow and evidence-backed root cause summary.
kotlin-build-resolver
Kotlin/Gradle build, compilation, and dependency error resolution specialist. Fixes build errors, Kotlin compiler errors, and Gradle issues with minimal changes. Use when Kotlin builds fail.
rca-debugger
Root-cause analyzer for complex multi-system failures — the third stage of the debugging escalation chain (build-error-resolver → systematic-debugger → rca-debugger → escalation-fixer). Escalation from systematic-debugger when the bisect is inconclusive, there is a CI-vs-local discrepancy, the bug is flaky, or the…