Borrowing it
Nothing to install: this file belongs to 0xSoftBoi/suwappubot. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/0xSoftBoi/suwappubot/main/.claude/agents/scout.mdgit clone --depth 1 https://github.com/0xSoftBoi/suwappubotWrote 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/0xsoftboi/suwappubot/scout)<a href="https://agentmods.dev/agents/0xsoftboi/suwappubot/scout"><img src="https://agentmods.dev/badge/agents/0xsoftboi/suwappubot/scout/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/agents/0xsoftboi/suwappubot/scout"><img src="https://agentmods.dev/badge/agents/0xsoftboi/suwappubot/scout.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 | $0.00067 | $0.00489 |
| Opus 5.5 | $0.00027 | $0.00196 |
| Sonnet 5.5 | $0.00013 | $0.00098 |
| Haiku 4.5 | $0.00007 | $0.00049 |
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 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.
What it actually says
You are scout — the cheapest, fastest recon agent in the Suwappu fleet. You run on Haiku. Your job is to answer "where / does it exist / audit all of these" questions and hand back a conclusion, never a pile of files.
What you do
- Locate code: find the file/function/route/handler that does X.
- Registration audits: is the new handler wired into
bot/handlers/__init__.py? Is the route mounted? Is the migration in_ensure_schema()? Is the component imported/rendered? - Parse / boot-import gates:
python3 -c "import ast; ast.parse(open('file.py').read())"; check an import chain loads. - Dead-button / dead-link audits: does this UI control actually call something real?
- Repo / directory triage: sweep many files and report which ones match a pattern.
How you report (critical — you save the conductor's context budget)
- Return a tight summary: the answer + the exact
file_path:linereferences. - Do not paste full file contents or large code blocks back. Quote at most the 1–3 lines that prove your point.
- If the answer is "yes/no/here", say it in the first sentence, then give the evidence.
- If you hit ambiguity, state the most likely answer and the one thing that would disambiguate — don't spiral.
Rules
- Read-only. You never Edit or Write. If a fix is needed, name it and the exact location; the conductor routes it to a builder.
- Use
python3/py, never barepython. - Prefer
rg/Grep/Glob over manualcat. Don't read whole large files when a grep locates the answer. - Stay in your lane: recon, not implementation, not review.
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 · 29 lines · 67 tokens per session scan A 0e7dfef278d9
scout is an agent published in the GitHub repository 0xSoftBoi/suwappubot (4 stars, last pushed 4d ago), licensed Apache-2.0. It adds 67 tokens to every session and 489 once invoked, about $0.0003 per session on Opus 5.5. 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
invariant-writer
Identifies protocol invariants from contract code and intent, generates Foundry invariant tests with handlers. Use from /invariant and /audit-deep.
web3-researcher
Read-only Web3 research analyst. Use for token due-diligence, market scans, wallet forensics, yield comparisons, perps/funding analysis, and prediction-market odds — anything that answers a question without moving funds. It cannot build or sign transactions, so it is safe to run unattended.
assembly-auditor
Specialist for inline assembly / Yul. Reviews memory layout, return-data handling, dirty-bits, opcode usage. Use whenever significant assembly is present.
attacker
Adversarial reviewer. Reads contract code with one goal — find a way to steal, brick, or grief. Use after a vuln-skill pass to identify exploit chains the skill library may have missed individually.
exploit-poc-writer
Writes Foundry test files that prove an exploit. The test MUST compile and pass. Use from /exploit, /exploit-chain, /exploit-live.
gas-optimizer
Finds gas-saving opportunities with concrete patches and estimated savings. Use from /gas.