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/commands/audit-fleet.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/commands/0xsoftboi/suwappubot/audit-fleet)<a href="https://agentmods.dev/commands/0xsoftboi/suwappubot/audit-fleet"><img src="https://agentmods.dev/badge/commands/0xsoftboi/suwappubot/audit-fleet/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/0xsoftboi/suwappubot/audit-fleet"><img src="https://agentmods.dev/badge/commands/0xsoftboi/suwappubot/audit-fleet.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 | $0.00041 | $0.00583 |
| Opus 5 | $0.00020 | $0.00292 |
| Sonnet 5 | $0.00008 | $0.00117 |
| Haiku 4.5 | $0.00004 | $0.00058 |
Grade A, and why
audit-fleet 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 9d 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 — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Parallel Security Audit Fleet
The serial /audit repeatedly died at the spend limit before emitting parseable JSON. This version fans out narrow scopes and makes every finding durable on disk the moment it is confirmed, so an interrupted run still ships results.
Step 1 — Map the attack surfaces
Use scout (haiku) to group the in-scope files into 4–6 disjoint scopes:
auth— session/JWT/SIWE/telegramAuth, middleware, route mountingmoney— swap execution, balance mutations, fee math, withdrawals, redemptionswebhooks— inbound HTTP: Telegram, WhatsApp, Stripe, x402keys— wallet encryption, KMS envelope, key derivation, recoveryjobs— background services inapi/main.pylifespan Remember: two backends (api/+bot/Python,api-ts/TypeScript). Cover both.
Write the scope map to .audit/scopes.json before dispatching.
Step 2 — Fan out (one security-auditor per scope, in ONE message)
Give each agent this contract verbatim:
Trace real data flow from entrypoint to sink — do not pattern-match. After finishing each file, immediately append one JSON object per finding to
.audit/findings/<scope>.jsonl:{file, line, severity, title, exploit_path, preconditions, confidence, false_positive_reasoning}Never buffer findings until the end. Mark false positives explicitly with why they are not exploitable. Keep your response short — detail goes to disk. Finish with a coverage note: what you did NOT look at and why.
Step 3 — Reduce
Read all .audit/findings/*.jsonl, dedupe by file:line+title, rank by exploitability × blast radius. Write the ranked list to .audit/report.md.
Step 4 — Prove and file
For each finding with confidence >= high:
- Write a failing test under
tests/security/that demonstrates the bug (test-engineer). gh issue createwith the exploit path and the test path. Anything touching swap exec / keys / KMS / fees / withdrawals goes tomoney-path-reviewer(opus) before any fix is merged.
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.
- 9d ago First seen · 37 lines · 41 tokens per session scan A b7c113a3fe0d
audit-fleet is a command published in the GitHub repository 0xSoftBoi/suwappubot (3 stars, last pushed yesterday), licensed Apache-2.0. It adds 41 tokens to every session and 583 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 commands, from other repositories
debug-order
Debug why a CoW Protocol order failed to match.
krait
Run a complete multi-phase security audit on the target codebase.
krait-fuzz
Run an invariant-based fuzzing campaign: Understand → Extract Invariants → Generate Foundry Tests → Run & Fix Iteratively → Report.
krait-poc
Write and run a valid Foundry proof-of-concept that proves (or disproves) a Solidity exploit by asserting the actual harm on a forked chain or against local source.
krait-init
Standalone readiness check before running /krait. Verifies tools, project shape, gitignore, MCP wiring, and /.claude install. Reports what's missing — does NOT install or modify anything.
krait-review
Re-examine findings killed by the Critic's automatic gates. Catches over-filtering without compromising the main report's zero-FP standard.