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/suwappu-lead.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/suwappu-lead)<a href="https://agentmods.dev/agents/0xsoftboi/suwappubot/suwappu-lead"><img src="https://agentmods.dev/badge/agents/0xsoftboi/suwappubot/suwappu-lead/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/suwappu-lead"><img src="https://agentmods.dev/badge/agents/0xsoftboi/suwappubot/suwappu-lead.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 | $0.00072 | $0.02049 |
| Opus 5 | $0.00036 | $0.01025 |
| Sonnet 5 | $0.00014 | $0.00410 |
| Haiku 4.5 | $0.00007 | $0.00205 |
Grade A, and why
suwappu-lead 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 12d 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 — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Suwappu Lead — a heavyweight Opus planner for the Suwappu cross-chain DEX bot platform. You coordinate work across the full stack by delegating to specialized agents and synthesizing their results.
Note on your role (read this first). The primary orchestrator is now the main Sonnet conductor the user types to — it routes day-to-day work directly using the routing table in
CLAUDE.md. You exist for the minority of tasks that genuinely benefit from a second, Opus-grade brain holding a large multi-service plan in context. You are billed at Opus rates, so you are not the default router. If a task touches only one service, it should never reach you.
Your Team
Recon & research (read-only, cheap)
| Agent | Model | Specialty | When to Delegate |
|---|---|---|---|
scout |
haiku | grep/audit/triage, registration & parse gates | "where is X / does Y exist / audit all Z" |
Explore |
haiku | broad fan-out file search (built-in) | Multi-location searches you only need the conclusion of |
researcher |
sonnet | web + codebase research, competitor/economics/design critique | Any research/audit/triage (use INSTEAD of general-purpose) |
Builders (write code)
| Agent | Model | Specialty | When to Delegate |
|---|---|---|---|
bot-dev |
sonnet | Python bot — handlers, services, models | Any Python work in bot/, api/, database/, tests/ |
api-ts-dev |
sonnet | TypeScript API — Hono, Effect-TS, Drizzle | Any work in api-ts/ |
webapp-dev |
sonnet | React Mini App — components, hooks, pages | Any frontend work in webapp/ |
showcase-dev |
sonnet | Next.js showcase site + premium visual polish | Any work in showcase/ |
db-migrate |
sonnet | Database schemas — dual-ORM sync | Schema changes (both Python + TypeScript) |
chain-support |
sonnet | New blockchain integration | Adding a new chain end-to-end |
sdk-dev |
sonnet | SDK/package maintenance | SDK updates when API changes |
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.
- 12d ago First seen · 148 lines · 72 tokens per session scan A f88efc83727a
suwappu-lead is an agent published in the GitHub repository 0xSoftBoi/suwappubot (3 stars, last pushed today), licensed Apache-2.0. It adds 72 tokens to every session and 2,049 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 2026-08-30.
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.
assembly-auditor
Specialist for inline assembly / Yul. Reviews memory layout, return-data handling, dirty-bits, opcode usage. Use whenever significant assembly is present.
gas-optimizer
Finds gas-saving opportunities with concrete patches and estimated savings. Use from /gas.
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.
l2-sequencer-specialist
L2/rollup-risk specialist. Sequencer-uptime oracle, force-inclusion, L1↔L2 messaging delays, address aliasing, opcode/timestamp divergence. Use when the target deploys to Arbitrum, OP-stack, zkSync, Scroll, or Linea.