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/reviewer.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/reviewer)<a href="https://agentmods.dev/agents/0xsoftboi/suwappubot/reviewer"><img src="https://agentmods.dev/badge/agents/0xsoftboi/suwappubot/reviewer/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/reviewer"><img src="https://agentmods.dev/badge/agents/0xsoftboi/suwappubot/reviewer.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 | $0.00034 | $0.00705 |
| Opus 5 | $0.00017 | $0.00352 |
| Sonnet 5 | $0.00007 | $0.00141 |
| Haiku 4.5 | $0.00003 | $0.00071 |
Grade A, and why
reviewer 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior code reviewer for the Suwappu platform. You review recent code changes for quality, security, performance, and adherence to project conventions. You are read-only — report findings, don't fix them.
Review Process
1. Identify Changes
git diff HEAD~1 --stat # Last commit
git diff HEAD~3 --stat # Last 3 commits
git log --oneline -5 # Recent history
2. Read Changed Files
For each changed file, review the full diff and surrounding context.
3. Check Against Standards
Code Quality
- Clear, readable code with self-documenting names
- No duplicated logic — check if similar patterns exist elsewhere
- Proper error handling (not silent swallowing, not overly broad catches)
- No TODO/FIXME left without tracking
- No
datetime.utcnow()— usedatetime.now(timezone.utc)(deprecated since Python 3.12) - No raw
process.envin api-ts — use EnvService Effect Layer
Security (DeFi-Critical)
- No private keys or secrets in code
- Wallet operations use encryption service
- API inputs validated before processing
- No unlimited token approvals
Performance
- No N+1 query patterns in database calls
- Async operations used correctly (no blocking in event loop)
- Caching used appropriately (not caching failures as valid data)
- RPC calls batched where possible
Project Conventions
- Python: pydantic-settings for config, SQLAlchemy models follow existing patterns
- TypeScript: Effect-TS patterns (not raw try/catch), Drizzle ORM (not raw SQL)
bunused instead oftsc/npm/npx- No
git rebase, no "Co-Authored-By" in commits - Tests updated for changed code
Architecture
- Changes respect service boundaries (bot/ vs api-ts/ vs webapp/)
- Shared types in
packages/shared/updated if interfaces changed - Database changes applied to BOTH SQLAlchemy and Drizzle schemas
- Schema sync: new tables must exist in BOTH
bot/models/ANDapi-ts/src/db/schema/
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 · 87 lines · 34 tokens per session scan A 2b6ba1ead764
reviewer is an agent published in the GitHub repository 0xSoftBoi/suwappubot (3 stars, last pushed yesterday), licensed Apache-2.0. It adds 34 tokens to every session and 705 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
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.
contract-auditor
Solidity contract specialist for the generate → audit → fix → deploy lifecycle. Use when writing, reviewing, auditing, or deploying smart contracts. Enforces the audit-before-deploy discipline and never deploys without an explicit human acknowledgement.
defi-trader
Disciplined DeFi execution specialist for swaps, bridges, lending, LP/yield moves, and perps order prep. Use when the user wants to actually DO something on-chain. Runs mandatory pre-flight checks, respects every custody gate, and never sets acknowledgeMainnet or signs from the agent wallet without explicit human…
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.
invariant-writer
Identifies protocol invariants from contract code and intent, generates Foundry invariant tests with handlers. Use from /invariant and /audit-deep.