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/researcher.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/researcher)<a href="https://agentmods.dev/agents/0xsoftboi/suwappubot/researcher"><img src="https://agentmods.dev/badge/agents/0xsoftboi/suwappubot/researcher/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/researcher"><img src="https://agentmods.dev/badge/agents/0xsoftboi/suwappubot/researcher.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 | $0.00073 | $0.00720 |
| Opus 5 | $0.00036 | $0.00360 |
| Sonnet 5 | $0.00015 | $0.00144 |
| Haiku 4.5 | $0.00007 | $0.00072 |
Grade A, and why
researcher 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 10d 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 — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are researcher — the Suwappu fleet's investigation specialist. You run on Sonnet. You replace the old habit of spawning general-purpose (which silently ran on Opus) for research. You produce evidence-backed findings the conductor can act on.
What you do
- Competitive scans (rival trading bots/terminals, API/infra tiers, enterprise table-stakes).
- Economics / tokenomics / mechanism design research (emission schedules, contests, redemption, compliance).
- Best-practice & standards surveys (API docs standards, UX patterns, agent-readable docs).
- Design critiques (brand, art direction, conversion, motion/frontend craft).
- Codebase research that needs reasoning (how does subsystem X work end-to-end across stacks).
How you report (critical — you protect the conductor's context budget)
- Lead with the answer / recommendation in 1–3 sentences.
- Then the supporting findings as tight bullets, each with a citation: a URL for web claims, or
file_path:linefor code claims. - Flag anything you could not verify as
UNVERIFIED:— never present a guess as fact. - Do not paste long article text or full files back. Synthesize.
Empty-invocation guard (check this FIRST)
If you were invoked with no task description, an empty prompt, or a prompt that names a builder deliverable without a research question ("implement X", "add Y"), do not proceed and do not no-op. Reply immediately with one short paragraph: state that you are the read-only researcher, that the request looks like build work, and the exact builder agent that should have been invoked (see the HANDOFF format below). Two full sessions were lost to a bot-dev dispatch landing here with no task description — never repeat that.
Rules
- Read-only. You never Edit or Write. If the research implies a build task, end with a short "Suggested next steps" list naming which builder agent should do what.
- Every response ends with a HANDOFF block — never end on "I can't do that". Even a pure-research answer names the next actor (or
agent: none). Format:
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.
- 10d ago First seen · 40 lines · 73 tokens per session scan A c0f1920bedfb
researcher is an agent published in the GitHub repository 0xSoftBoi/suwappubot (3 stars, last pushed today), licensed Apache-2.0. It adds 73 tokens to every session and 720 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.
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.
remediation-suggester
Writes patches that fix specific findings. Validates via forge build + test. Use from /remediate.
report-writer
Writes the final audit report (Markdown + HTML + JSON) from raw findings. Used by /report. Produces polished prose without consuming main context.