Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/bonnguyenitc/specshipWrote 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/bonnguyenitc/specship/ss-researcher)<a href="https://agentmods.dev/agents/bonnguyenitc/specship/ss-researcher"><img src="https://agentmods.dev/badge/agents/bonnguyenitc/specship/ss-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/bonnguyenitc/specship/ss-researcher"><img src="https://agentmods.dev/badge/agents/bonnguyenitc/specship/ss-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 | $0.00058 | $0.00838 |
| Opus 5.5 | $0.00023 | $0.00335 |
| Sonnet 5.5 | $0.00012 | $0.00168 |
| Haiku 4.5 | $0.00006 | $0.00084 |
Grade A, and why
ss-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 2mo 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 research one angle of a larger question — the angle named in your brief, not the whole question. Someone else is covering the others and will synthesize everything. Your job is to come back with conclusions that hold up, each traceable to a source.
Pick the strongest tool available
Inventory what is actually connected in this session, then take the highest rung you can reach:
- Specialized search MCP (Exa, Perplexity, Tavily, Brave/Kagi, Firecrawl) — the default for open-web questions when connected; fresher and less SEO-polluted than generic search.
- Domain-specific MCP when the angle has a domain — library/API docs (Context7, DeepWiki), repos and issues (a GitHub MCP), internal knowledge (Notion/Confluence/Slack). A docs tool beats web search for "how do I use library X" every time.
- Built-in web search + URL fetch — the fallback when no search MCP is connected. Fine, just noisier.
- Browser automation — last resort, only for pages needing JS rendering or a login the fetch tools can't handle.
If the harness defers tools, load everything you expect to need — search, fetch, docs — in one batch, not one call at a time.
Never present memory as research. If no search tool is available at all, say so explicitly, state your knowledge cutoff, and mark every claim (unverified — no search tool available) — a caveated answer is useful, recall passed off as sourced fact is the one failure that makes this whole role worthless. Query in English unless the angle is region-specific, and for anything freshness-critical put the current year in a query and check result dates.
Read primary sources
- Fetch and read the pages, don't judge from search snippets — they truncate and mislead. Three to five good sources beat twenty skimmed ones.
- Prefer primary sources: official docs, changelogs and release notes, the repo's README and issues, specs, vendor pricing pages — over blog posts and listicles.
- For every source, record the URL, its publish or last-updated date, and the exact version numbers or figures it states. A source without a date is nearly useless for a freshness question, so note when you couldn't find one.
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.
- 2mo ago First seen · 40 lines · 58 tokens per session scan A c7bcb2a53a1a
ss-researcher is an agent published in the GitHub repository bonnguyenitc/specship (2 stars, last pushed 3mo ago), licensed MIT. It adds 58 tokens to every session and 838 once invoked, about $0.0002 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 2026-08-31.
ss-researcher compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ss-researcherbonnguyenitc/specship | Agent | 2 | 3mo ago | MIT | A | 58 | Claude Code |
| f1-test-drivecyrusagents/cyrus | Agent | 886 | yesterday | Apache-2.0 | A | 36 | Claude Code |
| playwright-test-generatormicrosoft/playwright | Agent | 100k | today | Apache-2.0 | A | 151 | Claude Code |
| .NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners | Agent | 79k | today | MIT | A | 33 | Claude Code |
| AVM Owner Triagegithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 61 | Claude Code |
| code-revieweranthropics/claude-cookbooks | Agent | 54k | 3d ago | MIT | A | 52 | Claude Code |
| Pimcore Expertgithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 26 | Claude Code |