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.
npx skills add bonnguyenitc/specship --skill ss-researchgit 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/skills/bonnguyenitc/specship/ss-research)<a href="https://agentmods.dev/skills/bonnguyenitc/specship/ss-research"><img src="https://agentmods.dev/badge/skills/bonnguyenitc/specship/ss-research/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/skills/bonnguyenitc/specship/ss-research"><img src="https://agentmods.dev/badge/skills/bonnguyenitc/specship/ss-research.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 | $0.00122 | $0.01833 |
| Opus 5 | $0.00061 | $0.00916 |
| Sonnet 5 | $0.00024 | $0.00367 |
| Haiku 4.5 | $0.00012 | $0.00183 |
Grade A, and why
ss-research 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research
Goal: turn a question into a current, verified, cited answer. Model memory has a training cutoff and no sources — never answer a time-sensitive or external-fact question from memory alone.
When to use
- "Research X", "compare X vs Y", "what's the best library for X?".
- Choosing a dependency, API, service, or architecture that external facts decide.
- Anything where "latest", "current", version numbers, pricing, or dates matter.
- A pipeline stage (
spec,plan) hits an open question only the outside world can answer.
Not for questions the repo itself answers — use ss-explore-source / code search
for those.
Step 1 — Frame the question
Before any search, pin down (ask the user only if the answer changes the work):
- Decision: what will this research be used for? Research feeding "pick a library" needs comparison criteria; "how does this API work" needs docs.
- Freshness: does it need this week's state (releases, pricing) or stable knowledge (algorithms, standards)?
- Depth: quick answer, comparison table, or deep report? Match effort to it.
Step 2 — Pick the strongest search tool available
Inventory the session's tools first — list what's actually connected (MCP servers, built-ins) instead of defaulting to the generic web search. Then pick the highest rung available on this ladder:
- Specialized search MCP — e.g. Exa, Perplexity, Tavily, Brave/Kagi Search, Firecrawl. These return richer, fresher, less SEO-polluted results than generic search; if one is connected, it is the default for open-web questions.
- Domain-specific MCP when the question has a domain — library/API docs: Context7, DeepWiki; repos/issues/PRs: a GitHub MCP; internal knowledge: Notion/Confluence/Slack MCPs. 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 MCP search is connected. Still fine; just expect more noise.
- Browser automation — last resort, only for pages that need JS rendering or a login the fetch tools can't handle.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 161 lines · 122 tokens per session scan A 77719c11f61b
ss-research is a skill published in the GitHub repository bonnguyenitc/specship (2 stars, last pushed 1mo ago), licensed MIT. It adds 122 tokens to every session and 1,833 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
design-taste-frontend
Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design systems when applicable, audit-first on redesigns, strict pre-flight check.
html-artifacts
Author the HTML for a plan artifact, dashboard iframe, or Slack attachment — structure, design plan, available runtime, theming, and craft. Read this before writing HTML for saveplan, outputiframe, or slackattachhtml.
design-taste-frontend-v1
The original v1 taste-skill, preserved for projects depending on its exact behavior. The current default is design-taste-frontend (v2 experimental), which is a substantial rewrite. Use this v1 install name only if you need exact backward compatibility.
brandkit
Premium brand-kit image generation skill for creating high-end brand-guidelines boards, logo systems, identity decks, and visual-world presentations. Trained for minimalist, cinematic, editorial, dark-tech, luxury, cultural, security, gaming, developer-tool, and consumer-app brand systems. Optimized for intentional…
redesign-existing-projects
Upgrades existing websites and apps to premium quality. Audits current design, identifies generic AI patterns, and applies high-end design standards without breaking functionality. Works with any CSS framework or vanilla CSS.
gpt-taste
Elite UX/UI & Advanced GSAP Motion Engineer. Enforces Python-driven true randomization for layout variance, strict AIDA page structure, wide editorial typography (bans 6-line wraps), gapless bento grids, strict GSAP ScrollTriggers (pinning, stacking, scrubbing), inline micro-images, and massive section spacing.