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 sinaptik-ai/starpod --skill web-researchgit clone --depth 1 https://github.com/sinaptik-ai/starpodWrote 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/sinaptik-ai/starpod/web-research)<a href="https://agentmods.dev/skills/sinaptik-ai/starpod/web-research"><img src="https://agentmods.dev/badge/skills/sinaptik-ai/starpod/web-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/sinaptik-ai/starpod/web-research"><img src="https://agentmods.dev/badge/skills/sinaptik-ai/starpod/web-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 | $0.00056 | $0.00849 |
| Opus 5 | $0.00028 | $0.00425 |
| Sonnet 5 | $0.00011 | $0.00170 |
| Haiku 4.5 | $0.00006 | $0.00085 |
Grade A, and why
web-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 11d 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Web Research
Methodology
Follow this structured approach for any research task:
1. Scope the question
Before searching, clarify:
- What specifically does the user need to know?
- What format should the answer take? (summary, comparison table, list, report)
- How deep should the research go? (quick answer vs. comprehensive analysis)
2. Search strategy
- Start with 2–3 targeted queries using different phrasings
- Use specific terms, not vague ones: "React server components vs client components performance 2025" beats "React performance"
- For comparisons, search each option independently before comparing
- For recent topics, include the year in queries
- If initial results are thin, broaden terms or try adjacent queries
3. Source evaluation
Prioritize sources in this order:
- Official documentation — most reliable for technical topics
- Primary sources — research papers, official reports, announcements
- Expert analysis — recognized experts, reputable publications
- Community consensus — Stack Overflow, GitHub discussions (check vote counts and recency)
- News articles — for current events, cross-reference multiple outlets
Red flags: outdated dates, no author attribution, SEO-farm patterns, contradicted by official sources.
4. Synthesize findings
- Lead with the direct answer, then supporting evidence
- Note conflicting information across sources and which is more credible
- Include source URLs for key claims
- Flag uncertainty: "Based on available data..." or "Sources disagree on..."
- Distinguish facts from opinions
5. Present results
For quick questions: Direct answer in 2–3 sentences with source link.
For comparisons:
| Criteria | Option A | Option B |
|---|---|---|
| Key metric | Value | Value |
| Pros | ... | ... |
| Cons | ... | ... |
For deep research: Structure as:
- Summary — 2–3 sentence answer
- Key findings — bulleted list of important points
- Analysis — detailed discussion organized by theme
- Sources — numbered list of references used
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.
- 11d ago First seen · 95 lines · 56 tokens per session scan A bae8b00b739d
web-research is a skill published in the GitHub repository sinaptik-ai/starpod (78 stars, last pushed 5mo ago), licensed MIT. It adds 56 tokens to every session and 849 once invoked, about $0.0003 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 skills, from other repositories
personal-assistant
Use this skill whenever the user acts like Bamboo is their personal assistant. Triggers include stating commitments, deadlines, appointments, or recurring routines ("remind me to...", "I need to... by Friday", "every Monday I..."), asking to be reminded of something, agenda questions ("what's on my plate", "what's due…
review
Review code changes, pull requests, patches, or a scoped code area for actionable correctness, security, compatibility, and test risks with file and line evidence. Use for review or audit requests; do not use for general proofreading, feature implementation, or debugging a reported failure when the user wants a fix.
debug
Diagnose a concrete failure, regression, crash, hang, flaky test, or incorrect runtime behavior by reproducing it, testing hypotheses, and identifying the evidence-backed root cause. Use when symptoms or failing output exist; do not use for feature implementation without a failure, general code review, or a conceptual…
plan
Build an executable implementation, migration, or rollout plan from read-only repository exploration, including constraints, dependencies, ordered changes, verification, risks, and rollback points. Use when the user asks for a plan or decomposition before implementation; do not use when they want a small change…
research
Investigate a technical or product question using current primary sources and relevant repository evidence, then synthesize cited facts, explicit inferences, uncertainties, and implications. Use when freshness, external documentation, comparisons, or multi-source evidence matter; do not use for simple stable facts…
simplify
Reduce unnecessary code complexity, duplication, indirection, or abstraction while preserving observable behavior and validating equivalence. Use for simplify, cleanup, or behavior-preserving refactor requests; do not use for adding features, diagnosing an unexplained failure, broad code review without a…