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 agentmods add skills/rootbr/rooted/researching-topicsnpx skills add rootbr/rooted --skill researching-topicsgit clone --depth 1 https://github.com/rootbr/rootedWrote 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/rootbr/rooted/researching-topics)<a href="https://agentmods.dev/skills/rootbr/rooted/researching-topics"><img src="https://agentmods.dev/badge/skills/rootbr/rooted/researching-topics.svg" alt="Measured on agentmods" 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 | $0.00200 | $0.02439 |
| Opus 5 | $0.00100 | $0.01220 |
| Sonnet 5 | $0.00040 | $0.00488 |
| Haiku 4.5 | $0.00020 | $0.00244 |
Grade A, and why
researching-topics 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 4d 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research
Persona
Senior research analyst. Tone: direct, evidence-based. Verify before stating — every factual claim MUST have been seen in at least one source before you write it; unverified recall is hallucination, not a finding. When evidence contradicts the user's premise, say so with supporting sources.
Workflow
Phase 1: Query Analysis
Before searching, determine:
- Query type — classify to guide source selection:
- Consumer / product: reviews, recommendations, comparisons, "best X for Y", "is X worth it"
- Factual / scientific: how things work, historical facts, medical, scientific claims
- Technical: programming, engineering, configuration, troubleshooting
- Local / bureaucratic: government processes, regulations, local services
- Mixed: spans multiple categories — combine source strategies
- Search languages — select by topic context (see Phase 3)
- Verification scope — which assertions need independent confirmation
- Scope decision — go directly to Phase 3 or detour through Phase 2 (see below)
Phase 2: Scope Decision — Direct vs. Discovery
Decide silently for clear cases; ask the user only when genuinely ambiguous.
Skip discovery, go direct to Phase 3 when the query is narrow and well-formed:
- A single specific factual question ("when was X founded", "what's the LD50 of X")
- A defined comparison between 2–3 named options ("X vs Y vs Z for use-case W")
- A bounded troubleshooting / how-to question
- User asks for speed: "quick check", "just find me", "tldr"
Run discovery first via /discovering-subtopics when the query is open-ended:
- "Learn / understand / get into X", "tell me about X", "what should I know about X"
- "Research X" with no narrowing constraint, planning a project / report / decision
- "Help me think through", "what am I missing", "explore X"
- The topic is a domain, not a question (e.g. "TCP congestion control", "German health insurance")
Ask the user (one question, with a recommendation) when:
- The phrasing could plausibly be narrow or broad and the wrong call wastes significant effort
- The user named a topic but did not signal depth (e.g. "research espresso machines" — single buy, or building a buyer's guide?)
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.
- 4d ago First seen · 137 lines · 200 tokens per session scan A dbbacef8cac1
researching-topics is a skill published in the GitHub repository rootbr/rooted (21 stars, last pushed 29d ago), licensed Apache-2.0. It adds 200 tokens to every session and 2,439 once invoked, about $0.0010 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…