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/mpaarating/ai-workflow-kit/researchnpx skills add mpaarating/ai-workflow-kit --skill researchgit clone --depth 1 https://github.com/mpaarating/ai-workflow-kitWhat 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 | $0.00015 | $0.01314 |
| Opus 5 | $0.00008 | $0.00657 |
| Sonnet 5 | $0.00003 | $0.00263 |
| Haiku 4.5 | $0.00002 | $0.00131 |
Grade A, and why
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 2d 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research
Trigger Phrases
- "research [topic]"
- "deep dive on [topic]"
- "synthesize [topic]"
Inputs
The user provides a topic or question:
- A broad topic: "research React Server Components"
- A specific question: "research how other teams handle feature flag cleanup"
- A comparison: "research Zustand vs Jotai for our use case"
- A codebase question: "research how auth middleware works in this repo"
Workflow
Step 1: Clarify Scope
Assess the topic. If the request is clear and specific, proceed immediately. If ambiguous, ask one clarifying question — no more.
Good (proceed immediately):
- "research how to implement rate limiting in Express"
- "deep dive on React 19 cache API"
Needs clarification:
- "research databases" — too broad. Ask: "What aspect? Choosing one, optimizing queries, migration strategies?"
- "research the bug" — no context. Ask: "Which bug? Point me to a ticket or error message."
Step 2: Search Sources in Parallel
Search all available sources simultaneously. Use whichever sources are accessible:
Web Search
- Search for the topic using web search
- Look for: official documentation, well-regarded blog posts, conference talks, GitHub discussions
- Prefer primary sources (official docs, RFCs, author posts) over secondary summaries
- Skip SEO-farm results and outdated content (check publication dates)
Codebase Search
- Search the current repository for related code, patterns, and prior art
- Use filename search and content search
- Look for: existing implementations, similar patterns, comments referencing the topic, related tests
- If the repo is part of a monorepo or org, note whether broader search might be useful
Docs Search
- Search
{{notes}}for internal documentation, decision records, or previous research on the topic - Look for: ADRs, RFCs, design docs, wiki pages, previous research briefs
Step 3: Evaluate and Filter Sources
For each source found:
- Assess relevance (directly addresses the topic vs. tangentially related)
- Assess credibility (official docs > well-known authors > random blog posts)
- Assess freshness (recent > old, especially for fast-moving topics)
- Discard sources that are low-relevance, outdated, or unreliable
- Keep the top 5-10 most valuable sources
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.
- 2d ago First seen · 136 lines · 15 tokens per session scan A 39c131a9eb27
research is a skill published in the GitHub repository mpaarating/ai-workflow-kit (2 stars, last pushed 3mo ago), licensed MIT. It adds 15 tokens to every session and 1,314 once invoked, about $0.0001 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
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.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
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.