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/krishagel/geoffrey/researchnpx skills add krishagel/geoffrey --skill researchgit clone --depth 1 https://github.com/krishagel/geoffreyWrote 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/krishagel/geoffrey/research)<a href="https://agentmods.dev/skills/krishagel/geoffrey/research"><img src="https://agentmods.dev/badge/skills/krishagel/geoffrey/research.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 | $0.00013 | $0.02605 |
| Opus 5 | $0.00006 | $0.01303 |
| Sonnet 5 | $0.00003 | $0.00521 |
| Haiku 4.5 | $0.00001 | $0.00261 |
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 5d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- research — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 365 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Skill
Discovery-driven, exhaustive research using parallel LLM agents for comprehensive, current information gathering.
Core Principles
CRITICAL: These principles define how research works.
1. Discovery-Driven, Not List-Driven
- Find the BEST sources, not just known sources
- Don't limit to predefined source lists
- The internet is huge - explore it
- Value is in finding what user doesn't already know
2. Context-Aware
- Load user's domain context from preferences
- Research is RELEVANT to their specific situation
- But context doesn't limit WHERE you search
3. Exhaustive
- No time limits - can take 30 minutes to 3 hours
- Don't stop at first page of results
- Keep going until topic is exhausted
- Follow promising links deeper
4. Multimedia
- Not just text articles
- Videos (YouTube), TikTok, podcasts
- Real user experiences from forums
5. Highly Cited
- Every claim must have a citation
- Multiple sources for important claims
- Note when sources conflict
6. Clarifying Questions First
Before diving into research, ask deep, thought-provoking questions to understand:
- What's the actual goal? (not just the surface request)
- What constraints exist? (budget, time, preferences)
- What would success look like?
- What have they already tried or considered?
- Are there hidden requirements?
Example: "Research Japan ski trip" should prompt:
- "What skill level are you and Carrie? Blue runs, black diamonds?"
- "Is après-ski culture important, or pure skiing focus?"
- "Do you need English-friendly areas, or comfortable with Japanese-only?"
- "Any specific dates that are fixed vs flexible?"
- "Besides skiing, anything else you want to do (onsen, food tours)?"
Domain Context Loading
Research automatically loads relevant context from preferences based on detected domain.
How It Works
- Detect domain from query (travel, shopping, work, etc.)
- Load
research_domains.[domain]from preferences - Load referenced context keys
- Fetch any dynamic data (point balances, etc.)
- Apply domain-specific research patterns
What ships with it
8 files 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.
- 5d ago First seen · 365 lines · 13 tokens per session scan A 6419fbbeabcc
research is a skill published in the GitHub repository krishagel/geoffrey (5 stars, last pushed 5mo ago), licensed MIT. It adds 13 tokens to every session and 2,605 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.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…