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/moberghr/mtk-agent-toolkit/research-contextnpx skills add moberghr/mtk-agent-toolkit --skill research-contextgit clone --depth 1 https://github.com/moberghr/mtk-agent-toolkitWrote 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/moberghr/mtk-agent-toolkit/research-context)<a href="https://agentmods.dev/skills/moberghr/mtk-agent-toolkit/research-context"><img src="https://agentmods.dev/badge/skills/moberghr/mtk-agent-toolkit/research-context.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 5.1 | $0.00040 | $0.02524 |
| Opus 5 | $0.00020 | $0.01262 |
| Sonnet 5 | $0.00008 | $0.00505 |
| Haiku 4.5 | $0.00004 | $0.00252 |
Grade A, and why
research-context 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 6d 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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Context
Overview
source-driven-development answers "does this known API behave the way I think?" by checking authoritative docs for one call. research-context answers the broader, forward-looking question: "given what this repo already does, what is the current best way to do X?" — pulling fresh external information (release notes, current best-practices, migration paths, security advisories) and grounding it against named files in this repo so the answer fits the codebase, not a generic tutorial.
It is the MTK analog of Taskmaster's research mode: research is a first-class workflow primitive, not an ad-hoc web search. Its output is a small, cited brief that downstream skills consume — spec-driven-development (version-sensitive ambiguity gate, step 6) and implement (Phase 3, version-sensitive choices) — so spec and implementation decisions ride on current information rather than training-cutoff memory.
This skill does not edit code. It produces a brief; another skill acts on it.
Tool discipline (phase-locked): research is a read + web-fetch phase — use
Read/Grep/Globand the web tools only. Do notEdit/Writesource or test code; the only artifact it may write is its own brief. (It is not locked to theread-onlytoolset because it legitimately needsWebSearch/WebFetch, which that toolset excludes.) Model tier: runs onsonnet(synthesis of external sources into a cited brief) per.claude/references/model-routing.md.
When To Use
- A spec or plan hinges on a version-sensitive choice (which API/pattern is current in the installed package version, not the one from memory).
- Choosing between competing libraries/approaches where the landscape moved recently.
- A dependency upgrade or framework migration where the migration path matters.
- A security-sensitive decision where current advisories or deprecations could change the answer.
- The engineer literally asks to "research X" before building.
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.
- 6d ago First seen · 167 lines · 40 tokens per session scan A bb271895671a
research-context is a skill published in the GitHub repository moberghr/mtk-agent-toolkit (7 stars, last pushed yesterday), licensed MIT. It adds 40 tokens to every session and 2,524 once invoked, about $0.0002 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…
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…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…