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 dentiny/kon --skill external-researchgit clone --depth 1 https://github.com/dentiny/konWrote 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/dentiny/kon/external-research)<a href="https://agentmods.dev/skills/dentiny/kon/external-research"><img src="https://agentmods.dev/badge/skills/dentiny/kon/external-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/dentiny/kon/external-research"><img src="https://agentmods.dev/badge/skills/dentiny/kon/external-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 | $0.00048 | $0.00614 |
| Opus 5.5 | $0.00019 | $0.00246 |
| Sonnet 5.5 | $0.00010 | $0.00123 |
| Haiku 4.5 | $0.00005 | $0.00061 |
Grade A, and why
external-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 1mo 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
External Research
Owner: orchestrator
Consumers: /kon:research, /kon:team,
/kon:team, /kon:design
Core principles (always): follow skills/core-principles — cite sources; say "docs silent on X" instead of guessing; concise structured report only.
Azusa vs Jun
| Question type | Agent | Artifact |
|---|---|---|
| Where is X in our repo? How does our code work? | 🎸 Azusa | exploration notes (no file, or plan context) |
| What does library Y's API say? What's the migration path? | 📚 Jun | .kon/research.md |
| Compare our hook format to Cursor docs | Both (parallel) | research + exploration |
Rule: repo-first for "our code"; web-first for "their docs".
When to spawn Jun in /kon:team / /kon:design
Spawn Jun in parallel with Azusa when the task mentions any of:
- External API, SDK, SaaS, webhook, OAuth provider
- Library/framework version upgrade or migration
- "According to docs…", official spec, RFC, Cursor/Anthropic/OpenAI docs
- Error message clearly from a dependency (not our code)
- User explicitly asks to look something up
Skip Jun when:
- Pure internal refactor with no new external surface
.kon/research.mdalready exists for this topic and is still valid (orchestrator reads + confirms reuse)- User says codebase-only
/kon:research standalone
Read commands/research.md. Jun only — no Azusa/Mugi/Yui.
Use when the user asks a lookup question without intending to implement yet.
Handoff to Mugi
When both ran: Mugi reads .kon/research.md (if present) alongside Azusa's exploration
before writing the plan file (.kon/plan-<session-id>.md). Add a ## External context section in the plan summarizing
Jun's recommendations — do not paste raw URLs; link to .kon/research.md.
Orchestrator rules
- Spawn Jun via Task tool with
agents/Jun.md+ this skill - Jun may Write only
.kon/research.md - After Jun completes, run quality check with
teammate_role: Jun - Do not substitute web search yourself — Jun owns citations and
.kon/research.md
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.
- 1mo ago First seen · 58 lines · 48 tokens per session scan A f749e7b1991b
external-research is a skill published in the GitHub repository dentiny/kon (3 stars, last pushed 3mo ago), licensed MIT. It adds 48 tokens to every session and 614 once invoked, about $0.0002 per session on Opus 5.5. 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
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…