Borrowing it
Nothing to install: this file belongs to deandevz/king-context. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/deandevz/king-context/main/.agents/skills/king-research/SKILL.mdgit clone --depth 1 https://github.com/deandevz/king-contextWrote 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/deandevz/king-context/king-research)<a href="https://agentmods.dev/skills/deandevz/king-context/king-research"><img src="https://agentmods.dev/badge/skills/deandevz/king-context/king-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/deandevz/king-context/king-research"><img src="https://agentmods.dev/badge/skills/deandevz/king-context/king-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 | $0.00124 | $0.01697 |
| Opus 5.5 | $0.00050 | $0.00679 |
| Sonnet 5.5 | $0.00025 | $0.00339 |
| Haiku 4.5 | $0.00012 | $0.00170 |
Grade A, and why
king-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 2mo 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 — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
King Research — Topic Research Skill
Invoke king-research to build a research corpus on any topic. The user describes what they want; you extract the topic, pick the effort mode, and run the pipeline.
When to use this skill
| User wants... | Use |
|---|---|
| Sources on an open-web topic (papers, blog posts, discussions) | king-research (this skill) |
| A specific product/API doc site scraped | scraper-workflow (king-scrape) |
| To query already-indexed content | king-context (kctx search) |
If the user already mentions a URL or a specific product's docs, hand off to scraper-workflow.
Step 1: Extract the topic
Pull the topic from the user's message as a concise phrase (2–6 words).
Rules:
- Strip filler: "please", "por favor", "pode fazer", "quero que", "me faça".
- Keep semantic qualifiers: "for RAG pipelines", "in production", "2025".
- Prefer the user's wording over paraphrase.
- Quote multi-word topics when passing to the CLI.
If the topic is vague (e.g. "faz um research aí", "pesquise algo"), ask ONE clarifying question before running: "What topic?"
Step 2: Pick the effort mode
Explicit signals (override inference)
| Signal in the user's message | Mode |
|---|---|
| "rápido", "quick", "basic", "só uma ideia", "overview", "simples" | --basic |
| (no qualifier) | --medium (default) |
| "detalhado", "aprofundado", "profundo", "detailed", "in-depth", "completo" | --high |
| "exaustivo", "estado da arte", "thorough", "comprehensive", "state of the art", "máximo", "tudo que tiver" | --extrahigh |
Inferred from complexity (when no explicit signal)
| Topic shape | Mode |
|---|---|
| Narrow, well-known (e.g. "httpx timeouts") | --basic |
| Standard technical topic (e.g. "prompt caching strategies") | --medium (default) |
| Broad or comparative (e.g. "RAG vs fine-tuning") | --high |
| Bleeding-edge / multi-domain survey (e.g. "mixture of experts state of the art 2025") | --extrahigh |
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.
- 2mo ago First seen · 168 lines · 124 tokens per session scan A cc6d11efcbf2
king-research is a skill published in the GitHub repository deandevz/king-context (56 stars, last pushed 5mo ago), licensed MIT. It adds 124 tokens to every session and 1,697 once invoked, about $0.0005 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 2026-08-30.
king-research compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| king-researchdeandevz/king-context | Skill | 56 | 5mo ago | MIT | A | 124 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 103 | Claude Code |