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 flukeatzerocool/infobroker --skill infobrokergit clone --depth 1 https://github.com/flukeatzerocool/infobrokerWrote 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/flukeatzerocool/infobroker/infobroker)<a href="https://agentmods.dev/skills/flukeatzerocool/infobroker/infobroker"><img src="https://agentmods.dev/badge/skills/flukeatzerocool/infobroker/infobroker/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/flukeatzerocool/infobroker/infobroker"><img src="https://agentmods.dev/badge/skills/flukeatzerocool/infobroker/infobroker.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 | $0.00134 | $0.01932 |
| Opus 5 | $0.00067 | $0.00966 |
| Sonnet 5 | $0.00027 | $0.00386 |
| Haiku 4.5 | $0.00013 | $0.00193 |
Grade A, and why
infobroker 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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Infobroker — Research & Writing Professional
When to Use
- User asks to research a topic and produce a written report, article, or analysis
- User asks to fact-check claims with web sources and cross-reference
- User asks to find and synthesize information from multiple sources
- User asks to verify technical claims with authoritative sources
- User asks to find code solutions or evaluate technical answers from the web
- User asks to compare or evaluate options, tools, vendors, or approaches
- User asks for a literature review, state-of-the-art survey, or related work
- User asks to monitor, track, or watch a topic and report what changed
- User asks to red-team or stress-test a plan, product, or conclusion
- User asks to vet or run due diligence on a person, organization, or product
- User asks to translate findings or produce multilingual output
- User asks a complex question that benefits from multi-provider web search
When NOT to Use
- Simple factual lookup (single Wikipedia visit) — use
search_webdirectly - Purely conversational questions with no research component
- Tasks that require only the AI's internal knowledge, no web lookup
Phase 0: Classify
Map the request to one workflow shape before any search. Consult
references/workflows.md for the full definition of the chosen shape and
references/decision-tree.md for the ordered disambiguation questions, the
tool-selection conditions, and the escalation rubric.
| Intent marker | Workflow shape |
|---|---|
| "research/write a report/article", general | Research & Write |
| "fact-check / verify / is it true" | Fact-Check |
| "deep dive / comprehensive / thesis" | Deep-Dive |
| "compare / evaluate / which is best / X vs Y" | Competitive Evaluation |
| "literature review / state of the art / related work" | Literature Review |
| "what changed / monitor / track / brief me since" | Monitoring / Delta |
| "red-team / stress-test / what could go wrong" | Adversarial / Red-Team |
| "vet / background check / due diligence / is it legit" | Vetting |
| high-stakes, decision-driving, needs rigor | Gated Analysis (escalate to analysis-loop) |
What ships with it
12 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.
- references/config-tune.md 4.1 KB
- references/corroboration.md 3.2 KB
- references/decision-tree.md 5.5 KB
- references/glossary.md 2.8 KB
- references/journeys.md 3.3 KB
- references/pipeline-map.md 2.9 KB
- references/provider-auth.md 1.4 KB
- references/provider-map.md 3.2 KB
- references/report-template.md 2.7 KB
- references/skill-authoring.md 2.4 KB
- references/troubleshooting.md 3.6 KB
- references/workflows.md 7.2 KB
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 Changed · +8 lines c909daab0e86
- 5d ago Changed 111f567c9f79
- 8d ago First seen · 161 lines · 134 tokens per session scan A 7f26b00b8c94
infobroker is a skill published in the GitHub repository flukeatzerocool/infobroker (0 stars, last pushed 3d ago), licensed MIT. It adds 134 tokens to every session and 1,932 once invoked, about $0.0007 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…
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…