A research workflow for finding, checking, comparing, and combining information from multiple sources.

It helps with reports, fact-checking, technical research, comparisons, literature reviews, monitoring changes, plan testing, and due diligence.

It removes the need to handle complex research and source cross-checking as an unstructured task.

infobroker — Skill for Claude Code and Codex by flukeatzerocool

Install

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.

Any agent

npx skills add flukeatzerocool/infobroker --skill infobroker

Clone the repo

git clone --depth 1 https://github.com/flukeatzerocool/infobroker

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/flukeatzerocool/infobroker/infobroker/github.svg)](https://agentmods.dev/skills/flukeatzerocool/infobroker/infobroker)

Your own site

<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.

Your own site · 80×15

<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>

Per session 134 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,535 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.02535
Opus 5.5	$0.00054	$0.01014
Sonnet 5.5	$0.00027	$0.00507
Haiku 4.5	$0.00013	$0.00253

Measured 9d ago against content hash 40ba7d5dfb93, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 9d 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.

skills/infobroker/SKILL.md · 205 lines

How it starts

The opening of the file, as written. The whole thing — 205 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_web directly
Purely conversational questions with no research component
Tasks that require only the AI's internal knowledge, no web lookup

The writing pipeline runs only in a client that loads bundled skills. In a client without skill loading, Infobroker tools still retrieve and verify evidence, but no report manifest, validator, or writing pipeline runs; say so rather than claiming a finished report.

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. references/glossary.md defines the shared terminology these references use.

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`)

Read the full file on GitHub · 205 lines

Files

What ships with it

14 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.

Changes

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.

9d ago Changed · +32 lines 40ba7d5dfb93
16d ago Changed · +2 lines d172dd29e078
1mo ago Changed · +2 lines 6730e695338c
2mo ago Changed · +8 lines c909daab0e86
2mo ago Changed 111f567c9f79
2mo ago First seen · 161 lines · 134 tokens per session scan A 7f26b00b8c94

Subscribe to this mod's changes

infobroker is a skill published in the GitHub repository flukeatzerocool/infobroker (1 stars, last pushed 2d ago), licensed MIT. It adds 134 tokens to every session and 2,535 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 2026-08-31.

Research

infobroker next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
infobrokerflukeatzerocool/infobroker	Skill	1	2d ago	MIT	A	134	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	yesterday	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	103	Claude Code