group

A market-grouping agent sorts a company's established products into capability groups based on the jobs they help customers do and the competitors they would face.

In plain words
What is it for?
Organising researched products into market categories and naming each category in terms buyers would recognise.
Why use it?
It prevents a product list from being mistaken for a clear map of the markets the company serves.

Agent

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.

agentmods
npx agentmods add agents/mo-root/open-kb/group
Clone the repo
git clone --depth 1 https://github.com/mo-root/open-kb
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 499 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00499
Opus 5 $0.00000 $0.00249
Sonnet 5 $0.00000 $0.00100
Haiku 4.5 $0.00000 $0.00050

Measured yesterday against content hash b17926a0f241, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

group 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 yesterday.

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.

prompts/agents/group.md · 45 lines

How it starts

The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.

An investigation of {{anchor}}'s own site just finished. It read the pages itself and submitted every product it could establish; the list below is what it found, each line naming the page that establishes it. Your job is the judgement that list does not carry: group the products into the markets they actually sit in.

the company sells   {{sells}}
to                  {{buyer}}

The products the investigation established

{{products}}

Group them into capabilities

A company's product list is a sales artifact. It splits one job into several SKUs because that is how it prices, and it bundles several jobs into one SKU because that is how it packages. Neither split tracks where its competitors live, and competitors are the thing being mapped. So the grouping test is exactly one question: would these have different competitors?

Two SKUs a buyer chooses between inside a single purchase are ONE capability. Two things bought by different teams for different reasons are TWO, however similar the words look. Give each capability a name in the market's words — no brand, no product name, nothing a buyer would have to already know this company to type — and say plainly what job it does.

Mark each capability core or adjacent. Core is what buyers come to this company for. Adjacent is a side line, an integration or an add-on they would not switch vendor over. Be strict: most companies have one to three core capabilities and everything else is adjacent.

This grouping is what the run's search budget is divided across, so it decides what gets mapped. Too coarse and distinct markets get merged and never searched for; too fine and one market takes several shares of the budget while another takes none. And an adjacent line marked core is worse than either: a transactional email company that listed an AI-protocol integration alongside its email API spent a third of a small budget on the integration and got back eight pages about AI protocols and nothing about email.

Read the full file on GitHub · 45 lines

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.

  1. yesterday First seen · 45 lines · 0 tokens per session scan A b17926a0f241

Subscribe to this mod's changes

group is an agent published in the GitHub repository mo-root/open-kb (11 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 499 tokens. 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.

Related

Other agents, from other repositories

research-orchestrator

Orchestrator agent for sigint research sessions. Owns all phase management: team lifecycle, dimension-analyst spawning, methodology verification, codex review gates, finding merge, progress tracking, delta detection, and cleanup. Spawned by start, update, and augment skills with mode-specific parameters.

zircote-plugins/sigint · 66 tokens

report-synthesizer

Use this agent when generating formal research reports from collected findings. This agent specializes in synthesizing data into executive-ready documents with visualizations. Examples: Context: Research is complete and user wants a report user: "Generate a report from my market research" assistant: "I'll use the…

zircote-plugins/sigint · 331 tokens

dimension-analyst

Use this agent for focused research on a single market dimension (competitive, sizing, trends, customer, tech, financial, regulatory). Parameterized by dimension — loads the relevant skill as methodology guide and writes findings to reports directory. Examples: Context: Orchestrator spawning parallel analysts user…

zircote-plugins/sigint · 187 tokens

issue-architect

Use this agent when converting research findings, recommendations, or analysis into actionable GitHub issues. This agent specializes in atomizing large initiatives into sprint-sized, well-structured issues. Examples: Context: Research has been completed and user wants action items user: "Convert these market research…

zircote-plugins/sigint · 350 tokens

falsification-analyst

Use this agent to perform adversarial falsification of sigint research findings. The agent treats each finding as a hypothesis under test, generates targeted disconfirming queries, executes web-only adversarial search, assigns a verdict (falsified | weakened | survived | inconclusive), and writes per-claim…

zircote-plugins/sigint · 263 tokens

source-chunker

Use this agent to process large documents that exceed context limits. Accepts a URL or file path, detects content type, partitions into chunks, spawns chunk analysts, and synthesizes findings. Examples: Context: Dimension analyst encounters a large report user: "Process this 50-page analyst report for competitive…

zircote-plugins/sigint · 187 tokens