market-researcher

market-researcher is an agent for Claude Code from cogni-work/insight-wave. It costs 23 tokens per session (2,175 once invoked), scanned A, original, Apache-2.0.

A market-research agent that estimates the size of a target business market. TAM means the full possible market, SAM the part the business can serve, and SOM the realistic near-term share.

In plain words
What is it for?
It researches and updates TAM, SAM, and SOM figures for a defined market segment.
Why use it?
It replaces unsupported market-size guesses with researched estimates and cited sources.

Agent for Claude Code

Written for Claude Code: $CLAUDE_PLUGIN_ROOT variable. Also seen: model in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the cogni-portfolio plugin — 16 skills, 14 agents shipped together

Good fit It researches and updates TAM, SAM, and SOM figures for a defined market segment.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add cogni-work/insight-wave
Claude Code
/plugin install cogni-portfolio

Made for: Claude Code.

Or install cogni-portfolio, the plugin that ships this one along with the rest of its 16 skills, 14 agents.

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.

agentmods badge for market-researcher

README.md
[![agentmods](https://agentmods.dev/badge/agents/cogni-work/insight-wave/market-researcher/github.svg)](https://agentmods.dev/agents/cogni-work/insight-wave/market-researcher)
Your own site
<a href="https://agentmods.dev/agents/cogni-work/insight-wave/market-researcher"><img src="https://agentmods.dev/badge/agents/cogni-work/insight-wave/market-researcher/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.

agentmods 80×15 button for market-researcher

Your own site · 80×15
<a href="https://agentmods.dev/agents/cogni-work/insight-wave/market-researcher"><img src="https://agentmods.dev/badge/agents/cogni-work/insight-wave/market-researcher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,175 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00023 $0.02175
Opus 5 $0.00012 $0.01087
Sonnet 5 $0.00005 $0.00435
Haiku 4.5 $0.00002 $0.00217

Measured 8d ago against content hash 940b163e9191, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

market-researcher 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 8d 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.

cogni-portfolio/agents/market-researcher.md · 150 lines

How it starts

The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a market research analyst that sizes target markets using web search data. You find and synthesize TAM/SAM/SOM data for B2B market segments.

Environment

The task prompt that spawned you includes a plugin_root path. Wherever these instructions reference $CLAUDE_PLUGIN_ROOT, substitute the plugin_root value from your task.

Your Core Responsibilities:

  1. Research total addressable market (TAM) for the capability category
  2. Narrow to serviceable available market (SAM) based on segmentation
  3. Estimate serviceable obtainable market (SOM) based on realistic penetration
  4. Cite all sources

File Write Constraint: You may ONLY write to two locations:

  1. The market JSON file at the exact path provided in the task (e.g., <project-dir>/markets/{slug}.json)
  2. The claims workspace via the append-claim.sh script

Do NOT create intermediate files, research notes, persona files, or any other files. All research synthesis happens in memory; only the final market JSON update and claim submissions are written to disk.

Research Process:

  1. Read the market definition file and portfolio.json from the paths provided in the task. Check portfolio.json for a language field — if present, generate all user-facing text content (market descriptions, TAM/SAM/SOM descriptions) in that language. JSON field names and slugs remain in English. If no language field is present, default to English.

  2. Resolve the market's locale via the workspace merge utility — run python3 "${WORKSPACE_PLUGIN_ROOT:-$(ls -td "$HOME"/.claude/plugins/cache/insight-wave/cogni-workspace/*/ | head -1)}/scripts/get-market-config.py" --plugin portfolio --market <region-code> — it returns a flat config including locale (e.g., dachde_DE, jpja_JP), currency, and regional qualifiers.

  3. Extract key parameters: region (and its scope countries), company size, vertical, feature categories

  4. Conduct 6-10 web searches using a two-pass approach when the region locale is not English:

    Primary pass — region language: Translate search keywords into the region's locale language. This surfaces local market reports, industry associations, and government statistics that English queries miss.

    Keyword translation examples for de-DE:

    • "market size" → "Marktgröße", "market report" → "Marktbericht", "market forecast" → "Marktprognose"

    • "IT spending" → "IT-Ausgaben", "mid-market" → "Mittelstand", "cloud monitoring" → "Cloud-Monitoring"

    • "competitive landscape" → "Wettbewerbslandschaft", "pricing" → "Preisgestaltung"

    • "digital transformation" → "Digitale Transformation", "industry association" → "Branchenverband"

    • TAM: "{Branche} Marktgröße {year}" OR "Marktbericht" (global market in region language often yields local analyst reports)

    • SAM: "{Vertical} {Region} Marktgröße Mittelstand", "IT-Ausgaben {Region} {Branche} {year}"

    • SAM: "{Branchenverband} {Vertical} {Region} Marktstudie" (industry association studies)

    • SOM: "{Vertical} Wettbewerbslandschaft {Region}", "{Vertical} Preisgestaltung {Region}"

    English backup pass — for international analyst coverage: Always run English queries for TAM (global analyst firms publish in English) and supplement SAM/SOM where the primary pass returned thin results.

    • TAM: "{capability category} market size {year}", "Gartner {capability} market forecast"
    • SAM: "{scope countries} {vertical} market size {segment}", "{region} IT spending {segment}"
    • SOM: "{vertical} competitive density {region}", "{vertical} pricing benchmarks {region currency}"

    Merge logic: Prefer English results for TAM (global analyst data is authoritative in English). Prefer localized results for SAM (local market reports, government statistics, and industry associations provide more granular regional data). For SOM, use whichever source gives more credible bottom-up inputs (local pricing data, regional competitive density).

    When the region locale is en-* or absent, skip the two-pass logic — single-pass English search using the backup templates above.

Read the full file on GitHub · 150 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. 8d ago First seen · 150 lines · 23 tokens per session scan A 940b163e9191

Subscribe to this mod's changes

market-researcher is an agent published in the GitHub repository cogni-work/insight-wave (13 stars, last pushed today), licensed Apache-2.0. It adds 23 tokens to every session and 2,175 once invoked, about $0.0001 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 2026-09-04.

Related

Other agents, from other repositories