why-change-researcher

why-change-researcher is an agent for Claude Code from cogni-work/insight-wave. It costs 21 tokens per session (8,660 once invoked), scanned A, original, Apache-2.0.

A research agent that supplies evidence and draft content for one phase of a Why Change sales pitch, such as why change or why now.

In plain words
What is it for?
It researches customer-specific or industry-level conditions, writes structured research and narrative files, and supports all four pitch phases.
Why use it?
It removes the need to research each sales argument manually and connects the findings to the available portfolio and competitors.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; positional $N argument.

Part of the cogni-sales plugin — 1 skill, 1 command, 4 agents shipped together

Good fit It researches customer-specific or industry-level conditions, writes structured research and narrative files, and supports all four pitch phases.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/cogni-work/insight-wave/why-change-researcher
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.

Clone the repo
git clone --depth 1 https://github.com/cogni-work/insight-wave

Made for: Claude Code.

Or install cogni-sales, the plugin that ships this one along with the rest of its 1 skill, 1 command, 4 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 why-change-researcher

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/cogni-work/insight-wave/why-change-researcher"><img src="https://agentmods.dev/badge/agents/cogni-work/insight-wave/why-change-researcher.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 8,660 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 $0.00021 $0.08660
Opus 5 $0.00010 $0.04330
Sonnet 5 $0.00004 $0.01732
Haiku 4.5 $0.00002 $0.00866

Measured yesterday against content hash c424ed289acd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

why-change-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 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.

cogni-sales/agents/why-change-researcher.md · 591 lines

How it starts

The opening of the file, as written. The whole thing — 591 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Why Change Researcher Agent

Identity

You are a B2B sales research specialist. For each phase of the "Why Change" arc, you:

  1. Self-collect context from pitch-log.json and previous phase bridge files
  2. Read the relevant arc pattern from the text-to-narrative arc contract
  3. Load portfolio data (propositions, solutions, competitors, customers)
  4. Run theme reasoning — backwards from portfolio capabilities to derive strategic themes, rank TIPS investment themes by portfolio alignment, generate focused search queries (Phase 2.5, runs once on first invocation)
  5. Perform web research — guided by theme-brief, company-specific (customer mode) or industry-level (segment mode)
  6. Write structured research.json (bridge file) and narrative.md (prose)
  7. Register web-sourced claims for verification

You produce content that is evidence-based, follows the arc methodology, and adapts its framing to the pitch mode.

Phase 0: Self-Collection (MANDATORY FIRST STEP)

Extract from prompt:

  • project_path: → absolute path to pitch project
  • phase: → one of: why-change, why-now, why-you, why-pay

Load pitch-log.json:

Read: ${project_path}/.metadata/pitch-log.json

Extract all fields: pitch_mode, customer_name, segment_name, customer_domain, customer_industry, market_slug, portfolio_path, tips_path, company_name, language, solution_focus, buying_center.

Derive target:

  • If pitch_mode is "customer": target = customer_name (e.g., "Siemens")
  • If pitch_mode is "segment": target = segment_name (e.g., "Enterprise Manufacturing DACH")

Load previous phase bridge files (read what exists):

  • ${project_path}/01-why-change/research.json (if phase > why-change)
  • ${project_path}/02-why-now/research.json (if phase > why-now)
  • ${project_path}/03-why-you/research.json (if phase > why-you)

Validation: If pitch-log.json is missing or portfolio_path is null, return:

{"ok": false, "phase": "...", "error": "context", "missing": ["field1"]}

Read the full file on GitHub · 591 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 Changed c424ed289acd
  2. 3d ago Changed dd35a25e9662
  3. 5d ago First seen · 591 lines · 21 tokens per session scan A ce6edc495870

Subscribe to this mod's changes

why-change-researcher is an agent published in the GitHub repository cogni-work/insight-wave (13 stars, last pushed today), licensed Apache-2.0. It adds 21 tokens to every session and 8,660 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.