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 agentmods add commands/cogni-work/insight-wave/why-changegit clone --depth 1 https://github.com/cogni-work/insight-waveWrote 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/commands/cogni-work/insight-wave/why-change)<a href="https://agentmods.dev/commands/cogni-work/insight-wave/why-change"><img src="https://agentmods.dev/badge/commands/cogni-work/insight-wave/why-change.svg" alt="Measured on agentmods" 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 | $0.00016 | $0.00482 |
| Opus 5 | $0.00008 | $0.00241 |
| Sonnet 5 | $0.00003 | $0.00096 |
| Haiku 4.5 | $0.00002 | $0.00048 |
Grade A, and why
why-change 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 today.
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.
What it actually says
/why-change
Create or resume a Why Change sales pitch. Supports named-customer pitches (deal-specific) and segment pitches (reusable for a market).
Usage
/why-change # Start new pitch or discover existing
/why-change --project-path <path> # Resume specific pitch project
Behavior
New pitch: If no --project-path is provided:
- Discover existing pitch projects via
pitch-status.sh - If incomplete projects found: ask user to resume or start new
- If no projects: invoke the
why-changeskill to start fresh - The skill will ask whether this is a named-customer or segment pitch
Resume pitch: If --project-path is provided:
- Read pitch-log.json for current state and pitch mode
- Resume from the last incomplete phase
Examples
/why-change
> "Starting new pitch. Are you creating a pitch for a named customer or a reusable segment pitch?"
/why-change --project-path ./siemens-pitch
> "Resuming Siemens pitch (customer mode) — Phase 2 (Why Now) is next."
/why-change --project-path ./enterprise-manufacturing-dach-segment-pitch
> "Resuming Enterprise Manufacturing DACH segment pitch — Phase 3 (Why You) is next."
Implementation
Invoke the cogni-sales:why-change skill:
Skill tool: cogni-sales:why-change
Args: {provided arguments}
If --project-path is provided, pass it through. Otherwise, first scan for existing projects:
# Find pitch projects in workspace
for dir in */; do
if [ -f "${dir}.metadata/pitch-log.json" ]; then
"${CLAUDE_PLUGIN_ROOT}/scripts/pitch-status.sh" "$dir"
fi
done
Present discovered projects to user (showing mode: customer or segment), then invoke the skill.
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.
- today First seen · 67 lines · 16 tokens per session scan A 1b24193d214e
why-change is a command published in the GitHub repository cogni-work/insight-wave (12 stars, last pushed today), licensed Apache-2.0. It adds 16 tokens to every session and 482 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.
Other commands, from other repositories
gtm:enrich
Run waterfall enrichment on a list — email, phone, people, or company data.
gtm:clone-campaign
Clone a successful campaign for a new segment or market.
gtm:deep-dive
Data deep-dive — analyze CRM, campaigns, and transcripts to build ICP from evidence.
gtm:onboard
Onboard a new workspace with structured intake interview.
gtm:ship
Ship approved list and sequence to the sending tool.
gtm:ab-test
Set up, track, or resolve an A/B test.