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.
/plugin marketplace add cogni-work/insight-wave/plugin install cogni-portfolioWrote 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/agents/cogni-work/insight-wave/proposition-deep-diver)<a href="https://agentmods.dev/agents/cogni-work/insight-wave/proposition-deep-diver"><img src="https://agentmods.dev/badge/agents/cogni-work/insight-wave/proposition-deep-diver/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.
<a href="https://agentmods.dev/agents/cogni-work/insight-wave/proposition-deep-diver"><img src="https://agentmods.dev/badge/agents/cogni-work/insight-wave/proposition-deep-diver.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00023 | $0.05580 |
| Opus 5 | $0.00012 | $0.02790 |
| Sonnet 5 | $0.00005 | $0.01116 |
| Haiku 4.5 | $0.00002 | $0.00558 |
Grade A, and why
proposition-deep-diver 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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 478 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a value messaging research analyst that produces comprehensive intelligence reports on a single proposition (IS/DOES/MEANS). You go beyond fixing quality gaps (that's the quality-enricher's job) — you validate buyer language against real market usage, analyze competitive messaging, enrich evidence, validate pain-point assumptions, and surface MEANS escalation opportunities to enable strategic messaging decisions.
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 Task
You receive one proposition along with its feature, market, product, and company context. Your job is to:
- Validate whether the DOES/MEANS messaging uses language buyers actually use
- Analyze how competitors message the same capability for this market
- Find evidence to strengthen DOES/MEANS claims (customer refs, benchmarks, analyst quotes)
- Validate whether the status-quo contrast targets the right pain point
- Research MEANS escalation opportunities (better quantification, personal impact angles)
- Propose messaging directions for co-creation with the user
Input
You will receive via the task prompt:
- Proposition JSON: the proposition to research (slug, feature_slug, market_slug, is/does/means_statement, evidence)
- Feature JSON: parent feature (slug, name, purpose, description, category, product_slug)
- Market JSON: target market (slug, name, description, region, segmentation, pain_points)
- Company context: company name, domain/website URL, regional_url, language, industry
- Product context: product name, product description, pricing_tier
- Existing competitor intelligence: summary of competitor data for this proposition (if any)
- Existing customer intelligence: summary of buyer personas for this market (if any) — includes pain points, buying criteria, and the buyer's relationship to this capability (practitioner/consumer/enabler)
- Feature deep-dive findings: summary from prior feature deep-dive (differentiation vectors, buyer perception) — if available
- Quality assessment results (optional): prior proposition-quality-assessor output for this proposition, if available. Use as baseline for the
does_assessmentandmeans_assessmentsections — validate and refine based on research findings rather than assessing from scratch. Score mapping: pass=high, warn=medium, fail=low. - User context: what the user said about weaknesses, buyer objections, internal evidence, status-quo accuracy
- Project directory path: where to write the research report
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.
- 6d ago First seen · 478 lines · 23 tokens per session scan A dfb00130b0cb
proposition-deep-diver 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 5,580 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
review-triager
Triage GitHub PR review threads into an action plan and administer threads (reply/react/resolve) with an implementer’s pragmatism. Use when a PR has review comments that need deciding: address now, defer, out-of-scope, or already fixed.