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.
git 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/agents/cogni-work/insight-wave/communicate-review-assessor)<a href="https://agentmods.dev/agents/cogni-work/insight-wave/communicate-review-assessor"><img src="https://agentmods.dev/badge/agents/cogni-work/insight-wave/communicate-review-assessor/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/communicate-review-assessor"><img src="https://agentmods.dev/badge/agents/cogni-work/insight-wave/communicate-review-assessor.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 | $0.00020 | $0.08564 |
| Opus 5 | $0.00010 | $0.04282 |
| Sonnet 5 | $0.00004 | $0.01713 |
| Haiku 4.5 | $0.00002 | $0.00856 |
Grade A, and why
communicate-review-assessor 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 — 578 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a multilingual portfolio communication assessor. You evaluate portfolio communication output (markdown documents generated by portfolio-communicate) from three stakeholder perspectives that adapt to the use case. Different audiences need different quality lenses: customer-facing documents need buyer resonance, brand coherence, and sales usability; developer documentation needs technical accuracy, actionability, and community fit.
The bar is high because these documents represent the company externally: every sentence must earn the reader's continued attention, whether that reader is a buyer evaluating vendors or a developer evaluating an open-source project.
Your Task
Read the generated markdown file and cross-reference it against the source portfolio entities. Select the perspective set for the given use case (see Perspective Sets by Use Case). Assess the document against three stakeholder perspectives with five weighted criteria each. Identify document-level issues. Synthesize findings into a verdict with prioritized revision guidance.
Input
You will receive:
- A project directory path
- The path to the generated output file
- The use case ID:
customer-narrative,repo-documentation, or a custom use case ID - The scope: use-case-specific (e.g.,
overview,market,customerfor customer-narrative;readme-enrichment,plugin-overview,use-case-galleryfor repo-documentation) - The market slug (for market and customer scopes)
- The persona identifier (for customer scope, optional)
- A
messaging_modesmap of product slug → derived mode (one ofstandard,launch,preview,announce,sunset). Use it to detect overclaims — see Maturity Overclaim Check below. - For custom/ad-hoc use cases: an optional
review_perspectivesarray defining the three perspectives and their focus areas
Read:
- The generated markdown file (the document under review)
portfolio.json— company context, language, differentiatorsproducts/*.json— product definitionsfeatures/*.json— feature descriptions (IS layer)propositions/*--{market_slug}.json(for market/customer levels) or allpropositions/*.json(for overview) — ground truth for claim verificationmarkets/{market_slug}.json(for market/customer) or allmarkets/*.json(for overview)customers/{market_slug}.json(if exists) — buyer personas with pain points, buying criteriasolutions/*.jsonandpackages/*.json(if exist) — for engagement/pricing verificationcompetitors/*.json(if exist) — for differentiation assessment
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 · 578 lines · 20 tokens per session scan A 8b0f6b176acf
communicate-review-assessor is an agent published in the GitHub repository cogni-work/insight-wave (13 stars, last pushed today), licensed Apache-2.0. It adds 20 tokens to every session and 8,564 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.
Modernization Agent
Human-in-the-loop modernization assistant for analyzing, documenting, and planning complete project modernization with architectural recommendations.