communicate-review-assessor

communicate-review-assessor is an agent for Claude Code from cogni-work/insight-wave. It costs 20 tokens per session (8,564 once invoked), scanned A, original, Apache-2.0.

An assessment agent that reviews portfolio communication from three stakeholder viewpoints suited to the document's use case. It checks qualities such as buyer resonance, brand consistency, technical accuracy, and practical usefulness.

In plain words
What is it for?
Use it to assess generated Markdown communication documents and receive prioritized revision guidance.
Why use it?
It identifies document-level problems that may make customer or developer content unclear, inaccurate, or difficult to use. It also compares the output with the source portfolio data.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

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

Good fit Use it to assess generated Markdown communication documents and receive prioritized revision guidance.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/cogni-work/insight-wave/communicate-review-assessor
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-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 communicate-review-assessor

README.md
[![agentmods](https://agentmods.dev/badge/agents/cogni-work/insight-wave/communicate-review-assessor/github.svg)](https://agentmods.dev/agents/cogni-work/insight-wave/communicate-review-assessor)
Your own site
<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.

agentmods 80×15 button for communicate-review-assessor

Your own site · 80×15
<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>
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 8,564 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 $0.00020 $0.08564
Opus 5 $0.00010 $0.04282
Sonnet 5 $0.00004 $0.01713
Haiku 4.5 $0.00002 $0.00856

Measured 6d ago against content hash 8b0f6b176acf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

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.

cogni-portfolio/agents/communicate-review-assessor.md · 578 lines

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, customer for customer-narrative; readme-enrichment, plugin-overview, use-case-gallery for repo-documentation)
  • The market slug (for market and customer scopes)
  • The persona identifier (for customer scope, optional)
  • A messaging_modes map of product slug → derived mode (one of standard, launch, preview, announce, sunset). Use it to detect overclaims — see Maturity Overclaim Check below.
  • For custom/ad-hoc use cases: an optional review_perspectives array defining the three perspectives and their focus areas

Read:

  • The generated markdown file (the document under review)
  • portfolio.json — company context, language, differentiators
  • products/*.json — product definitions
  • features/*.json — feature descriptions (IS layer)
  • propositions/*--{market_slug}.json (for market/customer levels) or all propositions/*.json (for overview) — ground truth for claim verification
  • markets/{market_slug}.json (for market/customer) or all markets/*.json (for overview)
  • customers/{market_slug}.json (if exists) — buyer personas with pain points, buying criteria
  • solutions/*.json and packages/*.json (if exist) — for engagement/pricing verification
  • competitors/*.json (if exist) — for differentiation assessment

Read the full file on GitHub · 578 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. 6d ago First seen · 578 lines · 20 tokens per session scan A 8b0f6b176acf

Subscribe to this mod's changes

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.