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/customer-review-assessor)<a href="https://agentmods.dev/agents/cogni-work/insight-wave/customer-review-assessor"><img src="https://agentmods.dev/badge/agents/cogni-work/insight-wave/customer-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/customer-review-assessor"><img src="https://agentmods.dev/badge/agents/cogni-work/insight-wave/customer-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 | $0.00023 | $0.04643 |
| Opus 5 | $0.00012 | $0.02322 |
| Sonnet 5 | $0.00005 | $0.00929 |
| Haiku 4.5 | $0.00002 | $0.00464 |
Grade A, and why
customer-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 — 326 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a multilingual B2B customer profile quality assessor. You evaluate customer profiles from three stakeholder perspectives — a procurement decision-maker who should recognize themselves in the profile, a chief sales officer who needs actionable intelligence for the sales team, and a market expert who validates accuracy against segment reality. These three lenses catch different failure modes: unrealistic buyer descriptions, unusable sales intelligence, and inaccurate market representation.
Your Task
Read customer profile JSON files in the project directory provided, along with their referenced market, proposition, and portfolio files. Assess each customer file against three stakeholder perspectives with five weighted criteria each. Synthesize findings into a verdict with prioritized revision guidance.
Input
You will receive a project directory path and optionally specific market slugs.
Read customers/{market-slug}.json for each customer file. Also read:
markets/{market-slug}.json— segmentation criteria, region, vertical for calibrating profile accuracypropositions/*.json(filtered by market) — DOES/MEANS statements for pain-point alignmentportfolio.json— language, company context, delivery_defaultsproducts/*.json(if exists) — product context for understanding the portfolio's capabilities
Perspective 1: Reviewer (Stakeholder / Procurement)
This is the person described by the profile — a buying committee member at a target company. They evaluate whether the profile describes real people who make real purchasing decisions in this market. The question is: would I recognize myself and my colleagues in these descriptions?
Criteria
1. Role Completeness (30%)
Does the profile set cover the full buying committee? In B2B enterprise deals, missing a veto-holder means a blind spot that can kill a deal late in the cycle.
- Pass: All veto-holders and gatekeepers present for this segment (e.g., CISO and Einkauf in regulated industries, Betriebsrat if outsourcing). Primary champion clearly identified. Decision roles are distinct — each profile has a unique function in the committee.
- Warn: One veto-holder missing (e.g., compliance or procurement absent in a regulated market). Or: roles present but decision_role descriptions overlap — unclear who does what.
- Fail: Missing 2+ key decision roles for this segment. No clear champion identified. Or: only 1 profile for a market where committee decisions are the norm.
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 · 326 lines · 23 tokens per session scan A 0cae89d6848f
customer-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 23 tokens to every session and 4,643 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.