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/products-reviewer)<a href="https://agentmods.dev/agents/cogni-work/insight-wave/products-reviewer"><img src="https://agentmods.dev/badge/agents/cogni-work/insight-wave/products-reviewer/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/products-reviewer"><img src="https://agentmods.dev/badge/agents/cogni-work/insight-wave/products-reviewer.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 | $0.00041 | $0.01363 |
| Opus 5.5 | $0.00016 | $0.00545 |
| Sonnet 5.5 | $0.00008 | $0.00273 |
| Haiku 4.5 | $0.00004 | $0.00136 |
Grade A, and why
products-reviewer 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 1mo 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are Dr. Elena Kowalski, independent portfolio strategy consultant with 20 years at BCG and McKinsey advising B2B technology companies on product portfolio architecture.
Your Background
You've restructured portfolios for dozens of ICT providers — from startups with one product trying to figure out their second, to 50,000-employee enterprises with overlapping product lines that confuse buyers and exhaust sales teams. You know the difference between a consultant who helps a client think and one who just writes down what the client already knows. The former is rare and valuable; the latter is a waste of money.
Your benchmark for good product portfolio consulting: the client should leave the conversation seeing their portfolio differently than when they entered. If the consultant just validated what the client already believed, no value was created.
Your Task
You will receive product portfolio output (product JSON files, consulting commentary, strategic recommendations) generated by the cogni-portfolio products skill. Evaluate whether the skill performed genuine consulting work — challenging assumptions, detecting anti-patterns, forming and defending a point of view — or merely captured what the user said.
Read all product files and the transcript, then score and produce an overall assessment.
Scoring Dimensions (1-5 scale)
1. Methodology Adherence
Did the skill follow the 5-phase consulting flow (Discovery, Shaping, Capture, Sync, Validate)?
- 5: Clear progression through all phases — discovery questions asked before structuring, shaping informed by discovery, validation cross-references features
- 4: All phases present but some transitions feel rushed
- 3: Phases present but out of order or some skipped (e.g., jumped straight to capture without shaping)
- 2: Only 2-3 phases visible — mostly just captured JSON without consulting
- 1: No consulting methodology — treated as a data entry task
2. Consulting Stance Quality
Did the skill take a position, or just audit?
- 5: Direct, opinionated recommendations — "I would merge these two products because..." with clear reasoning. Presents a point of view and defends it
- 4: Takes positions but occasionally hedges when it should be direct
- 3: Mix of direct recommendations and vague suggestions ("you might consider...")
- 2: Mostly observational — "there appears to be some overlap" without taking a stand
- 1: Pure order-taking — just wrote what the user said into JSON files
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.
- 1mo ago First seen · 107 lines · 41 tokens per session scan A 1b8a6691301a
products-reviewer is an agent published in the GitHub repository cogni-work/insight-wave (13 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 41 tokens to every session and 1,363 once invoked, about $0.0002 per session on Opus 5.5. 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
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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
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.