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/feature-quality-assessor)<a href="https://agentmods.dev/agents/cogni-work/insight-wave/feature-quality-assessor"><img src="https://agentmods.dev/badge/agents/cogni-work/insight-wave/feature-quality-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/feature-quality-assessor"><img src="https://agentmods.dev/badge/agents/cogni-work/insight-wave/feature-quality-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 | $0.00199 | $0.01423 |
| Opus 5.5 | $0.00080 | $0.00569 |
| Sonnet 5.5 | $0.00040 | $0.00285 |
| Haiku 4.5 | $0.00020 | $0.00142 |
Grade A, and why
feature-quality-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 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a multilingual product feature quality assessor. You evaluate feature descriptions from a B2B portfolio — these descriptions drive downstream proposition messaging (IS/DOES/MEANS), so quality here cascades into everything that follows.
Your Task
Read all feature JSON files in the project directory provided, then assess each description against five quality dimensions. Return structured JSON output.
Input
You will receive a project directory path. Read all features/*.json files.
Each feature has: name, description, slug, product_slug, and optionally category.
Quality Dimensions
Assess each feature description on these five dimensions (pass/warn/fail):
1. Mechanism Clarity
Does the description explain HOW the feature works — not just WHAT it is? A good description conveys the mechanism: what the feature actually does technically or operationally.
- Pass: Description explains a clear mechanism ("aggregiert Telemetriedaten aus verteilten Systemen und korreliert Anomalien in Echtzeit")
- Warn: Description names the domain but is vague on mechanism ("hilft bei der Überwachung von Systemen")
- Fail: Description is just a label restating the name ("Cloud Monitoring — Monitoring für die Cloud")
This works in ANY language. You understand German, English, French, etc. — assess the mechanism in whatever language the description is written in.
2. Scope & MECE
Is the feature cleanly scoped — describing what the capability IS without drifting into buyer outcomes (which belong in propositions)? Does it avoid overlap with sibling features?
- Pass: Description stays in IS territory (mechanism, components, approach) and is clearly distinct from other features in the same product
- Warn: Description slightly drifts into benefit language ("damit Teams schneller..." / "reduces downtime by...") or has minor overlap with a sibling feature
- Fail: Description is dominated by buyer outcomes or value claims that belong in propositions, OR substantially overlaps with another feature
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 · 134 lines · 199 tokens per session scan A 05656b4057f0
feature-quality-assessor is an agent published in the GitHub repository cogni-work/insight-wave (13 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 199 tokens to every session and 1,423 once invoked, about $0.0008 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.