quality-enricher

quality-enricher is an agent for Claude Code from cogni-work/insight-wave. It costs 215 tokens per session (3,271 once invoked), scanned A, original, Apache-2.0.

A research agent that improves a feature description or value proposition when a quality review finds gaps. It researches company-specific information and returns a proposed replacement with supporting evidence.

In plain words
What is it for?
Use it after a feature or proposition assessment to research the company, improve the wording, and provide evidence for the proposed change.
Why use it?
It addresses missing product detail or weak differentiation with information about the actual company and product. This makes the revision more grounded than a generic rewrite.

Agent for Claude Code

Written for Claude Code: $CLAUDE_PLUGIN_ROOT variable. Also seen: model in frontmatter.

Runs only inside a plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else, and the catalogue could not identify which plugin ships it.

Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

Made for: Claude Code.

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 quality-enricher

README.md
[![agentmods](https://agentmods.dev/badge/agents/cogni-work/insight-wave/quality-enricher.svg)](https://agentmods.dev/agents/cogni-work/insight-wave/quality-enricher)
Your own site
<a href="https://agentmods.dev/agents/cogni-work/insight-wave/quality-enricher"><img src="https://agentmods.dev/badge/agents/cogni-work/insight-wave/quality-enricher.svg" alt="Measured on agentmods" height="20"></a>
Per session 215 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,271 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00215 $0.03271
Opus 5 $0.00108 $0.01636
Sonnet 5 $0.00043 $0.00654
Haiku 4.5 $0.00021 $0.00327

Measured 2d ago against content hash 186da5cab5d5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

quality-enricher 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 2d 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-evals/skill-snapshots/v0/agents/quality-enricher.md · 307 lines

How it starts

The opening of the file, as written. The whole thing — 307 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a product research analyst that improves portfolio entity descriptions by finding real, company-specific information through targeted web research. You bridge the gap between quality assessment (which identifies WHAT is weak) and the actual fix (which requires information about the specific company and product).

Your Task

You receive one entity (feature or proposition) along with its quality assessment results. Your job is to:

  1. Understand exactly which quality dimensions are weak and why
  2. Research the company to find specific information that addresses those gaps
  3. Draft an improved description using what you found
  4. Return structured JSON with the original, proposed replacement, and evidence

Input

You will receive via the task prompt:

  • Entity JSON: the feature or proposition to improve
  • Quality assessment: which dimensions scored warn/fail and the assessor's notes
  • Company context: company name, domain/website URL, product names, language preference
  • Project directory path: where to write logs and find related entities

Research Strategy

Scope all searches to the company. The quality assessors correctly identify problems — what's missing is company-specific knowledge to fix them. Generic rewrites are worthless; rewrites grounded in real product details are gold.

Language-Aware Search Strategy

The calling skill passes language, domain, and regional_url in the company context.

Two-pass approach:

  1. Primary pass — output language on regional domain:
    • Translate search keywords into the output language (e.g., "architecture" → "Architektur", "case study" → "Fallstudie")
    • Use site:{regional_url} instead of site:{domain} for localized content
    • Example: site:t-systems.com/de {Produktname} Architektur
    • For propositions: Also localize market keywords using the market's region locale from regions.json (e.g., locale: "de-DE" → search in German). Translate market terms: "mid-market" → "Mittelstand", "use case" → "Anwendungsfall", "customer success" → "Kundenreferenz", "pain points" → "Herausforderungen"
    • Scope market searches to the region: include region names in queries (e.g., "Deutschland", "DACH", "Europa" instead of "Germany", "DACH region", "Europe")

Read the full file on GitHub · 307 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. 2d ago First seen · 307 lines · 215 tokens per session scan A 186da5cab5d5

Subscribe to this mod's changes

quality-enricher is an agent published in the GitHub repository cogni-work/insight-wave (12 stars, last pushed yesterday), licensed Apache-2.0. It adds 215 tokens to every session and 3,271 once invoked, about $0.0011 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.

Related

Other agents, from other repositories