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/plugins/cogni-work/insight-wave/cogni-trends)<a href="https://agentmods.dev/plugins/cogni-work/insight-wave/cogni-trends"><img src="https://agentmods.dev/badge/plugins/cogni-work/insight-wave/cogni-trends/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/plugins/cogni-work/insight-wave/cogni-trends"><img src="https://agentmods.dev/badge/plugins/cogni-work/insight-wave/cogni-trends.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
cogni-trends 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.
What it actually says
{
"name": "cogni-trends",
"version": "0.6.37",
"description": "Strategic trend scouting and TIPS reporting pipeline. Combines the Smarter Service Trendradar (4 dimensions) with TIPS (Trends, Implications, Possibilities, Solutions): trend-scout → value-modeler → trend-research → trend-synthesis and/or trend-booklet → verify-trend-report. Evidence-backed CxO reports and reusable industry catalogs across DE/FR/IT/PL/NL/ES + US/UK.",
"author": {
"name": "Stephan de Haas",
"email": "[email protected]"
},
"license": "Apache-2.0",
"keywords": [
"tips",
"trend-scout",
"value-modeler",
"trend-research",
"trend-synthesis",
"trend-booklet",
"verify-trend-report",
"trends",
"strategic-trends",
"smarter-service",
"trendradar",
"capability-imperative",
"investment-theme",
"bilingual",
"agent"
]
}
What it installs
The manifest is a name and a version. 9 skills, 12 agents travel with it, and installing the plugin installs all of them — 2,029 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill trend-scout A 127 tokens
- Skill trend-synthesis A 237 tokens
- Skill trend-research A 237 tokens
- Skill value-modeler A 146 tokens
- Skill trend-booklet A 206 tokens
- Skill trends-dashboard A 103 tokens
- Skill trends-resume A 136 tokens
- Skill verify-trend-report A 177 tokens
- Skill trends-catalog A 134 tokens
- Agent trend-generator A 41 tokens
- Agent trend-web-researcher A 41 tokens
- Agent trend-candidate-reviewer A 27 tokens
- Agent trend-report-investment-theme-writer A 55 tokens
- Agent trend-report-composer A 81 tokens
- Agent trend-report-writer A 52 tokens
- Agent trend-deep-researcher A 24 tokens
- Agent trend-report-reviewer A 17 tokens
- Agent trend-report-revisor A 21 tokens
- Agent br-pre-scorer A 68 tokens
- Agent trend-booklet-formatter A 76 tokens
- Agent trend-signal-curator A 23 tokens
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 Changed 63a0c0a34113
- 1mo ago Changed 76253c27a66e
- 1mo ago Changed 83db24a5af9a
- 1mo ago Changed 42bb2425b686
- 1mo ago Changed c49e3aca0493
- 1mo ago Changed 7935ebd491ef
- 1mo ago Changed a03e791de176
- 1mo ago First seen · 28 lines scan A d1f1d4c967b8
cogni-trends is a plugin published in the GitHub repository cogni-work/insight-wave (13 stars, last pushed 1mo ago), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 plugins, from other repositories
humanizer
Rewrite AI-sounding text so it reads like the writer without changing what it says.
claude-plugins-official marketplace
Directory of popular Claude Code extensions including development tools, productivity plugins, and MCP integrations.
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.
themes-example
themes-example. An open-source AI agent that brings the power of Gemini directly into your terminal.
knowledge-work-plugins marketplace
Plugin marketplace listing 123 plugins: noibu, productivity, enterprise-search, cowork-plugin-management, sales.
superpowers
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques.