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.
/plugin marketplace add cogni-work/insight-wavenpx agentmods add plugins/cogni-work/insight-wave/cogni-consultgit 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-consult)<a href="https://agentmods.dev/plugins/cogni-work/insight-wave/cogni-consult"><img src="https://agentmods.dev/badge/plugins/cogni-work/insight-wave/cogni-consult.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
cogni-consult 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 yesterday.
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-consult",
"version": "0.1.123",
"description": "Consulting engagement orchestrator where action fields are the work-breakdown-structure containers for every deliverable: each deliverable runs its own design-thinking loop (empathize→define→ideate→prototype→test), acting stakeholder personas challenge the work in their own voice, and one cogni-knowledge base per engagement is the central research tool that compounds across all deliverables.",
"author": {
"name": "Stephan de Haas",
"email": "[email protected]"
},
"license": "Apache-2.0",
"keywords": [
"consulting",
"action-fields",
"wbs",
"design-thinking",
"deliverables",
"personas",
"knowledge-base",
"orchestrator",
"agent",
"hooks"
]
}
What it installs
The manifest is a name and a version. 9 skills, 4 agents, 1 hook travel with it, and installing the plugin installs all of them — 1,738 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill consult-design-thinking A 229 tokens
- Skill consult-action-fields A 238 tokens
- Skill consult-resume A 158 tokens
- Skill consult-dashboard A 88 tokens
- Skill consult-personas A 176 tokens
- Skill consult-project-plan A 233 tokens
- Skill consult-publish A 152 tokens
- Skill consult-scope A 150 tokens
- Skill consult-setup A 139 tokens
- Agent consult-empathy-mapper A 59 tokens
- Agent consult-framework-adherence-reviewer A 43 tokens
- Agent consult-dashboard-refresher A 24 tokens
- Agent consult-persona-challenger A 49 tokens
- Hook SubagentStart A not measured
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.
- yesterday Changed 57f938d77a5f
- 5d ago First seen · 23 lines scan A 7edf0ba0ca4b
cogni-consult is a plugin published in the GitHub repository cogni-work/insight-wave (12 stars, last pushed today), 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 2026-08-30.
Other plugins, from other repositories
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.
claude-plugins-official marketplace
Directory of popular Claude Code extensions including development tools, productivity plugins, and MCP integrations.
humanizer
Rewrite AI-sounding text so it reads naturally without changing what it says.
knowledge-work-plugins marketplace
Plugin marketplace listing 98 plugins: noibu, productivity, enterprise-search, cowork-plugin-management, sales.
mattpocock-skills
Matt Pocock's agent skills for real engineering: grilling, spec/ticket flows, TDD, code review, domain modelling and more. Plug-and-play, not vibe coding.
container
Teaches Claude container's command surface and how it maps to Docker, Lima, Colima, and Podman on macOS.