agentmods.dev

cogni-knowledge

cogni-knowledge is a plugin for Claude Code from cogni-work/insight-wave. Its manifest loads nothing; the 23 skills, 16 agents it bundles cost 5,468 tokens per session together, scanned A, original, Apache-2.0.

A wiki-based research plugin that stores findings in a shared knowledge base for later work. It can organize sources, check claims against stored evidence, and optionally refresh information from live sources.

In plain words
What is it for?
Use it to gather, file, query, verify, and reuse research in a team or project knowledge base.
Why use it?
It reduces repeated research and keeps later answers connected to earlier notes and citations.

Plugin for Claude Code

Written for Claude Code: a Claude Code plugin manifest.

not rated 13repo changed 1mo ago A scan tokens not measured original Apache-2.0

Good fit Use it to gather, file, query, verify, and reuse research in a team or project knowledge base.

Compare 6 plugins from other repositories ↓
Install in Claude Code
/plugin marketplace add cogni-work/insight-wave
/plugin install cogni-knowledge
View source ↗ cogni-work/insight-wave
Install

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.

Clone the repo
git clone --depth 1 https://github.com/cogni-work/insight-wave

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 cogni-knowledge

README.md
[![agentmods](https://agentmods.dev/badge/plugins/cogni-work/insight-wave/cogni-knowledge/github.svg)](https://agentmods.dev/plugins/cogni-work/insight-wave/cogni-knowledge)
Your own site
<a href="https://agentmods.dev/plugins/cogni-work/insight-wave/cogni-knowledge"><img src="https://agentmods.dev/badge/plugins/cogni-work/insight-wave/cogni-knowledge/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.

agentmods 80×15 button for cogni-knowledge

Your own site · 80×15
<a href="https://agentmods.dev/plugins/cogni-work/insight-wave/cogni-knowledge"><img src="https://agentmods.dev/badge/plugins/cogni-work/insight-wave/cogni-knowledge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured The manifest loads nothing itself; its 23 skills, 16 agents cost 5,468 tokens a session between them.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

cogni-knowledge 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.

cogni-knowledge/.claude-plugin/plugin.json · 27 lines

What it actually says

{
  "name": "cogni-knowledge",
  "version": "1.0.125",
  "description": "Wiki-first research that compounds. Binds each run to a wiki knowledge base; future runs read what prior runs filed before hitting the web. v0.1.0 inverted pipeline (plan → curate → fetch → ingest → distill → compose → verify → finalize) with zero-network, citation-consistent claim verification — opt-in live-source resweep via `knowledge-refresh --resweep`. The shallow `knowledge-query` rung is read-only by default and can optionally file its answer back as an un-verified synthesis page via `--file-back`.",
  "author": {
    "name": "Stephan de Haas",
    "email": "[email protected]"
  },
  "license": "Apache-2.0",
  "keywords": [
    "knowledge-base",
    "wiki-first",
    "compound-knowledge",
    "research-orchestrator",
    "binding",
    "karpathy",
    "inverted-pipeline",
    "citation-consistent",
    "zero-network-verification",
    "resweep",
    "contradiction-tripwire",
    "knowledge-graph",
    "agents",
    "released"
  ]
}
Contents

What it installs

The manifest is a name and a version. 23 skills, 16 agents travel with it, and installing the plugin installs all of them — 5,468 tokens a session between them. Each is measured on its own page, and each can be installed alone.

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. 1mo ago Changed 8726cabc4917
  2. 1mo ago Changed 8a73d183ae99
  3. 1mo ago Changed 2bfd05545bed
  4. 1mo ago Changed efa3ec38416e
  5. 1mo ago Changed 23178ab90a2a
  6. 1mo ago Changed 5e053e484d33
  7. 1mo ago Changed 13aa90d3a9f0
  8. 1mo ago First seen · 27 lines scan A 0d9489a80c7c

Subscribe to this mod's changes

cogni-knowledge 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 2026-08-30.

Memory and contextResearch
Related

Other plugins, from other repositories

open-knowledge-vault

Create and maintain portable Open Knowledge Format vaults with optional Obsidian and Dataview views.

glebis/claude-skills · not measured

knowledge-and-memory

Research methodology, corpus search, persistent memory, iterative workflows, and project knowledge management.

oaustegard/claude-skills · not measured

pai

Personal AI Infrastructure — persistent memory, session continuity, and knowledge graph for Claude Code.

mnott/PAI · not measured

tree-ring-memory

Local-first memory lifecycle, project bootstrap, and receipt-backed harness guidance for Claude Code using Tree Ring Memory v0.15+.

TerminallyLazy/Tree-Ring-Memory · not measured

claude-mega-brain

OKF-powered knowledge context for Claude Code — injects your project knowledge base at every session.

guhcostan/claude-mega-brain · not measured

vault-template

Personal Knowledge Management system for Obsidian with AI-powered workflows, goal tracking, and productivity coaching.

ballred/obsidian-claude-pkm · not measured