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/charlesjones-dev/claude-code-plugins-devWrote 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/charlesjones-dev/claude-code-plugins-dev/ai-knowledge)<a href="https://agentmods.dev/plugins/charlesjones-dev/claude-code-plugins-dev/ai-knowledge"><img src="https://agentmods.dev/badge/plugins/charlesjones-dev/claude-code-plugins-dev/ai-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.
<a href="https://agentmods.dev/plugins/charlesjones-dev/claude-code-plugins-dev/ai-knowledge"><img src="https://agentmods.dev/badge/plugins/charlesjones-dev/claude-code-plugins-dev/ai-knowledge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
ai-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 10d 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": "ai-knowledge",
"version": "1.5.2",
"description": "Keeps a git-versioned team knowledge base in docs/kb/ next to Claude Code's per-machine auto memory: capture learnings, import and search articles, load them by task, and browse the base in Obsidian",
"author": {
"name": "Charles Jones",
"url": "https://charlesjones.dev"
},
"repository": "https://github.com/charlesjones-dev/claude-code-plugins-dev",
"license": "MIT",
"keywords": [
"ai",
"knowledge-base",
"learnings",
"institutional-knowledge",
"claude-md",
"documentation",
"best-practices",
"lessons-learned",
"kb",
"productivity",
"obsidian",
"graph-view",
"wiki-links"
]
}
What it installs
The manifest is a name and a version. 17 skills travel with it, and installing the plugin installs all of them — 585 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill kb-discover A 34 tokens
- Skill kb-upgrade A 47 tokens
- Skill kb-harvest A 37 tokens
- Skill kb-learn A 35 tokens
- Skill kb-init A 32 tokens
- Skill kb-prune A 34 tokens
- Skill kb-absorb A 33 tokens
- Skill kb-add A 31 tokens
- Skill kb-ingest A 37 tokens
- Skill kb-query A 32 tokens
- Skill kb-import A 40 tokens
- Skill kb-organize A 38 tokens
- Skill kb-load A 40 tokens
- Skill kb-remove A 32 tokens
- Skill kb-list A 30 tokens
- Skill kb-search A 29 tokens
- Skill kb-auto A 24 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.
- 10d ago Changed · +1 lines 3f8d9b6db042
- 1mo ago First seen · 26 lines scan A cca1d2dc2391
ai-knowledge is a plugin published in the GitHub repository charlesjones-dev/claude-code-plugins-dev (35 stars, last pushed 6d ago), licensed MIT. 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
memstack
131 battle-tested skills for Claude Code. Session memory, git workflows, database migrations, security scanning, deployments, and more. Auto-trigger commands and project handoffs via markdown-based skills.
dstoic
Core infrastructure: git commits, model selection, hooks, scratch pad, kaizen, devil-advocate agent, context save/load, verbatim checkpoint, resumable work plans (plan-context), meta-prompt (RELIANCE recursive ledger), and session post-mortem.
unforgit-claude-code-marketplace
Claude Code plugins for Unforgit persistent repository memory.
commitlore
Recorded decisions from git history, delivered to the agent before it edits. Constraints, alternatives already ruled out, and warnings left by whoever was here last.
unforgit
Persistent repository memory for AI coding agents using MCP tools, repository rules, and durable project knowledge.
continuity
Durable project state across AI sessions: decisions, constraints, and rejected paths, versioned in git as plain markdown. Not a memory tool — it answers what is true about the project now, and what must not change.