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 zircote/git-notes-memorynpx agentmods add plugins/zircote/git-notes-memory/marketplacegit clone --depth 1 https://github.com/zircote/git-notes-memoryGrade A, and why
git-notes-memory 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": "git-notes-memory",
"description": "Plugin marketplace for git-notes-memory - Git-native, semantically-searchable memory storage for Claude Code",
"version": "1.0.0",
"owner": {
"name": "zircote",
"email": "[email protected]"
},
"plugins": [
{
"name": "memory-capture",
"description": "Git-backed memory system for Claude Code. Captures decisions, learnings, and context as git notes with semantic search and automatic recall.",
"version": "0.12.0",
"author": {
"name": "Robert Allen",
"email": "[email protected]"
},
"repository": "https://github.com/zircote/git-notes-memory-manager",
"license": "MIT",
"keywords": ["memory", "git-notes", "semantic-search", "context", "recall"],
"source": "./",
"homepage": "https://github.com/zircote/git-notes-memory-manager#readme"
}
]
}
What ships with it
1 file beside marketplace.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 First seen · 26 lines scan A 2cd0569937e1
git-notes-memory is a plugin published in the GitHub repository zircote/git-notes-memory (4 stars, last pushed 8mo 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 2026-08-31.
Other plugins, from other repositories
student-llm-wiki
Compile course materials into a persistent, interlinked Obsidian wiki. Karpathy LLM Wiki pattern with student features: Feynman review, exam prep, confidence decay, cross-course connections. Bilingual Chinese-English.
student-llm-wiki
Plugin marketplace listing 1 plugin: student-llm-wiki.
subcog
Persistent memory system for AI coding assistants. Captures decisions, learnings, and context from coding sessions and surfaces them when relevant.
quiz-me
Gates code changes behind an interactive quiz: Claude investigates, tests your understanding of root cause and fix, and only implements once you pass.
rudder-core
Cross-tool RudderStack domain knowledge: data catalog, data graphs, tracking plans, instrumentation planning, instrumentation debugging, and destination delivery debugging.
rudder-mcp
Workflows for RudderStack's MCP server at mcp.rudderstack.com: connect AI/LLM agents to a RudderStack workspace and drive catalog, sources, destinations, transformations, RETL, tracking plans, and live events via MCP tool calls.