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/Supa-Media/contextWrote 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/supa-media/context/gemini)<a href="https://agentmods.dev/plugins/supa-media/context/gemini"><img src="https://agentmods.dev/badge/plugins/supa-media/context/gemini/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/supa-media/context/gemini"><img src="https://agentmods.dev/badge/plugins/supa-media/context/gemini.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
context 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 today.
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": "context",
"version": "0.1.0",
"description": "Your Context notes in your coding agent: the MCP server, skills that say when to read and write them, and hooks that orient at session start and save the session at the end.",
"mcpServers": {
"context": {
"httpUrl": "https://mcp.context.lc/mcp"
}
}
}
What ships with it
1 file beside gemini-extension.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.
- today First seen · 11 lines scan A fea8dec4a606
context is a plugin published in the GitHub repository Supa-Media/context (3 stars, last pushed today), 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 2026-09-26.
Other plugins, from other repositories
llm-wiki
Self-maintaining LLM wiki (Karpathy pattern): recall, observe, retro, capture sources, ensure pages, lint, and ingest. 15 tools over MCP.
markdown-vault-mcp
Generic markdown vault MCP with hybrid search.
arscontexta
Conversational derivation engine — generate agent-native memory architecture from natural conversation. 15 kernel primitives, 26 commands, 17 feature blocks, 3 presets.
vellum
Connect Claude to your self-hosted vellum markdown vault: read, write, search, tags, tasks and backlinks.
project-brain
Every Claude Code session, in every project, captured into one plain-Markdown brain you own. Index-first recall, automatic redaction, LLM-distilled session notes.
inkwell-hooks
Nudges Claude Code / Codex to actually use the Inkwell MCP memory server — search before starting work, and remember non-trivial changes before finishing.