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/wrg32786/aigent-osWrote 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/wrg32786/aigent-os/context-capsule)<a href="https://agentmods.dev/plugins/wrg32786/aigent-os/context-capsule"><img src="https://agentmods.dev/badge/plugins/wrg32786/aigent-os/context-capsule/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/wrg32786/aigent-os/context-capsule"><img src="https://agentmods.dev/badge/plugins/wrg32786/aigent-os/context-capsule.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
context-capsule 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-capsule",
"version": "0.1.0",
"description": "Write a resume-ready capsule of your session, then /clear or auto-compact and pick up exactly where you left off. Manual-trigger refresh: PreCompact marker with a post-compact reminder, SessionStart pointer on clear and compact, /capsule, /refresh and /resume. Zero dependencies, no network.",
"author": { "name": "wrg32786" },
"homepage": "https://github.com/wrg32786/aigent-os/tree/master/plugins/context-capsule",
"repository": "https://github.com/wrg32786/aigent-os",
"license": "MIT",
"userConfig": {
"capsuleDir": {
"type": "string",
"title": "Capsule directory",
"description": "Folder where capsules are written and read. Relative paths resolve against the project. Empty: <project>/.claude/capsules/.",
"default": ""
},
"maxAgeDays": {
"type": "number",
"title": "Stale limit (days)",
"description": "Capsules older than this are refused at resume instead of loaded.",
"default": 14
}
}
}
What it installs
The manifest is a name and a version. 2 skills, 3 commands, 2 hooks travel with it, and installing the plugin installs all of them — 175 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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 · 24 lines scan A 7a042b4ad7a4
context-capsule is a plugin published in the GitHub repository wrg32786/aigent-os (25 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 2026-10-28.
Other plugins, from other repositories
ai-brain-starter
Set up or upgrade an AI-powered Obsidian vault with journaling, knowledge graphs, pattern recognition, and meeting workflows. Includes skills for daily journaling, weekly insights, graphify knowledge graphs, humanizer, and more.
prism-coder
Your coding agent forgets everything between sessions. Prism gives it a memory that sticks: your decisions, open TODOs, and changed files, restored the moment you return. It goes past a notes store — associative recall surfaces related past work, drift detection catches a long session wandering off-goal, and an…
claude-code-hermit
Your own local Claude Tag, in the Claude app, Discord, Telegram, or a custom Claude Code channel.
scout
Autonomous knowledge management and daily briefing system. Monitors your work tools (Slack, Calendar, Linear, GitHub, etc.), synthesizes findings into a persistent knowledge base with a formal ontology, and delivers daily action items — all running unattended via scheduled Claude Code sessions. Six session types…
context-doctor
Cut your Claude Code bill, measured on your own sessions: /context-doctor:savings shows the dollars, an every-prompt check names the waste, and /context-doctor:compact-window makes Claude Code compact earlier by itself.
para-knowledge-base
Build, query, index, and audit portable PARA knowledge bases in Obsidian with privacy-safe operation telemetry.