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/archcore-ai/pluginWrote 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/archcore-ai/plugin/archcore)<a href="https://agentmods.dev/plugins/archcore-ai/plugin/archcore"><img src="https://agentmods.dev/badge/plugins/archcore-ai/plugin/archcore/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/archcore-ai/plugin/archcore"><img src="https://agentmods.dev/badge/plugins/archcore-ai/plugin/archcore.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
archcore 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 25d 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": "archcore",
"description": "Spec-driven development and context engineering for AI coding agents, backed by project context in Git.",
"version": "0.9.3",
"author": {
"name": "Archcore"
},
"license": "Apache-2.0",
"repository": "https://github.com/archcore-ai/plugin",
"mcpServers": "./.claude.mcp.json",
"keywords": [
"claude-code",
"cursor",
"claude-code-plugin",
"mcp",
"ai-agents",
"ai-coding",
"coding-agents",
"project-context",
"context-engineering",
"architecture",
"adr",
"knowledge-management",
"rules",
"decisions",
"conventions",
"git-native",
"skills",
"subagents",
"spec-driven-development",
"documentation"
]
}
What it installs
The manifest is a name and a version. 4 skills, 4 commands, 2 agents, 3 hooks travel with it, and installing the plugin installs all of them — 1,100 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill init A 235 tokens
- Skill document A 183 tokens
- Skill plan A 247 tokens
- Skill review A 127 tokens
- Command init A 65 tokens
- Command plan A 68 tokens
- Command review A 39 tokens
- Command document A 43 tokens
- Agent archcore-auditor B 43 tokens
- Agent archcore-assistant C 50 tokens
- Hook PostToolUse A not measured
- Hook PreToolUse A not measured
- Hook SessionStart A not measured
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.
- 25d ago Changed 1bad307b2d86
- 27d ago Changed 72dc6333dc52
- 29d ago Changed 0e5a4377cea4
- 1mo ago Changed 3a1165d739cb
- 1mo ago Changed 8378558ed47c
- 1mo ago First seen · 34 lines scan A 021321910458
archcore is a plugin published in the GitHub repository archcore-ai/plugin (58 stars, last pushed 26d 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.
Other plugins, from other repositories
cc-hud
Compact statusline HUD for Claude Code — context, agents, rate limits.
compact-manager
Warns the main session as its own context fills, captures a wake packet before compaction, and reorients the session after it — so an autonomous orchestrator survives past one context window.
digital-brain
Claude + Obsidian knowledge companion. Sets up a persistent, compounding wiki vault. Covers memory management, session notetaking, knowledge organization, and agent context across projects. Based on Andrej Karpathy's LLM Wiki pattern.
context-memory
Persistent, searchable context storage across Claude Code sessions using SQLite + FTS5.
prompt-vault
Never lose context again. Automatic session logging with phase-based history, HTML reports, and seamless recovery after context compaction.
lore
Lore — cross-session memory for Claude Code. Every session becomes a markdown note in your Obsidian vault; the next session recalls what you built and where it lives, without searching.