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 OutlineDriven/odin-claude-pluginnpx agentmods add plugins/outlinedriven/odin-claude-plugin/odin-coregit clone --depth 1 https://github.com/OutlineDriven/odin-claude-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/outlinedriven/odin-claude-plugin/odin-core)<a href="https://agentmods.dev/plugins/outlinedriven/odin-claude-plugin/odin-core"><img src="https://agentmods.dev/badge/plugins/outlinedriven/odin-claude-plugin/odin-core.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
odin-core 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
{
"$schema": "https://json.schemastore.org/claude-code-plugin-manifest.json",
"name": "odin-core",
"displayName": "ODIN Core",
"version": "2.0.4",
"description": "Core ODIN workflows for planning, executing, and checking changes.",
"author": {
"name": "OutlineDriven",
"url": "https://github.com/OutlineDriven"
},
"homepage": "https://github.com/OutlineDriven/odin-claude-plugin",
"repository": "https://github.com/OutlineDriven/odin-claude-plugin",
"license": "SEE LICENSE IN LICENSE",
"keywords": [
"odin",
"outlinedriven",
"agent-skills",
"core"
],
"mcpServers": "./mcp.json",
"outputStyles": "./output-styles"
}
What it installs
The manifest is a name and a version. 16 skills travel with it, and installing the plugin installs all of them — 928 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill graph-backbone A 51 tokens
- Skill minimap A 56 tokens
- Skill axiom-mode A 61 tokens
- Skill keep-why-repo-trust-boundary A 49 tokens
- Skill possible-worlds A 62 tokens
- Skill ai-collab-protocols A 60 tokens
- Skill instruction-understanding-gate A 67 tokens
- Skill necessary-work A 59 tokens
- Skill verification-before-completion A 90 tokens
- Skill post-change-check-gate A 53 tokens
- Skill skill-gap-finder A 58 tokens
- Skill intent-proposal A 47 tokens
- Skill entropy-assisted-planning A 48 tokens
- Skill cybernetic-loop A 52 tokens
- Skill diamond-task A 59 tokens
- Skill enforce-workflow-constraints A 56 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.
- yesterday First seen · 23 lines scan A df1b7264b568
odin-core is a plugin published in the GitHub repository OutlineDriven/odin-claude-plugin (35 stars, last pushed yesterday), 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 2026-09-04.
Other plugins, from other repositories
action
Convert tickets to branches in isolated worktrees. Uses team branch conventions, lands gated commits, and supports parallel tickets.
gh
File durable GitHub issues with reproductions, pinned links, and stripped PII. Enforces a markdown writing discipline reusable for any PR, comment, or ticket.
situate
Gain situational awareness before modifying code. Scans branches, PRs, tickets, and project conventions to orient the agent and verify the work required.
ccx
Scratch-notebook context management for any project: per-thread STATE.md handoff docs with one-command create-or-resume (/ccx:start-thread), a compiled parallel-session-safe INDEX dashboard that recompiles itself on every STATE write (/ccx:save-state · /ccx:tidy-scratch), a Stop-hook freshness guard so working state…
agent-critter
一只桌宠小精灵,实时展示 Claude Code 的工作状态。支持 Petdex 社区 2700+ 精灵,透明窗口、可拖拽、可缩放。.
agent-critter marketplace
Agent Critter — Claude Code 桌面宠物插件,兼容 Petdex 2700+ 精灵.