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-code-advancedgit 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-code-advanced)<a href="https://agentmods.dev/plugins/outlinedriven/odin-claude-plugin/odin-code-advanced"><img src="https://agentmods.dev/badge/plugins/outlinedriven/odin-claude-plugin/odin-code-advanced.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
odin-code-advanced 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-code-advanced",
"displayName": "ODIN Code Advanced",
"version": "2.0.4",
"description": "Advanced ODIN workflows for complex code changes and technical audits.",
"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",
"code",
"advanced"
]
}
What it installs
The manifest is a name and a version. 50 skills travel with it, and installing the plugin installs all of them — 3,060 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill slicing-code-context A 54 tokens
- Skill strict-validation-setup A 61 tokens
- Skill git-branchless A 58 tokens
- Skill validation-first-driven A 78 tokens
- Skill optimize A 86 tokens
- Skill smart-contract-code-maturity-assessor A 68 tokens
- Skill extremely-optimize A 54 tokens
- Skill model-retuning A 57 tokens
- Skill property-test-authoring A 57 tokens
- Skill property-test-review A 56 tokens
- Skill smart-contract-guidelines-advisor A 59 tokens
- Skill spec-to-code-compliance A 66 tokens
- Skill breaking-driven A 63 tokens
- Skill deprecate-and-migrate A 58 tokens
- Skill exhaustive A 77 tokens
- Skill guillotine A 78 tokens
- Skill make-bot-ui A 59 tokens
- Skill model-challenge A 56 tokens
- Skill mutation-campaign-configuration A 68 tokens
- Skill possible-worlds-qa A 86 tokens
- Skill proof-driven A 55 tokens
- Skill property-test-failure-triage A 56 tokens
- Skill property-testing-fit-assessment A 62 tokens
- Skill restart-keeping-lessons A 84 tokens
- Skill test-migration-coverage-gate A 83 tokens
- Skill tests-purge-unneeded A 71 tokens
- Skill verification-skill A 66 tokens
- Skill mutation-triage-genotoxic A 68 tokens
- Skill no-hide A 52 tokens
- Skill refactor-break-compat A 57 tokens
- Skill to-greenfield A 55 tokens
- Skill unleak-abstraction A 73 tokens
- Skill leave-only-first-principle A 51 tokens
- Skill record-design-decisions A 50 tokens
- Skill grill-with-docs A 55 tokens
- Skill pr-impact-quiz A 47 tokens
- Skill architect A 90 tokens
- Skill dimensional-analysis A 68 tokens
- Skill design-it-twice A 53 tokens
- Skill behavior-validator A 59 tokens
- Skill blast-radius A 51 tokens
- Skill capture-isolated-patch A 53 tokens
- Skill ci-sweeper A 54 tokens
- Skill clean-clean-cut A 55 tokens
- Skill document-api-endpoint A 63 tokens
- Skill control-cli A 42 tokens
- Skill control-ui A 40 tokens
- Skill fastopt A 49 tokens
- Skill fastopt-extreme A 52 tokens
- Skill complexity-grill A 47 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 · 22 lines scan A aa3768df71e1
odin-code-advanced is a plugin published in the GitHub repository OutlineDriven/odin-claude-plugin (35 stars, last pushed today), 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
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.
java-quality
Java quality toolkit — security (OWASP), performance (N+1, memory, threading), and testing (JUnit 5, Mockito, Testcontainers) for Java 8+ projects.
java-core
General Java skills, architect agent, and coding standards for Java 8+.
java-spring
Spring Boot scaffold skill and Spring expert agent for Java 8+ projects.
adversarial-review
Cross-host adversarial review for coding workflows. Material-only findings include over-engineering and missed reuse. Provider routing uses Codex GPT-5.6 Luna max, OpenCode Go DeepSeek V4 Flash xhigh, direct Moonshot Kimi K3 xhigh, direct-xAI Grok 4.5 high, and Gemini 3.7 Flash High first in the Antigravity ladder.