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-codegit 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)<a href="https://agentmods.dev/plugins/outlinedriven/odin-claude-plugin/odin-code"><img src="https://agentmods.dev/badge/plugins/outlinedriven/odin-claude-plugin/odin-code.svg" alt="Measured on agentmods" height="20"></a>Grade A, and why
odin-code 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",
"displayName": "ODIN Code",
"version": "2.0.4",
"description": "ODIN workflows for writing, reviewing, and maintaining code.",
"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"
]
}
What it installs
The manifest is a name and a version. 52 skills travel with it, and installing the plugin installs all of them — 3,200 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill deps-upgrade A 78 tokens
- Skill commit A 66 tokens
- Skill setup-gitignore A 58 tokens
- Skill doubt-driven A 51 tokens
- Skill to-spec A 58 tokens
- Skill principles A 61 tokens
- Skill observability A 72 tokens
- Skill review A 69 tokens
- Skill validate-changes-match-specs A 58 tokens
- Skill ci-cd A 62 tokens
- Skill codebase-design A 51 tokens
- Skill no-comments A 78 tokens
- Skill offense A 89 tokens
- Skill resolve-merge-conflicts A 61 tokens
- Skill setup-pre-commit A 71 tokens
- Skill simplify A 65 tokens
- Skill tdd A 80 tokens
- Skill tests-adversarial A 53 tokens
- Skill ast-grep A 57 tokens
- Skill minimalism-driven A 56 tokens
- Skill planning-and-task-breakdown A 62 tokens
- Skill reproduce-bug-report A 61 tokens
- Skill spec-driven A 54 tokens
- Skill trailmark-summary A 73 tokens
- Skill worktree A 59 tokens
- Skill contract-driven A 52 tokens
- Skill explore A 40 tokens
- Skill incremental-implementation A 58 tokens
- Skill isolate-workspace-gate A 64 tokens
- Skill lighter-checks A 48 tokens
- Skill reproduce-and-fix-issues A 55 tokens
- Skill run-smoke-tests A 43 tokens
- Skill sarif-parsing A 57 tokens
- Skill source-driven A 52 tokens
- Skill spec-driven-implementation A 52 tokens
- Skill type-driven A 65 tokens
- Skill universal-invariant-baseline A 54 tokens
- Skill review-reception-protocol A 55 tokens
- Skill visual-diff-review A 57 tokens
- Skill review-speedread A 64 tokens
- Skill deslop B 74 tokens
- Skill isolate-work-in-worktree C 59 tokens
- Skill diagramming-code A 69 tokens
- Skill ci-fix A 94 tokens
- Skill classify-ci-failure A 64 tokens
- Skill code-simplification A 56 tokens
- Skill dx-audit A 56 tokens
- Skill commit-economy A 62 tokens
- Skill constraint-driven-development A 69 tokens
- Skill api-and-interface-design A 60 tokens
- Skill create-branch A 56 tokens
- Skill devcontainer-setup C 62 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 · 21 lines scan A 50569f537794
odin-code 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
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.
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.