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/michaelChe956/Cadence-skillsWrote 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/michaelche956/cadence-skills/cadence-init)<a href="https://agentmods.dev/plugins/michaelche956/cadence-skills/cadence-init"><img src="https://agentmods.dev/badge/plugins/michaelche956/cadence-skills/cadence-init/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/michaelche956/cadence-skills/cadence-init"><img src="https://agentmods.dev/badge/plugins/michaelche956/cadence-skills/cadence-init.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
cadence-init 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 1mo 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": "cadence-init",
"description": "项目初始化与存量项目知识库插件 - 包含环境检查、规则配置、MCP配置、Java + Vue/React Schema 4.0 KnowledgeBase、字段级数据模型、配置快照、强制变更包和渐进式任务上下文能力",
"version": "0.0.4",
"author": {
"name": "michaelChe",
"email": "[email protected]"
},
"homepage": "https://github.com/michaelChe956/Cadence-skills",
"repository": "https://github.com/michaelChe956/Cadence-skills",
"license": "MIT",
"keywords": ["cadence", "init", "project-setup", "knowledge-base", "context", "java", "vue", "react", "mcp", "environment"]
}
What it installs
The manifest is a name and a version. 14 skills travel with it, and installing the plugin installs all of them — 724 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill knowledge-base-overview A 70 tokens
- Skill knowledge-base-update A 29 tokens
- Skill knowledge-base-api A 39 tokens
- Skill knowledge-base-bootstrap A 64 tokens
- Skill knowledge-base-context A 123 tokens
- Skill knowledge-base-pages A 37 tokens
- Skill legacy-bootstrap A 32 tokens
- Skill project-rules-examples A 30 tokens
- Skill rule-config A 27 tokens
- Skill pre-check A 55 tokens
- Skill devbox-stack A 89 tokens
- Skill skill-creator A 56 tokens
- Skill knowledge-base-base-info A 46 tokens
- Skill mcp-configuration B 27 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.
- 1mo ago Changed 1e6dcd0c6638
- 1mo ago First seen · 14 lines scan A 42fafbc8a094
cadence-init is a plugin published in the GitHub repository michaelChe956/Cadence-skills (10 stars, last pushed 1mo ago), 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 2026-08-30.
Other plugins, from other repositories
mindos
Shared local people, project tasks and generated work views.
project-templates-toolkit
Four skills for starting, tracking, and closing out journalism projects: a project-instruction writer, a LESSONS.md retrospective writer, a template-selector decision tree for editorial tools, events, publications, research, pipelines, and archives, and an evidence-based weighted progress tracker.
delimit
Keep the state. Change the model. Persistent tasks, decisions, and handoffs across sessions and assistants.
papi
Persistent project management inside your AI coding tool. PAPI plans what to build next, tracks every decision, and keeps projects coherent across sessions — so a new session starts where the last one left off instead of from nothing.
handoff
Portable project memory + development workflow for coding agents: auto-loads STATUS+RULES each session, enforces folder-level CONTEXT.md on edit, nudges durable state updates at turn end, scaffolds the system into any repo via guided discovery, and ships a tiered 6-phase workflow skill set covering every phase (brief.
giovanni
AI Chief of Staff runtime: 4-layer memory with hard limits, daily digest with drift detection, stakeholder trajectories, invisible shadow hypotheses, adversarial-default review, and a governance lint that fails the build on contradictions. State lives in your repo; the mechanism lives here.