A plugin containing three skills for governing, operating, and communicating about an AI-agent engineering repository. It provides guidance for repository safeguards, day-to-day operations, and clear technical documents and diagrams.

Use it to audit or add repository guardrails, operate an agent fleet, and write items such as design documents, runbooks, handoffs, READMEs, tutorials, and API references.

It brings related instructions for controls, operations, and engineering communication into one installable package. This helps keep the repository safer to run and easier for engineers to understand.

mage — Plugin by davisjam

Install

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.

Claude Code

/plugin marketplace add davisjam/model-based-agentic-software-engineering

agentmods

npx agentmods add plugins/davisjam/model-based-agentic-software-engineering/mage

Clone the repo

git clone --depth 1 https://github.com/davisjam/model-based-agentic-software-engineering

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

mage 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.

plugin/mage/.claude-plugin/plugin.json · 22 lines

What it actually says

{
  "name": "mage",
  "description": "The mage toolkit — the Davis AI-First Engineering Method plus the control catalogue, packaged as installable skills. Ships three partner skills: self-governance (harden — audit a repo for missing guardrails, or convert a recurring failure into a durable control), self-operations (operate — run the agent-fleet substrate; route a break to its fix, and escalate a recurring one to self-governance), and self-communicate (communicate — write and diagram engineer-facing docs well: rhetoric, the Diátaxis register, a house lexicon, and a prose+diagram audit).",
  "version": "0.1.0",
  "license": "MIT",
  "author": {
    "name": "James C. Davis, PhD",
    "email": "[email protected]"
  },
  "homepage": "https://davisjam.github.io/agent-governance-mechanisms/",
  "repository": "https://github.com/davisjam/agent-governance-mechanisms",
  "keywords": [
    "governance",
    "agents",
    "ai-engineering",
    "linting",
    "code-review",
    "guardrails",
    "mbse"
  ]
}

Changes

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 810b84d4f2d0

Subscribe to this mod's changes

mage is a plugin published in the GitHub repository davisjam/model-based-agentic-software-engineering (18 stars, last pushed yesterday), 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.

Backend and APIs Learning and teaching agentic-coding softwareengineering vibecoding

manifest-dev-tools

Tools for prompts and PRs alongside the manifest workflow. Includes collaborative PR walkthroughs, autonomous PR review with independent per-gate manifest verification, author-side PR babysitting that forwards /do verification policy, gap-calibrated prompt engineering, cross-boundary context handoff, incremental…

doodledood/manifest-dev · not measured

tsk-help

Teaches Claude core tsk commands for delegating development tasks to AI agents in sandboxed containers.

dtormoen/tsk-tsk · not measured

cc-code

极简开发工作流系统。角色串行(PM→Architect→Dev→QA) + L0L4 文件分层的状态机循环。/cc-code:init 三轨初始化（新建/已最新/旧版升级迁移，全程零删除），13 skill + 3 配套 agent，含 /cc-code:plan-prd-feature 增量迭代规划、/cc-code:whole-qa 全量验收修复闭环与 /cc-code:experience-summary 项目级经验沉淀（references 按需读取）。⭐0.10.0 codegraph 全静默深度集成（15/15 能力：静默建索引 + affected 精准回归 + impact 真爆炸半径 + 角色权限矩阵，人零心智负.

weiyi88/cc-code · not measured

clawness

Puts the right rules in context on every prompt, automatically — built for full-stack developers moving across frontend, backend, and SQL in one session, researchers working in bare or LaTeX-only directories, and teams who want adversarial review (security red/blue team, code critic) before merge. 222 rules across 30…

fullymiddleaged/Clawness · not measured

study-ios

Plugin marketplace listing 1 plugin: swift-study-skills.

ITlearning/study-ios · not measured

swift-study-skills

Swift/iOS learning skills - Socratic tutoring, adaptive quizzes, and note-taking.