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/alexsds/ade-workflowWrote 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/alexsds/ade-workflow/ade-workflow)<a href="https://agentmods.dev/plugins/alexsds/ade-workflow/ade-workflow"><img src="https://agentmods.dev/badge/plugins/alexsds/ade-workflow/ade-workflow/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/alexsds/ade-workflow/ade-workflow"><img src="https://agentmods.dev/badge/plugins/alexsds/ade-workflow/ade-workflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
ade 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": "ade",
"description": "Agent-Driven Engineering: Anthropic's 3-agent harness with pluggable rubrics and testing tools for long-running app development",
"version": "0.1.0",
"author": {
"name": "ADE Contributors"
},
"repository": "https://github.com/alexsds/ade-workflow",
"homepage": "https://github.com/alexsds/ade-workflow#readme",
"license": "MIT",
"keywords": [
"agents",
"harness",
"planner",
"generator",
"evaluator",
"rubrics",
"testing"
]
}
What it installs
The manifest is a name and a version. 3 skills, 4 commands, 2 agents, 1 hook, 1 MCP server travel with it, and installing the plugin installs all of them — 762 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill ade-evaluation A 115 tokens
- Skill ade-planning A 115 tokens
- Skill ade-generation A 78 tokens
- Command execute A 12 tokens
- Command plan A 17 tokens
- Command done A 6 tokens
- Command status A 8 tokens
- Agent ade-evaluator A 213 tokens
- Agent ade-generator A 198 tokens
- Hook SessionStart A not measured
- MCP server playwright A not measured
What ships with it
1 file beside plugin.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 First seen · 21 lines scan A 7ea7210e2b35
ade is a plugin published in the GitHub repository alexsds/ade-workflow (1 stars, last pushed 6mo 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 2026-08-31.
Other plugins, from other repositories
mean-tester
Mean tests another agent through readonly probes or marked actions on admitted test installations, checks owned approvals and state, and reports a computed ship verdict. It files nothing and fixes nothing.
optimus
Sets up your project for effective AI-assisted development — optimized CLAUDE.md files, effective coding guidelines, formatter hooks, built-in code-quality agents, TDD and test coverage, all tailored to your actual codebase.
harnessay
Profile Claude Code and Codex transcripts: context budget reports, before/after comparisons, source evidence, and skill regression tests. Local-only, stdlib-only.
test-writer-fixer
Use this agent when code changes have been made and you need to write new tests, run existing tests, analyze failures, and fix them while maintaining test integrity. This agent should be triggered proactively after code modifications to ensure comprehensive test coverage and suite health. Examples:\n\n \nContex.
nova
AI Agent Ops framework for Claude Code — independent evaluator, adversarial review, and pre-commit quality gate for AI-generated code.
full-audit
One command that audits a whole repository: dispatches every relevant audit lane in parallel, proves the repo's own gates actually fail, and returns one evidence-backed report. Reports only — never fixes.