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/AppleCG/devflowWrote 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/applecg/devflow/devflow)<a href="https://agentmods.dev/plugins/applecg/devflow/devflow"><img src="https://agentmods.dev/badge/plugins/applecg/devflow/devflow/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/applecg/devflow/devflow"><img src="https://agentmods.dev/badge/plugins/applecg/devflow/devflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
devflow 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": "devflow",
"version": "1.0.0",
"description": "Full-lifecycle AI development workflow — fuses grill-with-docs (Matt Pocock) + OpenSpec (Fission-AI) + superpowers (obra) into one disciplined pipeline. Three modes: Design (quick-grill → spec-lite), Build (grill → spec → plan → isolate → enhanced-apply → review → archive), Fix (diagnose → apply → verify → archive).",
"author": "DevFlow",
"license": "MIT",
"repository": "https://github.com/user/devflow",
"keywords": ["devflow", "workflow", "spec-driven", "tdd", "grill", "design", "development"],
"skills": [
{
"name": "devflow",
"description": "Route to the right mode (design/build/fix) and enforce the full development pipeline. Auto-detects whether you're discussing design, building features, or fixing bugs.",
"path": "skills/devflow/SKILL.md"
}
],
"hooks": {
"SessionStart": [
{
"prompt": "DevFlow is active. Before any action, analyze the user's intent: Are they discussing/designing a solution (→ Design mode)? Are they building a feature or implementing a change (→ Build mode)? Are they reporting a bug or unexpected behavior (→ Fix mode)? Route to the devflow skill accordingly. All artifacts go to devwork/ directory. Templates are in skills/devflow/templates/.",
"skills": ["devflow"]
}
]
}
}
What it installs
The manifest is a name and a version. 1 skill travel with it, and installing the plugin installs all of them — 53 tokens a session between them. Each is measured on its own page, and each can be installed alone.
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 · 25 lines scan A 5a58cda6a37d
devflow is a plugin published in the GitHub repository AppleCG/devflow (8 stars, last pushed 3mo 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
agent-alchemy-tdd-tools
Agent Alchemy TDD Tools — Test Driven Development tools for AI agents.
superpowers-cc-to-codex
Codex-backed fork of seven Superpowers workflows: brainstorming, planning, implementation, code review, debugging, TDD, and branch completion.
implementation-planner
Structured implementation planning, execution, and TDD workflow for Claude Code. Create plans with Opus, execute with Sonnet, enforce TDD discipline.
auto-pilot
Long-cycle coding workflow plugin - Structured state machine with TDD-driven milestone execution and deterministic gates for sustained AI coding sessions.
nw
nWave: AI-powered workflow framework — 23 agents, 98+ skills, TDD enforcement, and wave-based development methodology for Claude Code.
atdd
Acceptance Test Driven Development for Claude Code. Enforces the ATDD methodology: write Given/When/Then specs first, generate a project-specific test pipeline, maintain two test streams (acceptance + unit). Inspired by Robert C. Martin's acceptance test approach from empire-2025.