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/MageByte-Zero/spec-superflowWrote 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/magebyte-zero/spec-superflow/gemini-extension)<a href="https://agentmods.dev/plugins/magebyte-zero/spec-superflow/gemini-extension"><img src="https://agentmods.dev/badge/plugins/magebyte-zero/spec-superflow/gemini-extension/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/magebyte-zero/spec-superflow/gemini-extension"><img src="https://agentmods.dev/badge/plugins/magebyte-zero/spec-superflow/gemini-extension.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
spec-superflow 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 22d 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": "spec-superflow",
"description": "Lean spec workflow: direct or planned execution with evidence-based completion",
"version": "2.0.1",
"contextFileName": "GEMINI.md"
}
What ships with it
60 files beside gemini-extension.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.
- assets/icon.svg 342 B
- assets/magebyte-wechat.jpg 39 KB
- scripts/check-update.mjs 3.3 KB runs code
- scripts/check-version-consistency.mjs 5.7 KB runs code
- scripts/ensure-branch.mjs 12 KB runs code
- scripts/get-config 919 B
- scripts/guard/checks/artifacts-exist.mjs 1.3 KB runs code
- scripts/guard/checks/contract-current.mjs 1.1 KB runs code
- scripts/guard/checks/contract-fresh.mjs 1.2 KB runs code
- scripts/guard/checks/dp-gate-passed.mjs 1.2 KB runs code
- scripts/guard/checks/dp3-approved.mjs 623 B runs code
- scripts/guard/checks/execution-plan-ready.mjs 1.5 KB runs code
- scripts/guard/checks/execution-reviews-passed.mjs 2.4 KB runs code
- scripts/guard/checks/schema-valid.mjs 1.9 KB runs code
- scripts/guard/checks/specs-merged.mjs 1.9 KB runs code
- scripts/guard/checks/tasks-checkbox-format.mjs 983 B runs code
- scripts/guard/checks/tasks-complete.mjs 1.0 KB runs code
- scripts/guard/checks/tests-passing.mjs 1.2 KB runs code
- scripts/guard/guard.mjs 17 KB runs code
- scripts/infer-workflow.mjs 4.6 KB runs code
- scripts/install-amazon-q.mjs 347 B runs code
- scripts/install-cline.mjs 319 B runs code
- scripts/install-codebuddy.mjs 818 B runs code
- scripts/install-continue.mjs 335 B runs code
- scripts/install-cursor.mjs 7.8 KB runs code
- scripts/install-git-hooks.mjs 2.5 KB runs code
- scripts/install-kiro.mjs 318 B runs code
- scripts/install-pi.mjs 345 B runs code
- scripts/install-qoder.mjs 320 B runs code
- scripts/install-qwen.mjs 320 B runs code
- scripts/install-roocode.mjs 323 B runs code
- scripts/install-windsurf.mjs 335 B runs code
- scripts/install-zcode.mjs 7.8 KB runs code
- scripts/lib/change-recovery.mjs 14 KB runs code
- scripts/lib/cmd-audit.mjs 4.5 KB runs code
- scripts/lib/cmd-checkpoint.mjs 3.6 KB runs code
- scripts/lib/cmd-config.mjs 2.7 KB runs code
- scripts/lib/cmd-debug.mjs 2.9 KB runs code
- scripts/lib/cmd-doctor.mjs 10 KB runs code
- scripts/lib/cmd-execution.mjs 12 KB runs code
- scripts/lib/cmd-finish.mjs 11 KB runs code
- scripts/lib/cmd-handoff.mjs 3.4 KB runs code
- scripts/lib/cmd-inject.mjs 14 KB runs code
- scripts/lib/cmd-install-amazon-q.mjs 500 B runs code
- scripts/lib/cmd-install-cline.mjs 478 B runs code
- scripts/lib/cmd-install-codebuddy.mjs 22 KB runs code
- scripts/lib/cmd-install-continue.mjs 490 B runs code
- scripts/lib/cmd-install-cursor.mjs 518 B runs code
- scripts/lib/cmd-install-kiro.mjs 474 B runs code
- scripts/lib/cmd-install-pi.mjs 472 B runs code
- scripts/lib/cmd-install-qoder.mjs 478 B runs code
- scripts/lib/cmd-install-qwen.mjs 479 B runs code
- scripts/lib/cmd-install-roocode.mjs 487 B runs code
- scripts/lib/cmd-install-windsurf.mjs 490 B runs code
- scripts/lib/cmd-install-workbuddy.mjs 17 KB runs code
- scripts/lib/cmd-install-zcode.mjs 508 B runs code
- scripts/lib/cmd-isolate.mjs 1.4 KB runs code
- scripts/lib/cmd-list.mjs 2.8 KB runs code
- scripts/lib/cmd-resume.mjs 142 B runs code
- scripts/lib/cmd-runtime.mjs 2.7 KB runs code
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.
- 22d ago Changed 4b970ad64f61
- 24d ago Changed 295d202f14f7
- 1mo ago First seen · 7 lines scan A 48101384e523
spec-superflow is a plugin published in the GitHub repository MageByte-Zero/spec-superflow (864 stars, last pushed 14d 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 2026-09-16.
Other plugins, from other repositories
superpowers-zh
A Chinese-language plugin containing 20 AI coding skills, including translated and original workflows, for several coding-agent tools. Its listed topics include testing-driven development, debugging, and development practices.
t-tools
DDD-driven development skills, sub-agents and workflow commands for Rust, React, miniapp, Flutter, Chrome Extension, and Shopify App projects.
azure-agent-skills
A curated collection of production-ready agentic skills for Microsoft Azure development. Installs 193+ skills covering Azure compute, data, AI/ML, networking, security, and management services. Built from Microsoft Learn documentation and following the Agent Skills open standard.
coding-coach
A collection of skills for non-developers who want to turn an idea into a launched product. It covers engineering, product work, interface design, writing, and deployment.
humanizer
Rewrite AI-sounding text so it reads like the writer without changing what it says.
nextjs
Official Next.js skills: adopt and optimize Cache Components, adopt Partial Prefetching, and verify runtime behavior against a running dev server.