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.
/plugin marketplace add fusebase-dev/fusebase-flownpx agentmods add plugins/fusebase-dev/fusebase-flow/marketplacegit clone --depth 1 https://github.com/fusebase-dev/fusebase-flowGrade A, and why
fusebase-flow 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.
What it actually says
{
"name": "fusebase-flow",
"owner": {
"name": "FuseBase (Nimbus Web Inc.)"
},
"metadata": {
"description": "FuseBase Flow — the spec-to-deploy AI app-development framework for client-facing teams, packaged with FuseBase Apps domain skills."
},
"plugins": [
{
"name": "fusebase-flow",
"source": "./",
"description": "Two-agent (Product Owner + AI Developer) spec-to-deploy lifecycle for building internal and client apps with AI, plus FuseBase Apps domain skills. Repo-local, tool-portable, no SaaS.",
"version": "4.14.1",
"author": {
"name": "FuseBase (Nimbus Web Inc.)"
},
"homepage": "https://ai-dev.thefusebase.com/",
"repository": "https://github.com/fusebase-dev/fusebase-flow",
"license": "MIT",
"category": "workflow",
"keywords": [
"ai-coding-assistant",
"claude-code",
"ai-agents",
"product-owner",
"client-facing",
"spec-driven-development",
"fusebase"
],
"strict": true
}
]
}
What ships with it
1 file beside marketplace.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.
- yesterday First seen · 35 lines scan A afeb6731214f
fusebase-flow is a plugin published in the GitHub repository fusebase-dev/fusebase-flow (9 stars, last pushed 6d 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-toolkit
Plugin marketplace listing 4 plugins: agent-toolkit-core, agent-toolkit-agents, agent-toolkit-forge, agent-toolkit-craft.
vibeflow
Spec-driven development for AI agents. Define what to build, let the agent build it right. Vibeflow separates thinking from coding with specs, guardrails, and audits — grounded in your project's real patterns.
agent-toolkit-complete
Full stable skill catalog coverage for consumers who want everything (.
threnody
Local-first MCP meta-harness: routes, plans, and swarms multi-agent coding work — emitting tier-aware Dynamic Workflows on Claude Code — while the host shell executes via Agent/Task subagents.
code-discipline
Plugin marketplace listing 1 plugin: code-discipline.
code-discipline
Coding methodology for production-grade software development. Six principles: think before coding, verify reality, simplicity first, surgical changes, respect existing contracts, goal-driven execution.