Super Simple Software Factory workflow
super-simple-software-factory
Repeatable agent-plus-code workflows in one skill: deterministic Python runs the phases while agents work as nodes inside the process
- 966 ★ on the repository
- Last commit
- MIT
Extended access
Why this level
- Launches coding agents and scripts in your repository
- Agents edit files and run commands
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add workflows/super-simple-software-factoryDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- Launches coding agents and scripts in your repository
- Agents edit files and run commands
This is third-party code. Review the repository files before installing.
What it does
Super Simple Software Factory moves control from the prompt into code. A Python script (ADW, AI Developer Workflow) owns the order of phases, retries and acceptance, while a coding agent does only the work inside one bounded phase: engineer, planner, builder, reviewer. Events are written to a SQLite trace that the interface reads. It is packaged as one skill that is stamped into any repository. Installation is by cloning: `git clone <repo> sssf`. MIT license, no releases.
Who it is for. For developers who need a repeatable result from an agent: the same phases and clarity about which step failed.
Good fit when
- You need reproducible workflows instead of one big request
- You need to see which phase the agent failed on
- You need an event trace in a database
Not a fit when
- You need a ready no-code process: here are Python scripts and setup
- You need a quick one-off fix: a factory is overkill
Example request
Run the factory on the task of adding a filter to the order list: planner, builder, reviewer, trace in SQLiteLimitations
The skill launches coding agents and Python scripts in your repository, so access is extended: agents edit files and run commands. Start with a test repository. There are no releases, and the branch contains only the skill itself while ready examples live in another branch.
How to disable. Delete the skill folder from the repository and the sssf clone.
FAQ
What is the idea?
Code owns sequencing, retries and acceptance, while the agent does only the work inside one phase.
How do I install it?
git clone from the repository link into the sssf folder, then follow the README.
Where is the trace written?
Events of each phase go to a SQLite database that the interface reads.
Discussion
No questions or reviews yet.
Related
WorkflowsA visual workflow builder for agents: draw a flow on a canvas and export it as skills and commands for Claude Code, Codex, Cursor and others
pydantic-deepagents
pydantic-deepagents (pydantic-deep)
An open-source terminal AI assistant and Python framework with a Docker sandbox, agent tools and subagents
A skill plus hooks that keep a coding agent on task and cut speculative defenses, unread checksums and scope creep
Loopy
Loopy (Loop Library)
A skill and library of ready agent loops: find, audit, repair, craft and run a repeatable workflow
A multi-agent harness that verifies results by artifacts: stop hooks, an independent judge and an event log for Claude Code, Codex, Cursor and more
An orchestrator for agents: the workflow is defined in code, every step is enforced, key points need human approval and decisions go into an immutable journal
Comparison with similar tools
Entries that share the main search query, and how they differ.
| Entry | Official | Repository stars | Main difference |
|---|---|---|---|
| Super Simple Software Factory (this entry) | no | 966 | |
| FlowGram | yes | 8,492 | a framework for an AI workflow editor for developers |
| Zeroshot | no | 1,950 | an agent graph where one implements and independent ones verify |
| dzhng/skills | no | 1,028 | a chain from idea to spec to implementation |
README in short
The README describes an agent-plus-code workflow packaged as one skill where Python runs the phases and agents work as bounded nodes. MIT license.