Browse / General-purpose / ai-workflow
ai-workflow
brawblan
My AI coding workflow: Claude Code plugin, portable SKILL.md skills, global rules, and tips.
Open brawblan/ai-workflow → Checked against the four rules.
agent-frameworkagentsaillms
Works with any agent
ships AGENTS.md, the cross-tool instruction file.
In its own words
Cornerstone: a framework for agent-assisted software delivery, where checks decide that work is done.
Version 1.6.0. All 10 profiles are supported, and each generated check blocks.
This repo holds Cornerstone, its stone CLI, the cornerstone plugin skills, my personal agent rules, and tips. Read the docs at brawblan.github.io/ai-workflow.
What Cornerstone is
Cornerstone says how a human and an agent deliver software together. It is a set of written rules and a CLI that turns the rules into files for your repo.
- Stages and roles. The work moves through Intake, Shape, Plan, Build, Test, Verify, Review,
Deliver, and Learn. A shaper, a planner, an implementer, a tester, a reviewer, and an investigator do the work.
- Gates. A human approves the ticket, the plan, and the change. Only CI passes the checks gate.
- A code index.
stone-indexis a local index of the files in a repo. An agent asks it where a symbol is, and reads fewer files. The rule cut output tokens by 13 to 30 percent (D109). On one large multi-file task, M3, it cost 11 to 25 percent less (3 trials, no SE). Over all scenarios the cost saving is inside the noise (evidence). Guide: Use the code index. - Profiles. Ten profiles set the plan form and the gates for each type of work, from a spike to
a full project.
- A neutral core. The core never names a tool. An adapter turns it into files for one harness.
stone render writes those files into your repo.
Quoting 27% of the README. Read the rest on GitHub ↗
Read from the repository's git tree on 2026-08-17.