ai-workflow-playbooks
CLAUDE.md2 starsChanged 6 months agoMITView on GitHub
This repository contains structured engineering playbooks designed for AI coding agents. Each playbook guides agents through a specific phase of the software delivery pipeline with executable workflows, exit criteria, and anti-pattern guards. DISCOVER → ARCHITECT → CONSTRUCT → HARDEN → VALIDATE → RELEASE → OPERATE Each stage gates the next: an agent must satisfy a stage's exit criteria before proceeding. Skipping stages is an anti-pattern; a guardian review is required at HARDEN and VALIDATE.
In this repository10 other files it gives its agents.
The file
We split this CLAUDE.md into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 27
All content is plain Markdown for maximum agent compatibility
≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
AI Workflow Playbooks - Project Context
This repository contains structured engineering playbooks designed for AI coding agents. Each playbook guides agents through a specific phase of the software delivery pipeline with executable workflows, exit criteria, and anti-pattern guards.
Repository Layout
playbooks/- 21 operational playbooks organized by pipeline stageskills/- 10 agent skills loaded on demand to augment the playbooksguardians/- 4 specialist review personas (architecture, quality, security, operations)runbooks/- 5 cross-cutting operational checklistslifecycle/- Pipeline stage documentation and hooksdocs/- Platform-specific setup guides.claude/commands/- 7 pipeline slash commands
Pipeline Stages
DISCOVER → ARCHITECT → CONSTRUCT → HARDEN → VALIDATE → RELEASE → OPERATE
Each stage gates the next: an agent must satisfy a stage's exit criteria before proceeding. Skipping stages is an anti-pattern; a guardian review is required at HARDEN and VALIDATE.
Conventions
- Playbook files are named
PLAYBOOK.md - Each playbook has: Objective, Triggers, Workflow, Guardrails, Exit Criteria, Anti-Patterns
- Guardians are specialist personas loaded for targeted review
- Runbooks are reference checklists loaded on demand
- All content is plain Markdown for maximum agent compatibility
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.