about-sage
Skill0 starsChanged 5 months agoMITView on GitHub
Brief overview of the Sage SDLC agent system and each agent's role. Use when the user asks what Sage is, how it works, or about Sage agents.
In this repository15 other files it gives its agents.
- Agents.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .cursor/rules/sage-system.mdcCursor rule
- sage-architectSkill
- sage-buildSkill
- sage-designSkill
- sage-devopsSkill
- sage-engineerSkill
- sage-handoffSkill
- sage-initSkill
- sage-orchestratorSkill
- sage-planSkill
- sage-qaSkill
- sage-releaseSkill
- sage-statusSkill
The file
We split this skill 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 9
When invoked, give a short overview of Sage, then the agent table below.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill 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
About Sage
When invoked, give a short overview of Sage, then the agent table below. Keep it brief. Do not dump Agents.md or phase workflows unless asked.
What Sage is
Sage is an SDLC agent orchestration system. Specialized agents run phases of software delivery (plan, design, architect, build, qa, devops, release) in order. An orchestrator routes work by workflow profile, writes handoffs between phases, and stores run artifacts under runs/<run-id>/. Each agent reads Agents.md first, then its role file in agents/.
Agents
| Agent | What it does | Primary role |
| Sage Orchestrator | Runs the pipeline, picks profile, enforces gates | Orchestrate |
| Sage Planner | Clarifies requirements; plan.md in full or steps format | Plan |
| Sage Designer | UI/UX specs, components, asset structure | Design |
| Sage Architect | Schemas, boundaries, deployment impact, test strategy | Architect |
| Sage Engineer | Full-stack implementation, tests, wiring | Build |
| Sage QA | Tests, lint, verification against plan | Verify |
| Sage DevOps | Docker, CDN sync, nginx, deploy prep | Package |
| Sage Release | Commits, branches, PRs | Ship |
| Sage Status | Reports run phase, profile, gates, next command | Status |
| Sage Handoff | Writes or validates phase handoff documents | Handoff |
| Sage Init | Bootstraps ./runs/ and project Sage config | Init |
Slash commands
Each phase agent maps to a /sage-* command. Use /sage-plan steps when the problem is unfamiliar (plain breakdown). Use /sage-plan or /sage-plan full for the handoff-ready spec. Start a run with /sage-orchestrator.
Skills live in .cursor/skills/ and must match the Skills mirror table in Agents.md. One skill folder per registry row; no orphan skills.
For profile paths and global rules, point to Agents.md and workflows/profiles.md.
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.

