04-build
Skill0 starsChanged 29 days agoMITView on GitHub
In this repository10 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- 00-foundationSkill
- 01-discoverSkill
- 02-architectSkill
- 03-planSkill
- 05-validateSkill
- 06-orchestrateSkill
- 07-maintainSkill
- 08-shipSkill
The file
We found no rules to list in this file: it reads as prose or reference rather than instructions.
Files
SKILL-04: BUILD (Master Skill)
Purpose
Build the planned slices - in parallel where the platform allows - with correctness enforced by git and the compiler, never by LLM opinion.
Sub-Skills
| ID | File | Purpose |
| 04a | 04a-parallel-build.md | Team composition + slice spawning in worktrees |
| 04b | 04b-integration-orchestrator.md | DAG-ordered merges through the oracle |
| 04c | 04c-integration.md | Contract validation, migrations, integration tests |
The Five Non-Negotiables (CLI-enforced)
| # | Rule | Enforcement |
| N1 | Contract PR merges before any agent spawns | aegis transition 04a refuses |
| N2 | Worktree-per-slice, always | aegis slice create (outside repo, A1.5) |
| N3 | Merge oracle = real merge + tsc + contract diff | aegis merge check exit 9 |
| N4 | Platform capabilities verified with evidence | Appendix C matrix |
| N5 | Lane caps are the only swarm throttle | aegis slice create refuses at cap |
Routing
03b -> [N1] -> 04a -> 04b -> 04c -> [SACRED G3] -> 05a
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.