02-architect
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
- 03-planSkill
- 04-buildSkill
- 05-validateSkill
- 06-orchestrateSkill
- 07-maintainSkill
- 08-shipSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 28
Every structural claim must be checkable against aegis ast build output later.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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
SKILL-02: ARCHITECT (Master Skill)
Purpose
Turn a frozen scope into a frozen architecture: system design, database, security - the three documents every later skill trusts.
Sub-Skills
| ID | File | Purpose | Gate |
| 02a | 02a-system-design.md | System architecture + ADRs | SACRED G1: arch freeze |
| 02b | 02b-database.md | Schema, migrations, API contracts | destructive-migration review |
| 02c | 02c-security.md | STRIDE/OWASP threat model | SACRED G2: security sign-off |
Shared Rules
- Contracts are CODE, not prose: TS interfaces, stub exports, OpenAPI, numbered migrations. They merge to the base branch BEFORE any slice (N1).
- Every structural claim must be checkable against
aegis ast buildoutput later. No architecture the graph can't verify. - Anti-fragility: DAG only (the CLI detects cycles, exit 8), no God Objects, explicit over implicit, fail-safe defaults.
Routing
01c -> 02a -> [SACRED G1] -> 02b -> 02c -> [SACRED G2] -> 03a
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.