00-foundation
Skill0 starsChanged 29 days agoMITView on GitHub
In this repository10 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- 01-discoverSkill
- 02-architectSkill
- 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
4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
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 29
Brain protocol: read brain/context-window.md before any edit.
- Distinctive: line 31
Dual mode: every step lists the CLI command (Runtime mode) and the manual fallback (human runs command, pastes output).
- Distinctive: line 34
Determinism: never write timestamps into generated artifacts (A1.2).
- Distinctive: line 35
Honesty: if a step cannot be performed in the current environment level, say so explicitly and label outputs UNVERIFIED.
≈ “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-00: FOUNDATION (Master Skill)
Purpose
Set up Aegis in any repo, lock context, recover sessions, ingest existing codebases. Everything else in Aegis depends on this family being correct.
Sub-Skills
| ID | File | Purpose | Human gate |
| 00a | 00a-installer.md | One-command install, environment detection | Overwrite prompt only |
| 00b | 00b-context-lock.md | Setup interview + locked manifest | The interview itself |
| 00c | 00c-resume.md | Crash/session recovery with verified integrity | Integrity failure |
| 00d | 00d-brownfield.md | Reverse-discovery: brain FROM existing code | Inference confirmation |
| 00e | 00e-ask-aegis.md | Next-action advisor: ONE recommended step + evidence | Gate approval / loop escalation |
| 00f | 00f-aegis-guide.md | Interactive onboarding: agent does setup, explains, asks | Consent + autonomy choice |
Shared Rules (all sub-skills)
- Brain protocol: read
brain/context-window.mdbefore any edit; write outputs to the designated brain files; state changes ONLY via theaegisCLI. - Dual mode: every step lists the CLI command (Runtime mode) and the manual fallback (human runs command, pastes output). Never pretend enforcement exists in Manual mode.
- Determinism: never write timestamps into generated artifacts (A1.2).
- Honesty: if a step cannot be performed in the current environment level, say so explicitly and label outputs UNVERIFIED.
Routing
- greenfield: 00a -> 00b -> 01a
- brownfield: 00a -> 00b -> 00d -> (01a for new features | 07a for hardening)
- crash/interruption: 00c -> checkpoint target
- unsure / blocked / cold session: 00e (ask-aegis) -> the one legal next action
- "guide me" / first contact / knows nothing: 00f (aegis-guide) -> configured + understood setup
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.