loadout
CLAUDE.md2 starsChanged 7 months agoMITView on GitHub
- Deletes or force-pushes
- Commits and pushes
In this repository2 other files it gives its agents.
- docs-architectSkill
- loadout-system-designSkill
The file
We split this CLAUDE.md into the rules it gives an agent
5 rules. About 0 are common, 2 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- could be automatic: a setting could enforce it
- Very specific: line 8
NEVER call VSCode APIs (vscode.*, fs.*) from inside the webview — all filesystem ops go through postMessage to the extension host
- Distinctive: line 9
NEVER use git add -A or git add .
- Distinctive: line 10
NEVER git push --force to main
- Very specific: line 11
NEVER skip pre-commit hooks (--no-verify)
- Very specific: line 12
NEVER use --amend without explicit user request
≈ “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
Loadout — Project Rules
Context
VSCode extension that manages Claude Code agents, skills, and profiles as swappable loadouts.
The extension host (Node.js/CommonJS) communicates with an Angular 21 webview via postMessage.
Hard NOs
- NEVER call VSCode APIs (
vscode.*,fs.*) from inside the webview — all filesystem ops go throughpostMessageto the extension host - NEVER use
git add -Aorgit add .— always stage specific files by name - NEVER
git push --forceto main - NEVER skip pre-commit hooks (
--no-verify) - NEVER use
--amendwithout explicit user request
Conventions
- Documentation language: english
- Code language: english
- Extension host files (
extension.js,data.js) use CommonJS — no ESM, noimport
Process
- Branches:
feature/<slug>→main - Commits: conventional format, imperative mood, no AI attribution
- Build:
cd webview && npm run buildbefore committing UI changes
Where context comes from
- Always-loaded rules:
.claude/rules/*.mdwithoutpaths:frontmatter — load every session - Auto-loaded rules:
.claude/rules/*.mdwithpaths:frontmatter — load only when Claude reads matching files - Full docs:
docs/*.md— read on-demand when detail is needed beyond what the rules carry - Governance:
docs/README.md— doc-folder rules, story/bug workflows
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.

