ordo / templates
CLAUDE.md0 starsChanged 28 days agoMITView on GitHub
- Commits. <Commit only when told, each time. | Committing is allowed.> <- Each rule the user states for this repository, one line.> - docs/dev/building.md: how to build and test, and what the green check is. Read it before running or reporting any build. - docs/dev/change-standard.md: how a change is made and reported. Every brief points here first. <- docs/dev/design-principles.md and the pages under docs/dev/coding-standards/: how code is designed and written.> <- docs/dev/ui-standard.md: how the user interface is built.> -…
In this repository16 other files it gives its agents.
- code-commentsSkill
- diagnoseSkill
- grillSkill
- landSkill
- ordo-helpSkill
- ordo-initSkill
- paperSkill
- plan-orchestrationSkill
- plan-retroSkill
- planSkill
- refuteSkill
- repo-setupSkill
- roadmapSkill
- session-retroSkill
- specSkill
- writingSkill
The file
Files
Working conventions for <name>
<One paragraph: what the repository is, its language and build system, and its main parts.>
<!-- ordo:shared-rules begin --><!-- ordo:shared-rules end -->Project rules
- Commits. <Commit only when told, each time. | Committing is allowed.> <- Each rule the user states for this repository, one line.>
Read before you act
docs/dev/building.md: how to build and test, and what the green check is. Read it before running or reporting any build.docs/dev/change-standard.md: how a change is made and reported. Every brief points here first. <-docs/dev/design-principles.mdand the pages underdocs/dev/coding-standards/: how code is designed and written.> <-docs/dev/ui-standard.md: how the user interface is built.>docs/dev/prose-standard.md: how every comment, page and message is written.docs/roadmap.md: what is open and in what order. Answer "what is left?" from this file, never from memory.docs/glossary.md: the terms this repository and the skills it is set up with use in a sense of their own, each defined once.docs/adr/: the decisions that bind work after the plan that made them closes, with the alternatives rejected. A step whose text or brief contradicts an ADR is a rule clash.
Build
<the commands from docs/dev/building.md, one per line, each with a comment>Skills
skills-lock.json lists the project skills; npx skills experimental_install restores them into .agents/skills/ with links under .claude/skills/. The plan skills are installed per user and are not listed here.
<- <skill>: <its description, one line>.>
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.