workspace-maintenance
Skill2 starsChanged 56 days agoMITView on GitHub
Maintain the Codex Workspace safely across docs, scripts, caches, and repo-level conventions
In this repository10 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .github/copilot-instructions.mdCopilot instructions
- agent-tooling-doctorSkill
- quality-gateSkill
- repo-onboardingSkill
- runtime-triageSkill
- security-checkSkill
- ssh-keychain-accessSkill
- typescript-reviewSkill
- workspace-quality-gateSkill
The file
We split this skill into the rules it gives an agent
10 rules. About 0 are common, 7 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈7
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
- Distinctive: line 8
Use this skill when the task is about improving the workspace itself rather than a single child repo.
- Distinctive: line 12
Keep the workspace predictable, low-duplication, and easy for Codex or other local agents to navigate.
- Very specific: line 16
Read AGENTS.md and the relevant docs in docs/.
- Very specific: line 17
Run tools/scripts/doctor-workspace.sh before changing shared setup assumptions.
- Distinctive: line 18
Prefer workspace-native scripts and templates over ad hoc one-off layouts.
- Distinctive: line 19
Keep repo installs local to each repo.
- Very specific: line 20
When a reviewed reference appears in tools/ref/, extract the pattern into tracked workspace code, docs, templates, or skills rather than …
- Distinctive: line 34
Do not make experimental orchestration layers mandatory for the whole workspace.
- Distinctive: line 35
Do not centralize dependencies across unrelated repos.
- Distinctive: line 36
Prefer small, inspectable tracked improvements over hidden runtime magic.
≈ “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
Workspace Maintenance
Use this skill when the task is about improving the workspace itself rather than a single child repo.
Goal
Keep the workspace predictable, low-duplication, and easy for Codex or other local agents to navigate.
Default workflow
- Read
AGENTS.mdand the relevant docs indocs/. - Run
tools/scripts/doctor-workspace.shbefore changing shared setup assumptions. - Prefer workspace-native scripts and templates over ad hoc one-off layouts.
- Keep repo installs local to each repo. Share caches, not installs.
- When a reviewed reference appears in
tools/ref/, extract the pattern into tracked workspace code, docs, templates, or skills rather than adding the reference as a dependency.
Useful commands
tools/scripts/doctor-workspace.sh
tools/scripts/doctor-agent-tooling.sh
tools/scripts/setup-workspace-profile.sh --list
tools/scripts/sync-reference-snapshots.sh --list
tools/scripts/update-all.sh --list-groupsGuardrails
- Do not make experimental orchestration layers mandatory for the whole workspace.
- Do not centralize dependencies across unrelated repos.
- Prefer small, inspectable tracked improvements over hidden runtime magic.
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.

