edit-mode
Skill0 starsChanged 7 months agoMITView on GitHub
Governance unlock/lock cycle. Use /sagex:edit-mode to unlock rules, skills, hooks, approved sources for modification. Use /sagex:lock to re-engage. Only Sage can invoke.
In this repository6 other files it gives its agents.
- audit-loopSkill
- brain-harnessSkill
- coding-harnessSkill
- notebooklm-researchSkill
- research-gateSkill
- worktree-isolationSkill
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
- Distinctive: line 11
Only when Sage explicitly requests to modify governance components (rules, skills, hooks, configs).
- Distinctive: line 17
Read back every change for confirmation
- Very specific: line 35
All changes logged to .claude/edit_mode_log.md with timestamp
- Distinctive: line 36
If session ends without /sagex:lock, next session starts locked (fail-safe)
≈ “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
Edit Mode — Governance Unlock/Lock
When to Use
Only when Sage explicitly requests to modify governance components (rules, skills, hooks, configs).
Protocol
- Sage invokes /sagex:edit-mode
- Confirm: "Edit mode active. What do you want to change?"
- Make ONLY the changes Sage specifies
- Read back every change for confirmation
- Sage invokes /sagex:lock to re-engage
What unlocks
- config/approved_sources.json
- config/notebook_assignments.json
- rules/ directory
- skills/ directory
- hooks/ directory
- agents/ directory
What stays locked
- The edit-mode command itself
- The lock command
- Hook enforcement (hooks still fire)
Safety
- Edit mode does NOT disable hooks — it enables modification of files hooks READ
- All changes logged to .claude/edit_mode_log.md with timestamp
- If session ends without /sagex:lock, next session starts locked (fail-safe)
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.

