mogui-ADE-orchestrator / master-ops
CLAUDE.md22 starsChanged 4 months agoMITView on GitHub
In this repository4 other files it gives its agents.
- AGENTS.mdAGENTS.md
- master-ops/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- delivery-gateSkill
The file
We split this CLAUDE.md into the rules it gives an agent
2 rules. About 0 are common, 1 is distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
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
After compaction, clear, or session recovery, first reload issue-tracker context and re-check active tracks before continuing.
- Very specific: line 15
Default master model identifier to measure at boot: {{MODEL_ID}}
≈ “Common” is an estimate: at least 1 in 5 of the 27,641 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
Master Operations Card ({{WORKSPACE_NAME}})
- This repository is the workspace/orchestrator operations layer for
{{WORKSPACE_NAME}}. Do not load repository-level coding rules globally here; each product repo owns its own code rules. - Workspace root:
{{WORKSPACE_ROOT}} - Operations repository:
{{OPS_REPO}} - Workspace repositories:
{{REPO_LIST}} - Master operations SSOT:
docs/MASTER-OPERATIONS.md - Role state SSOT:
docs/runbooks/role-state.md - Orca docs grounding:
docs/orca-docs-grounding.md; never guess Orca flags. - Execution state belongs in the issue tracker. Plans, designs, closed decisions, and durable runbooks belong in Git.
- After compaction, clear, or session recovery, first reload issue-tracker context and re-check active tracks before continuing.
- Sensitive lanes such as auth, permission, credentials, production data, and secrets should be delegated to a dedicated security or operations session. The master coordinates and verifies; it does not improvise sensitive implementation.
- When speaking to the workspace owner, expand internal vocabulary: refer to tracker issues by title with the ID in parentheses, never by bare ID, and give charter terms such as Role Lock or dispatch gate one plain clause of explanation on first use in a conversation. The owner has not read this repository.
- Times are written to the minute, anchored to one named event, and never masked; see §7. Records.
- Default master model identifier to measure at boot:
{{MODEL_ID}} - Context-quality monitor namespace:
{{MONITOR_NS}}
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.

