vnx-orchestration / T2
CLAUDE.md63 starsChanged 9 days agoMITView on GitHub
Purpose: testing, integration, validation. For this feature, T2 is responsible for proving that headless observability signals are real, not just structurally present. This prints the skill command and full prompt. Execute those instructions as your task. Your report must always include:
In this repository56 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- .claude/terminals/T0/CLAUDE.mdCLAUDE.md
- .claude/terminals/T1/CLAUDE.mdCLAUDE.md
- .claude/terminals/T3/CLAUDE.mdCLAUDE.md
- api-developerSkill
- architectSkill
- backend-developerSkill
- control-centreSkill
- data-analystSkill
- database-engineerSkill
- debuggerSkill
- excel-reporterSkill
- fabric-referenceSkill
- featureplan-kickoffSkill
- frontend-developerSkill
- horizonSkill
- intelligence-engineerSkill
- monitoring-specialistSkill
- panelSkill
- performance-profilerSkill
- plannerSkill
- pmSkill
- python-optimizerSkill
- quality-engineerSkill
- refactor-safeSkill
- reviewerSkill
- security-engineerSkill
- supabase-expertSkill
- t0-orchestratorSkill
- test-engineerSkill
- vnx-managerSkill
- api-developerSkill
- architectSkill
- backend-developerSkill
- data-analystSkill
- database-engineerSkill
- debuggerSkill
- excel-reporterSkill
- fabric-referenceSkill
- featureplan-kickoffSkill
- frontend-developerSkill
- horizonSkill
- intelligence-engineerSkill
- monitoring-specialistSkill
- performance-profilerSkill
- plannerSkill
- pmSkill
- python-optimizerSkill
- quality-engineerSkill
- refactor-safeSkill
- reviewerSkill
- security-engineerSkill
- supabase-expertSkill
- t0-orchestratorSkill
- test-engineerSkill
- vnx-managerSkill
The file
We split this CLAUDE.md into the rules it gives an agent
8 rules. About 0 are common, 5 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
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
- Very specific: line 7
Write your report to $VNX_DATA_DIR/unified_reports/ using the absolute runtime path from environment.
- Very specific: line 10
When your first message is load-dispatch <dispatch-id>, read the dispatch bundle from disk:
- Very specific: line 43
All shell changes must pass bash -n
- Distinctive: line 48
Prefer exact commands over prose summaries
- Distinctive: line 49
If CI matters, say whether you checked local-only or remote GitHub state
- Distinctive: line 50
If path resolution or worktree behavior is relevant, test both where feasible
- Distinctive: line 51
If closure depends on your numbers, make them independently checkable by T0
- Distinctive: line 52
Call out explicitly when smoke, integration, certification, PTY behavior, or live-worker coverage is still missing
≈ “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
T2 Worker Terminal (Track B)
Purpose: testing, integration, validation. For this feature, T2 is responsible for proving that headless observability signals are real, not just structurally present.
Startup
- Your dispatch arrives in this conversation. Execute only the scoped work in that dispatch.
- Write your report to
$VNX_DATA_DIR/unified_reports/using the absolute runtime path from environment.
load-dispatch Activation
When your first message is load-dispatch <dispatch-id>, read the dispatch bundle from disk:
python scripts/load_dispatch.py --dispatch-id <dispatch-id>This prints the skill command and full prompt. Execute those instructions as your task.
Required Report Discipline
Your report must always include:
- exact verification commands
- exact test file names
- actual pass/fail totals from what you ran
- which run scenarios you exercised:
- success
- timeout
- no-output hang
- interrupted run
- any CI, path, integration, or environment caveats
## Open Itemssection, even when empty
Do NOT:
- quote test totals you did not personally verify
- refer to non-existent test files
- mark integration "done" if only unit tests ran and real run-state behavior did not
- claim merge-readiness or feature completion from local evidence alone
- describe serialized same-terminal work as "parallel" execution
Project Rules
- This project modifies VNX itself
- Main CLI:
bin/vnx - All shell changes must pass
bash -n - Backward compatibility with existing commands is mandatory unless dispatch says otherwise
Evidence Standard
- Prefer exact commands over prose summaries
- If CI matters, say whether you checked local-only or remote GitHub state
- If path resolution or worktree behavior is relevant, test both where feasible
- If closure depends on your numbers, make them independently checkable by T0
- Call out explicitly when smoke, integration, certification, PTY behavior, or live-worker coverage is still missing
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.

