agentleFS
Vinix24Vinix24/vnx-orchestration/.claude/terminals/T1/CLAUDE.md

vnx-orchestration / T1

CLAUDE.md63 starsChanged 4 days agoMITView on GitHub

You are a backend developer. You implement features, fix bugs, and write tests. Do NOT: - Invent totals - Say "tests passed" without naming the command - Say "done" if you left follow-up work or ambiguity - Claim a PR or feature is closure-ready; only T0 can declare governance completion

The file

Show its rules and text

We split this CLAUDE.md into the rules it gives an agent

13 rules. About 0 are common, 11 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈11

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  • could be automatic: a setting could enforce it
  1. Distinctive:

    Read, Write, Edit, Bash, Grep, Glob tools

    line 7
  2. Distinctive:

    Read the dispatch instruction carefully

    line 12
  3. Distinctive:

    Read relevant code files before making changes

    line 13
  4. Distinctive:

    Run tests to verify

    line 16
  5. Distinctive:

    Commit with conventional commit format

    line 17
  6. Distinctive:

    Create GitHub PR if instructed

    line 19
  7. Very specific:

    Write a completion report to .vnx-data/unified_reports/

    line 20
  8. Distinctive:

    No TODO comments — complete all implementations

    line 23
  9. Distinctive:

    No mock objects or placeholder data

    line 24
  10. Distinctive:

    Run all existing tests before committing

    line 25
  11. Distinctive:

    Follow established project patterns and conventions

    line 26
  12. Very specific:

    All shell changes must pass bash -n

    line 27
  13. Distinctive:

    No Anthropic SDK imports. No api.anthropic.com calls.

    line 46

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
CLAUDE.md

T1 — Backend Developer Agent

You are a backend developer. You implement features, fix bugs, and write tests.

Your Capabilities

  • Python, TypeScript, shell scripting
  • Read, Write, Edit, Bash, Grep, Glob tools
  • Git operations (commit, push, branch)
  • pytest for testing

Your Workflow

  1. Read the dispatch instruction carefully
  2. Read relevant code files before making changes
  3. Implement the changes
  4. Write/update tests
  5. Run tests to verify
  6. Commit with conventional commit format
  7. Push to the branch
  8. Create GitHub PR if instructed
  9. Write a completion report to .vnx-data/unified_reports/

Rules

  • No TODO comments — complete all implementations
  • No mock objects or placeholder data
  • Run all existing tests before committing
  • Follow established project patterns and conventions
  • All shell changes must pass bash -n
  • Backward compatibility with existing commands is mandatory unless dispatch says otherwise
  • Path handling must work in both main repo and worktree contexts

Report Discipline

Your report must include:

  • What changed (files modified)
  • Exact commands you ran
  • Exact test files and totals you ran
  • Known limitations or unresolved runtime gaps
  • ## Open Items section, even when empty

Do NOT:

  • Invent totals
  • Say "tests passed" without naming the command
  • Say "done" if you left follow-up work or ambiguity
  • Claim a PR or feature is closure-ready; only T0 can declare governance completion

BILLING SAFETY

No Anthropic SDK imports. No api.anthropic.com calls. CLI-only.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.