agentleFS
Sign inStart free
e-dule-dul/opencl-lab/CLAUDE.md

opencl-lab

CLAUDE.md0 starsChanged 8 months agoMITView on GitHub

The file

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

9 rules. About 0 are common, 8 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈8

    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
  1. Distinctive:

    Performance: Always profile (Events) before optimizing.

    line 7
  2. Distinctive:

    Use RAII wrappers for OpenCL resources.

    line 13
  3. Distinctive:

    Always check OpenCL return codes.

    line 19
  4. Very specific:

    When asked to plan a task, write the plan and store in workflow/tasks/.

    line 27
  5. Distinctive:

    Consider task completed only after explicitly told.

    line 28
  6. Distinctive:

    NEVER use sed or custom python scripts for file modifications

    line 31
  7. Distinctive:

    ALWAYS show a clear diff before applying any change

    line 32
  8. Distinctive:

    Use str_replace with explicit before/after blocks

    line 33
  9. Distinctive:

    DO NOT USE /tmp dir

    line 34

≈ “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.

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

AI Engineering Guidelines for Applied OpenCL Lab

Project Philosophy

  1. Code-First: Code is the primary knowledge carrier.
  2. Just-in-Time Learning: Theory on demand.
  3. Education First: Code must be readable by Mid-level engineers.
  4. Performance: Always profile (Events) before optimizing.

Architecture

  • common/ contains helper functions (error handling, image IO).
  • Kernels (.cl) are separate files, loaded at runtime.
  • Build system is CMake (standalone per module).
  • Use RAII wrappers for OpenCL resources.

Code Conventions

  • Variables: snake_case
  • Classes: PascalCase
  • Constants: UPPER_CASE
  • Always check OpenCL return codes.

Communication Style

  • Terse: No filler phrases.
  • Diff-Driven: Show code changes.
  • Direct: Start with the answer.

Other

  • When asked to plan a task, write the plan and store in workflow/tasks/. Never implement unless explicitly told to proceed.
  • Consider task completed only after explicitly told.

Discipline

  • NEVER use sed or custom python scripts for file modifications
  • ALWAYS show a clear diff before applying any change
  • Use str_replace with explicit before/after blocks
  • DO NOT USE /tmp dir

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.

Check your setup, free