agentleFS
Avarok-CybersecurityAvarok-Cybersecurity/atlas/.claude/skills/oracle_pre_commit_cross_hardware_check/SKILL.md

oracle_pre_commit_cross_hardware_check

Skill724 starsChanged 2 months agoAGPL-3.0View on GitHub

O.R.A.C.L.E::pre_commit_cross_hardware_check — run BEFORE pushing any commit that touches kernels/ (especially kernels/gb10/common/), a __SCALE__ / __HIP / __CUDA_ARCH__ arm, cfg!(avarok_scale) or cfg(avarok_hip) host dispatch, a KERNEL.toml / MODEL.toml / HARDWARE.toml, or a symlink under kernels/. Detects cross-hardware kernel interference (CHKI): a change meant for one hardware (gb10, strix, strix-hip, metal) that alters what another hardware compiles through symlinks, common/ fan-out, or kernel_source redirects — strix is 7 real files and 105 symlinks into gb10, so a gb10 edit silently changes what AMD builds. Runs the static reach check, gathers verbatim evidence, launches the oracle for the remedy verdict (benign / parameterize in HARDWARE.toml with a reader / separate kernel with no symlink), and writes the Hardware: and CHKI-Verdict: trailers the CI job cross-hardware-reach requires. Also use when that CI job is red, when a strix or strix-hip compile leg fails on a gb10 edit, or when tempted to add a __SCALE__ guard to a gb10 file. Born from d584c0c50 (a gb10 edit broke hipcc, caught only by a compile leg) and 17fe989ec (a Strix workaround in gb10 common code invalidated 27 targets' records).

  • Commits and pushes

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

Licensed with conditions — read it at the source. We count its rules but don't quote them. Read them on GitHub.

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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.

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.