orkid: Skill for Claude Code

.claude/skills/orklev2-ci/SKILL.md

orklev2-ci is a skill for Claude Code from tweakoz/orkid. It costs 55 tokens per session (728 once invoked), scanned A, original, MIT.

A reference guide to orkid's ComputeInterface for running GPU compute shaders, programs that perform parallel calculations on graphics hardware.

In plain words
What is it for?
Use it when working with direct or indirect compute dispatch, storage buffers, images, samplers, or GPU synchronization.
Why use it?
It explains how to dispatch compute work and safely connect buffers, images, samplers, and memory barriers.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

This is tweakoz/orkid's own configuration. It tells Claude Code how to work on orkid itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything orkid configures →

Reuse

Borrowing it

Nothing to install: this file belongs to tweakoz/orkid. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/tweakoz/orkid/develop/.claude/skills/orklev2-ci/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/tweakoz/orkid

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for orklev2-ci

README.md
[![agentmods](https://agentmods.dev/badge/skills/tweakoz/orkid/orklev2-ci/github.svg)](https://agentmods.dev/skills/tweakoz/orkid/orklev2-ci)
Your own site
<a href="https://agentmods.dev/skills/tweakoz/orkid/orklev2-ci"><img src="https://agentmods.dev/badge/skills/tweakoz/orkid/orklev2-ci/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for orklev2-ci

Your own site · 80×15
<a href="https://agentmods.dev/skills/tweakoz/orkid/orklev2-ci"><img src="https://agentmods.dev/badge/skills/tweakoz/orkid/orklev2-ci.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 728 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00055 $0.00728
Opus 5.5 $0.00022 $0.00291
Sonnet 5.5 $0.00011 $0.00146
Haiku 4.5 $0.00006 $0.00073

Measured 2mo ago against content hash eb915d9ea3ce, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

orklev2-ci scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/orklev2-ci/SKILL.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Orkid ComputeInterface (CI) Reference

When answering questions about compute shaders or GPU compute in orkid, consult the files below. All under ork.lev2/.

Key Files

Component File
CI Interface inc/ork/lev2/gfx/ci.h (lines 8–44)
FxComputeShader inc/ork/lev2/gfx/shadman.h
Vulkan CI src/gfx/vulkan/headers/vulkan_ctx.h (lines 584–619)
Python Bindings pyext/src/pyext_gfx.cpp

CI Interface (ci.h:8–44)

ImageBindAccess Enum

  • EIBA_READ_ONLY = 0
  • EIBA_WRITE_ONLY = 1
  • EIBA_READ_WRITE = 2

Dispatch Phase Management

  • beginDispatchPhase() — suspends active render pass if needed
  • endDispatchPhase() — resumes render pass

Compute Dispatch

  • dispatchCompute(shader, numgroups_x, numgroups_y, numgroups_z) — direct dispatch
  • dispatchComputeIndirect(shader, indirect_ptr) — indirect dispatch from buffer

Resource Binding

  • bindStorageBuffer(shader, binding_index, buffer) — bind SSBO to compute shader
  • bindImage(shader, binding_index, texture, access) — bind image for load/store
  • bindSampler(shader, binding_index, texture) — bind texture sampler

Memory Barriers

  • storageBarrier() — ensures prior SSBO writes are visible to subsequent dispatches

Typical Usage

auto* CI = ctx->CI();
auto* FXI = ctx->FXI();

// Get compute shader from loaded FxShader
auto* cs = FXI->computeShader(shader, "cs_blur");

CI->beginDispatchPhase();

// Bind resources
CI->bindStorageBuffer(cs, 0, input_ssbo);
CI->bindStorageBuffer(cs, 1, output_ssbo);
CI->bindImage(cs, 2, texture, ComputeInterface::EIBA_WRITE_ONLY);

// Dispatch workgroups
CI->dispatchCompute(cs, groups_x, groups_y, groups_z);

// Barrier between passes
CI->storageBarrier();

// Second dispatch can read first dispatch's output
CI->dispatchCompute(cs2, groups_x, groups_y, groups_z);

CI->endDispatchPhase();

Vulkan Implementation Notes

The Vulkan CI (VkComputeInterface) handles:

  • Suspending/resuming active render passes for compute dispatch
  • Pipeline binding for compute shaders (separate from graphics pipeline)
  • Descriptor set binding for compute resources
  • vkCmdDispatch / vkCmdDispatchIndirect calls
  • VK_PIPELINE_STAGE_COMPUTE_SHADER_BIT barriers

Read the full file on GitHub · 86 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2mo ago First seen · 86 lines · 55 tokens per session scan A eb915d9ea3ce

Subscribe to this mod's changes

orklev2-ci is a skill published in the GitHub repository tweakoz/orkid (35 stars, last pushed 2mo ago), licensed MIT. It adds 55 tokens to every session and 728 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-01.

Related

orklev2-ci compared with skills from other repositories

orklev2-ci next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
orklev2-citweakoz/orkidSkill352mo agoMITA55Claude Code
unity-pipelineAlex-Rachel/TEngineSkill2.4k16d agoMITA97Claude Code
dart-verify-simdartsim/dartSkill1.2kyesterdayBSD-2-ClauseA32Claude Code, Codex
metasoundskevinpbuckley/VibeUESkill8122d agoMITA63Claude Code, Codex
dart-model-upgradedartsim/dartSkill1.2kyesterdayBSD-2-ClauseA42Claude Code
html-to-uguiAlex-Rachel/TEngineSkill2.4k16d agoMITA75Codex
luban-devAlex-Rachel/TEngineSkill2.4k16d agoMITA62Codex