triton-kernel-reflection-prompts

triton-kernel-reflection-prompts is a skill for Claude Code, Codex from AMD-AGI/Apex. It costs 31 tokens per session (170 once invoked), scanned A, original, MIT.

A set of self-review prompts for checking and improving Triton GPU kernels aimed at AMD hardware. Triton is a language for writing GPU programs.

In plain words
What is it for?
Use it after running or testing an AMD kernel to suggest code changes, explain their reasons, and check AMD-specific concerns such as memory access, GPU occupancy, and shared-memory conflicts.
Why use it?
It gives a structured way to investigate failed tests or performance problems while keeping correctness ahead of speed and readability.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it after running or testing an AMD kernel to suggest code changes, explain their reasons, and check AMD-specific concerns such as memory access, GPU occupancy, and shared-memory conflicts.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/amd-agi/apex/triton-kernel-reflection-prompts
View source ↗ AMD-AGI/Apex
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add AMD-AGI/Apex --skill triton-kernel-reflection-prompts
Clone the repo
git clone --depth 1 https://github.com/AMD-AGI/Apex

Made for: Claude Code, Codex.

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 triton-kernel-reflection-prompts

README.md
[![agentmods](https://agentmods.dev/badge/skills/amd-agi/apex/triton-kernel-reflection-prompts.svg)](https://agentmods.dev/skills/amd-agi/apex/triton-kernel-reflection-prompts)
Your own site
<a href="https://agentmods.dev/skills/amd-agi/apex/triton-kernel-reflection-prompts"><img src="https://agentmods.dev/badge/skills/amd-agi/apex/triton-kernel-reflection-prompts.svg" alt="Measured on agentmods" height="20"></a>
Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 170 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 $0.00031 $0.00170
Opus 5 $0.00015 $0.00085
Sonnet 5 $0.00006 $0.00034
Haiku 4.5 $0.00003 $0.00017

Measured 8d ago against content hash 0a84473997d4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

triton-kernel-reflection-prompts 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 8d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (references/prompt_for_reflection.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

tools/skills/triton-kernel-reflection-prompts/SKILL.md · 19 lines

What it actually says

AMD Kernel Reflection Prompts

  • Use after a kernel run/test to drive structured self-review and fixes.
  • Load references/prompt_for_reflection.py for the full reflection prompt and guidance.

How to use

  • Summarize failures/perf gaps, then feed the reflection prompt to propose patches.
  • Follow the checklist: correctness first, then performance and readability.
  • Keep AMD-focused advice: wave64 occupancy, LDS/bank conflict avoidance, coalesced and vectorized memory access.
  • Output schema should include proposed code changes plus rationale for downstream tools.

References

  • references/prompt_for_reflection.py: Reflection prompt definitions.
Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 8d ago First seen · 19 lines · 31 tokens per session scan A 0a84473997d4

Subscribe to this mod's changes

triton-kernel-reflection-prompts is a skill published in the GitHub repository AMD-AGI/Apex (76 stars, last pushed 5d ago), licensed MIT. It adds 31 tokens to every session and 170 once invoked, about $0.0002 per session on Opus 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 2026-08-30.