Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/slowlyC/agent-gpu-skillsnpx agentmods add skills/slowlyc/agent-gpu-skills/triton-skillWrote 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.
[](https://agentmods.dev/skills/slowlyc/agent-gpu-skills/triton-skill)<a href="https://agentmods.dev/skills/slowlyc/agent-gpu-skills/triton-skill"><img src="https://agentmods.dev/badge/skills/slowlyc/agent-gpu-skills/triton-skill/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.
<a href="https://agentmods.dev/skills/slowlyc/agent-gpu-skills/triton-skill"><img src="https://agentmods.dev/badge/skills/slowlyc/agent-gpu-skills/triton-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00116 | $0.01307 |
| Opus 5 | $0.00058 | $0.00654 |
| Sonnet 5 | $0.00023 | $0.00261 |
| Haiku 4.5 | $0.00012 | $0.00131 |
Grade A, and why
triton-skill 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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Triton and Gluon development
Use the local Triton checkout as the primary source for APIs and implementation patterns. Prefer current tutorials and source over remembered signatures because Triton and Gluon evolve quickly.
Locate the checkout
Resolve the directory containing this SKILL.md, then use its repos/triton/ child. The installer links that path to agent-gpu-skills/third_party/triton/ or to the checkout supplied through TRITON_REPO.
In commands below, replace TRITON_REPO with the resolved absolute path:
TRITON_REPO=/absolute/path/to/triton-skill/repos/triton
If the checkout is missing, run this from the agent-gpu-skills repository and reinstall the Skill:
bash update-repos.sh triton
bash install.sh --skill triton-skill
Choose the source surface
| Task | Start here |
|---|---|
| Triton language syntax and introductory patterns | python/tutorials/ |
| Gluon layout and architecture-level patterns | python/tutorials/gluon/ |
| Complete example kernels | python/examples/ |
| Production matmul, reduction, top-k and SwiGLU | python/triton_kernels/triton_kernels/ |
tl.* definitions and semantics |
python/triton/language/ |
| JIT, autotuning and runtime behavior | python/triton/runtime/ |
| Python compiler entry points | python/triton/compiler/ |
| Triton and GPU dialect definitions | include/triton/Dialect/ |
| Compiler analyses, transforms and lowering | lib/ |
Read quick-reference.md when choosing a tutorial, a complete example, or a production-kernel implementation.
Query workflow
- Identify whether the task is Triton, Gluon, or compiler internals.
- Find the closest current tutorial or implementation for the operation and architecture.
- Verify every API used against its definition or another current call site.
- Preserve the target workload's shape, dtype, stride, layout, masking, and numerical contract.
- Establish correctness before changing launch parameters or optimization strategy.
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.
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.
- 10d ago First seen · 138 lines · 116 tokens per session scan A f84507d3d67c
triton-skill is a skill published in the GitHub repository slowlyC/agent-gpu-skills (165 stars, last pushed 1mo ago), licensed MIT. It adds 116 tokens to every session and 1,307 once invoked, about $0.0006 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.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.