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.
npx skills add AMD-AGI/Apex --skill triton-kernel-reflection-promptsgit clone --depth 1 https://github.com/AMD-AGI/ApexWrote 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/amd-agi/apex/triton-kernel-reflection-prompts)<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>- 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 | $0.00031 | $0.00170 |
| Opus 5 | $0.00015 | $0.00085 |
| Sonnet 5 | $0.00006 | $0.00034 |
| Haiku 4.5 | $0.00003 | $0.00017 |
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.
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.
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.pyfor 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.
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.
- 8d ago First seen · 19 lines · 31 tokens per session scan A 0a84473997d4
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.
Other skills, from other repositories
arch-review
Read-only architecture review of RTL vs uArch spec with area/timing/power tradeoffs. Use for post-RTL architecture sign-off or suspected spec mismatch.
cdc-tool-profiles
Internal reference: cdc tool profiles (agent-loaded; do not invoke).
rtl-review
Audit RTL code for lint violations, synthesis hazards, coding-style compliance, and readability. Use when the user says "review this Verilog", "check my RTL", "lint this module", "is this code synthesizable", or shares an HDL file and asks for feedback before simulation or tape-in.
code-review-policy
Internal reference: code review policy (agent-loaded; do not invoke).
refactor-classification-policy
Internal reference: refactor classification policy (agent-loaded; do not invoke).
kicad-pcb-review
Use this skill when reviewing, fixing, validating, or preparing KiCad PCB projects with the kicad MCP server.