Borrowing it
Nothing to install: this file belongs to ROCm/aiter. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ROCm/aiter/main/.claude/skills/opus-module-build-optimization/SKILL.mdgit clone --depth 1 https://github.com/ROCm/aiterWrote 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/rocm/aiter/opus-module-build-optimization)<a href="https://agentmods.dev/skills/rocm/aiter/opus-module-build-optimization"><img src="https://agentmods.dev/badge/skills/rocm/aiter/opus-module-build-optimization/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/rocm/aiter/opus-module-build-optimization"><img src="https://agentmods.dev/badge/skills/rocm/aiter/opus-module-build-optimization.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 29 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
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 | $0.00046 | $0.03703 |
| Opus 5.5 | $0.00018 | $0.01481 |
| Sonnet 5.5 | $0.00009 | $0.00741 |
| Haiku 4.5 | $0.00005 | $0.00370 |
Grade C, and why
opus-module-build-optimization scanned grade C with 1 finding 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf $AITER_ROOT/aiter/jit/build/$MODULE \ How it starts
The opening of the file, as written. The whole thing — 283 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Opus Module Build-Time Optimization
Techniques for reducing the JIT build wall of an aiter module bundling N opus kernel TUs + a dispatcher + a pybind TU. Patterns developed while taking module_deepgemm_opus from 48.4s to 11.1s (-77%) end-to-end rebuild.
This skill is the module-level companion to opus-kernel-best-practice (which covers single-kernel codegen). Use this one when the bottleneck is host-pass header weight, TU count + parallelism, or dispatcher / pybind TU cost. Use the kernel-author skill instead when a single TU's device-pass MCG dominates.
0. Diagnose Before Optimizing (Most Important)
Always run these probes first. Speculation on what saves how much is unreliable -- module bottlenecks are non-obvious and often counter-intuitive (we expected -mllvm flags to matter, they didn't; we expected splitk to be slower, it was actually a hipgraph trap).
Set these once before running any snippet below:
export AITER_ROOT=$(pwd) # your aiter checkout
export MODULE=module_<name> # e.g. module_deepgemm_opus
export BUILD_DIR=$AITER_ROOT/aiter/jit/build/$MODULE/build
End-to-end build wall (3-trial)
for i in 1 2 3; do
rm -rf $AITER_ROOT/aiter/jit/build/$MODULE \
$AITER_ROOT/aiter/jit/$MODULE.so
AITER_REBUILD=1 AITER_LOG_LEVEL=info python3 -c \
"import aiter.ops.<module_python_path>" 2>&1 | grep "finish build"
done
Per-TU wall ranking (find the critical path)
cd $BUILD_DIR
for tu in *.cuda.o; do
ninja -t commands $tu > /tmp/cmd.sh; chmod +x /tmp/cmd.sh
rm -f $tu
t0=$(date +%s.%N); /tmp/cmd.sh > /dev/null 2>&1; t1=$(date +%s.%N)
printf "%5ss %s\n" "$(awk -v t0=$t0 -v t1=$t1 'BEGIN{printf "%.2f", t1-t0}')" "$tu"
done | sort -rn | head -10
Top 1-2 TUs ARE the build wall under AITER_MAX_JOBS >= N. Optimize those; don't touch the long tail.
Per-pass timing (host vs device)
export TU=<one_slow_tu>.cuda.o
cd $BUILD_DIR
ninja -t commands $TU > /tmp/cmd.sh
sed -i 's| -c | -ftime-report -c |' /tmp/cmd.sh; chmod +x /tmp/cmd.sh
rm -f $TU; /tmp/cmd.sh 2>&1 | tee /tmp/tr.log
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 Changed 92d919f3fdae
- 2mo ago First seen · 283 lines · 46 tokens per session scan C 47c5b3767622
opus-module-build-optimization is a skill published in the GitHub repository ROCm/aiter (598 stars, last pushed today), licensed MIT. It adds 46 tokens to every session and 3,703 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). 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.
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…
cwv-optimizer
Diagnose and fix Core Web Vitals issues on AEM Edge Delivery Services pages. Goes deeper than generic CWV advice by understanding EDS-specific performance patterns including the 100KB LCP budget, E-L-D loading phases, block rendering behavior, and third-party script impact. Produces specific fixes for LCP, CLS, and…
incident-response-incident-response
Coordinate production incident triage, mitigation, investigation, recovery, and follow-up. Use when responding to outages or other incidents that require structured operational coordination.
ci-fixer
CI failures - read error, minimal fix, verify.