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 Zfinix/aster --skill build-triagegit clone --depth 1 https://github.com/Zfinix/asterWrote 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/zfinix/aster/build-triage)<a href="https://agentmods.dev/skills/zfinix/aster/build-triage"><img src="https://agentmods.dev/badge/skills/zfinix/aster/build-triage/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/zfinix/aster/build-triage"><img src="https://agentmods.dev/badge/skills/zfinix/aster/build-triage.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 | $0.00036 | $0.00404 |
| Opus 5.5 | $0.00014 | $0.00162 |
| Sonnet 5.5 | $0.00007 | $0.00081 |
| Haiku 4.5 | $0.00004 | $0.00040 |
Grade A, and why
build-triage 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 9d 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
Build triage
- Fix the first error, not the last. Everything after the first error is
usually cascade.
cargo build 2>&1 | grep -m1 -B1 -A6 "^error". - Exit code 0 can still be a failure. The exit code of a pipeline belongs
to its last stage:
cargo build 2>&1 | tail -3reports tail's success. Trust the output text (error[,FAILED,panicked) over the code. - Bound the output.
| tail -20for verdicts (test runners put the verdict last),| head -30for first errors,--statfor diffs. Never dump a full build log. - Never escalate a timeout. A command that timed out will time out again
with a bigger budget. The exception is work that is long by nature (an
eval, a full suite): run it with
background:true, seelong-running-work. Kill leftovers (pkill -f cargo), then narrow: one package, one test, one file.cargo check -p one-cratebeats a 10 minute workspace build. - Label pipeline stages so partial output says where it died:
echo "=== build ===" && cargo check 2>&1 | tail -3 && echo "=== test ===" && cargo test 2>&1 | tail -5 - Filter noise to signal. A hundred identical warnings hide one error:
2>&1 | grep -E "^(error|FAILED|thread)" | head -10.
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.
- 9d ago Changed · +1 lines 60250801a97c
- 1mo ago First seen · 24 lines · 36 tokens per session scan A ffbde263a441
build-triage is a skill published in the GitHub repository Zfinix/aster (133 stars, last pushed 2d ago), licensed Apache-2.0. It adds 36 tokens to every session and 404 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
diagnose-windows-sandbox-acl
Use on Windows for unexpected ALEGO sandbox access denials: workspace writes or listing fail, or an ordinarily readable path cannot be read. One bundled command inspects the path and every ancestor and repairs the ACL problems it proves in that same run. Expected confinement denials need no ACL repair.
ctx
Codebase intelligence and evidence-driven governance with the indexed ctx CLI. Use when exploring an unfamiliar repository, locating symbols or callers, checking for existing implementations, estimating change impact, enforcing architecture rules, scoring a branch, finding hotspots or duplication, or analyzing…
node-notready-triage
Use when nodes are NotReady or the whole cluster looks unhealthy — inspects node conditions, CNI/kube-system pods, and capacity to find what is keeping the kubelet or network from being ready.
pod-crashloop-triage
Use when pods are in CrashLoopBackOff, ImagePullBackOff, ErrImagePull, or OOMKilled — collects describe/logs/events and identifies the failure class before recommending a fix.
ml-training-job-triage
Use when triaging failed, slow, or expensive ML training jobs, GPU utilization, data/input errors, checkpoints, and retry strategy.
platform-sre-triage
Use when triaging platform reliability issues — orchestrates service health reporting, then Docker disk diagnostics, then the smallest safe next action.