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 opendatahub-io/ai-helpers --skill rpm-examinegit clone --depth 1 https://github.com/opendatahub-io/ai-helpersWrote 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/opendatahub-io/ai-helpers/rpm-examine)<a href="https://agentmods.dev/skills/opendatahub-io/ai-helpers/rpm-examine"><img src="https://agentmods.dev/badge/skills/opendatahub-io/ai-helpers/rpm-examine/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/opendatahub-io/ai-helpers/rpm-examine"><img src="https://agentmods.dev/badge/skills/opendatahub-io/ai-helpers/rpm-examine.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 | $0.00009 | $0.01415 |
| Opus 5.5 | $0.00004 | $0.00566 |
| Sonnet 5.5 | $0.00002 | $0.00283 |
| Haiku 4.5 | $0.00001 | $0.00142 |
Grade A, and why
rpm-examine scanned grade A 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 2mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -LO <copr-url>/builder-live.log.gz How it starts
The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Name
odh-ai-helpers:rpm-examine
Synopsis
/rpm:examine <copr-chroot-url>
/rpm:examine <build-log-url> <srpm-url>
/rpm:examine <build.log> <specfile|dist-git> [sources]
Description
Analyze RPM build.log failures. Provide a comprehensive analysis with error summary, root cause, and actionable fixes.
Mode 1: Copr Results URL or Direct URLs to build.log and SRPM
Provide a single Copr build results URL to automatically fetch all build artifacts or provide two URLs - one for build.log and one for SRPM.
What gets downloaded:
build-live.log.gzorbuild.log- Main build log*.src.rpm- Source RPM containing spec file, sources, and patchesroot.log.gz,state.log- Additional context logs (optional)
Mode 2: Local Files
Provide paths to local build artifacts.
Arguments:
<build.log>- Path to build log file (required)<specfile|dist-git>- Path to spec file or dist-git repo clone (required)[sources]- Path to source tarball or unpacked sources (optional)
Context gathering: If sources not provided, search in:
- build.log parent directory
- specfile parent directory
- dist-git clone directory
Implementation
1. Input Detection
- If single URL: Copr results directory → continue to step 2a
- If two URLs: Direct URLs to build.log and SRPM (Koji/Brew) → download both directly, then follow 2a steps 3-5
- If local path(s): Local workflow → continue to step 2b
2. Artifact Collection
2a. URL Workflow
- Create temporary working directory
- Download files from Copr URL:
curl -LO <copr-url>/builder-live.log.gz curl -LO <copr-url>/*.src.rpm curl -LO <copr-url>/root.log.gz # optional curl -LO <copr-url>/state.log # optional - Decompress logs:
gunzip *.log.gz(if needed) - Extract SRPM:
rpm2cpio *.src.rpm | cpio -idmv - Locate extracted spec file
2b. Local Workflow
- Verify build.log exists and is readable
- Verify specfile/dist-git path exists
- Search for sources if not provided:
- Check build.log parent directory for
*.tar.*or*.src.rpm - Check specfile parent directory
- If dist-git repo, check for sources in repo
- Check build.log parent directory for
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.
- 2mo ago First seen · 153 lines · 9 tokens per session scan A 25e44ed9f73b
rpm-examine is a skill published in the GitHub repository opendatahub-io/ai-helpers (39 stars, last pushed 5d ago), licensed Apache-2.0. It adds 9 tokens to every session and 1,415 once invoked, about $0.0000 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
rpm-examine compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| rpm-examineopendatahub-io/ai-helpers | Skill | 39 | 5d ago | Apache-2.0 | A | 9 | Claude Code |
| debugging-strategieswshobson/agents | Skill | 42k | yesterday | MIT | A | 43 | Claude Code |
| sql-optimization-patternswshobson/agents | Skill | 42k | yesterday | MIT | A | 44 | Claude Code |
| parallel-debuggingwshobson/agents | Skill | 42k | yesterday | MIT | A | 44 | Claude Code |
| git-advanced-workflowswshobson/agents | Skill | 42k | yesterday | MIT | A | 54 | Claude Code |
| error-handling-patternswshobson/agents | Skill | 42k | yesterday | MIT | A | 43 | Claude Code |
| spark-optimizationwshobson/agents | Skill | 42k | yesterday | MIT | A | 37 | Claude Code |