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 runxhq/runx --skill sbom-makergit clone --depth 1 https://github.com/runxhq/runxWrote 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/runxhq/runx/sbom-maker)<a href="https://agentmods.dev/skills/runxhq/runx/sbom-maker"><img src="https://agentmods.dev/badge/skills/runxhq/runx/sbom-maker/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/runxhq/runx/sbom-maker"><img src="https://agentmods.dev/badge/skills/runxhq/runx/sbom-maker.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 | $0.00043 | $0.00406 |
| Opus 5 | $0.00022 | $0.00203 |
| Sonnet 5 | $0.00009 | $0.00081 |
| Haiku 4.5 | $0.00004 | $0.00041 |
Grade A, and why
sbom-maker 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
SBOM Maker
Turn one lockfile into a verifiable component inventory. The caller supplies
the parsed lockfile; nothing is fetched, so the same input always seals the
same SBOM. This is the inventory layer of the security pipeline: sbom-maker
derives what is present, cve-audit detects what is vulnerable.
Procedure
- Native
data.digestbinds the exact lockfile object; the SBOM serial number and metadata carry that digest, so the inventory cannot drift from its source. - Deterministic extraction reads the modern
packagesmap (or the classic nesteddependenciesmap) and keeps only pinned components with versions, each with its evidence location inside the lockfile. - Licenses are normalized, counted, and risk-flagged: strong copyleft is
high, weak copyleft ismedium, missing license evidence isreview. Risks are surfaced, never suppressed. - A lockfile that is not an object, carries no dependency map, or pins no components refuses with findings instead of emitting an empty inventory.
To inventory a remote lockfile, compose web-fetch for the governed read and
pass its content here; the digest binds whatever bytes were supplied.
Output
sbom_result (runx.sbom.v1) carries decision (generated, refused),
the CycloneDX 1.5 sbom or null, component_count, license_summary,
license_risks, validation, and the lockfile digest.
Inputs are lockfile and optional lockfile_type (package-lock,
npm-shrinkwrap).
What ships with it
2 files 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.
- 9d ago First seen · 38 lines · 43 tokens per session scan A 35cbf71ec533
sbom-maker is a skill published in the GitHub repository runxhq/runx (87 stars, last pushed 3d ago), licensed Apache-2.0. It adds 43 tokens to every session and 406 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 2026-09-03.
Other skills, from other repositories
dd-report-format
Standard output format for due diligence analysis reports. Use when producing your final analysis to ensure consistency across all specialist agents.
dd-risk-scoring
Calculate weighted risk scores from specialist agent reports. Use when synthesizing multiple due diligence reports into an overall investment risk assessment.
dd-synthesis
Synthesize findings from multiple specialist agents into a coherent investment recommendation. Use when combining reports from 9+ specialist agents into a single decision document.
dd-sourcing
Document sources properly for due diligence reports. Use when citing any external data, ensuring full traceability and auditability of findings.
dd-verification
Verify claims in pitch decks and founder statements using multiple independent sources. Use when analyzing any claim about market size, traction, team background, or competitive positioning.
codew-release-qa-sweep
Use before claiming Codewhale release work is done: run the full gate sweep and list the manual QA targets.