What is generate-sbom?

A tool that creates an AI software bill of materials, or SBOM, for a pull request. An SBOM is a structured record of the tools, models, and skills that contributed to the code.

Use it to prepare an AI-assistance section for a pull request, summarize current-session AI usage, or extract provenance from earlier sessions.

It records AI involvement and provenance in a consistent format for code reviews and project history.

generate-sbom — Skill for Claude Code by openshift-eng

Install

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.

Any agent

npx skills add openshift-eng/ai-helpers --skill generate-sbom

Clone the repo

git clone --depth 1 https://github.com/openshift-eng/ai-helpers

Made for: Claude Code.

Or install ai-sbom, the plugin that ships this one along with the rest of its 1 skill.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/openshift-eng/ai-helpers/generate-sbom.svg)](https://agentmods.dev/skills/openshift-eng/ai-helpers/generate-sbom)

Your own site

<a href="https://agentmods.dev/skills/openshift-eng/ai-helpers/generate-sbom"><img src="https://agentmods.dev/badge/skills/openshift-eng/ai-helpers/generate-sbom.svg" alt="Measured on agentmods" height="20"></a>

Per session 73 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 856 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 3 findings, up to medium

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 →

medium Rogue Agent · line 3
Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
medium Agent Snooping · line 38
Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
medium Agent Snooping · line 39
Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

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	$0.00073	$0.00856
Opus 5	$0.00036	$0.00428
Sonnet 5	$0.00015	$0.00171
Haiku 4.5	$0.00007	$0.00086

Measured 8d ago against content hash 63361d3ef4d9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

generate-sbom 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.

plugins/ai-sbom/skills/generate-sbom/SKILL.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Generate AI SBOM Declaration

Generate a formatted ai-assisted code fence block for a PR description that declares which AI tools, models, and skills contributed to the work.

Modes

Current Session

When the user asks to generate an AI SBOM during an active session, you already know which skills were invoked. Collect the list from your own tool usage history in this conversation. Get the tool version by running claude --version.

Past Session

When the user wants an SBOM for a previous session or across multiple sessions:

Identify the project directory: ~/.claude/projects/<project-path-with-dashes>/

Run the extraction script:

python3 <ai-sbom-plugin-path>/scripts/extract_skills.py <path-to-session-or-project-dir>

The script outputs a JSON object with skills, models, and tool_version. The tool version is extracted from the session transcript when available; if not found, it falls back to the currently installed version via claude --version.

Resolving Provenance

For each skill identified, resolve its version and source:

Read ~/.claude/plugins/installed_plugins.json to find the plugin entry
- The key format is plugin-name@marketplace-name (e.g., superpowers@claude-plugins-official)
- Extract version and gitCommitSha from the entry
Read ~/.claude/plugins/known_marketplaces.json to find the source repo
- Match the marketplace name to get the source.repo (e.g., anthropics/claude-plugins-official)
For repo-local skills (.claude/skills/), use the repo: prefix with no version
For user-level skills (~/.claude/skills/), use the user: prefix with no version

Output Format

Read the format specification at plugins/ai-sbom/docs/AI_SBOM.md for the exact block structure, field definitions, skill entry format, and examples. Generate the ai-assisted code fence block following that spec.

Writing to a PR

When the user asks to write the SBOM to a PR:

Find the PR for the current branch: gh pr view --json number,body
Generate the SBOM block with the ## AI Assistance header
Check if the PR body already contains a ## AI Assistance section
- If yes, replace everything from ## AI Assistance through the closing ``` of the ai-assisted fence
- If no, append the section to the end of the PR body
Update the PR: gh pr edit <number> --body "<updated body>"
Confirm to the user what was written

Read the full file on GitHub · 69 lines

Changes

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 · 69 lines · 73 tokens per session scan A 63361d3ef4d9

Subscribe to this mod's changes

generate-sbom is a skill published in the GitHub repository openshift-eng/ai-helpers (116 stars, last pushed 4d ago), licensed Apache-2.0. It adds 73 tokens to every session and 856 once invoked, about $0.0004 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.

Git and workflow Security

prowler-commit

Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.

prowler-cloud/prowler · 33 tokens

gh-auth-isolation

Safely manage multiple GitHub identities (EMU + personal) in agent workflows.

github/gh-aw · 20 tokens

comet-github

A routing guide for Comet-related GitHub work. It directs requests about pull requests, issues, CI failures, ideas, and fixes to the appropriate review or implementation process.

rpamis/comet · 72 tokens

github-skill

Work with GitHub via the gh CLI — clone repositories, create/list/merge pull requests, create/list issues, and run any other gh command (API calls, workflow runs, releases, repo administration). List operations return parsed JSON.

zeenie-ai/OpenCompany · 51 tokens

re0-merge

Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…

LilMGenius/paperthin · 70 tokens

codex-autoresearch

Run autonomous, measurable experiments in a Git repository: change one hypothesis, verify a numeric metric, keep improvements, and revert failures. Use when the user wants Codex to keep iterating toward a numeric target in the foreground or as a detached background run. Do not use for ordinary one-shot coding…

leo-lilinxiao/codex-autoresearch · 80 tokens