Vex Authoring
relizaio/rearm
Author CycloneDX-VEX or OpenVEX documents that import cleanly into ReARM.
Runs supply-chain risk analysis on CycloneDX BOMs with cdx-audit predictive auditing and cdxgen --bom-audit embedded rules, covering npm and PyPI package compromise posture, CI permission risk…
Install Bom Audit
$ npx skills add cdxgen/cdxgen --skill bom-audit -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install cdxgen/cdxgen bom-audit --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/cdxgen/cdxgen.git skills-src && mkdir -p .claude/skills && cp -r skills-src/claude-plugin/skills/bom-audit .claude/skills/bom-audit && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "bom-audit" agent skill from https://github.com/cdxgen/cdxgen/tree/master/claude-plugin/skills/bom-audit into .claude/skills/bom-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bom-audit", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/cdxgen/cdxgen/tree/master/claude-plugin/skills/bom-auditType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add cdxgen/cdxgen --skill bom-audit -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install cdxgen/cdxgen bom-audit --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cdxgen/cdxgen.git skills-src && mkdir -p .agents/skills && cp -r skills-src/claude-plugin/skills/bom-audit .agents/skills/bom-audit && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "bom-audit" agent skill from https://github.com/cdxgen/cdxgen/tree/master/claude-plugin/skills/bom-audit into .agents/skills/bom-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bom-audit", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add cdxgen/cdxgen --skill bom-audit -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install cdxgen/cdxgen bom-audit --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cdxgen/cdxgen.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/claude-plugin/skills/bom-audit .cursor/skills/bom-audit && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "bom-audit" agent skill from https://github.com/cdxgen/cdxgen/tree/master/claude-plugin/skills/bom-audit into .cursor/skills/bom-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bom-audit", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/cdxgen/cdxgen.git --path claude-plugin/skills/bom-audit--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add cdxgen/cdxgen --skill bom-audit -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install cdxgen/cdxgen bom-audit --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cdxgen/cdxgen.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/claude-plugin/skills/bom-audit .gemini/skills/bom-audit && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "bom-audit" agent skill from https://github.com/cdxgen/cdxgen/tree/master/claude-plugin/skills/bom-audit into .gemini/skills/bom-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bom-audit", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install cdxgen/cdxgen bom-auditInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add cdxgen/cdxgen --skill bom-audit -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/cdxgen/cdxgen.git skills-src && mkdir -p .github/skills && cp -r skills-src/claude-plugin/skills/bom-audit .github/skills/bom-audit && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "bom-audit" agent skill from https://github.com/cdxgen/cdxgen/tree/master/claude-plugin/skills/bom-audit into .github/skills/bom-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bom-audit", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add cdxgen/cdxgen --skill bom-audit -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install cdxgen/cdxgen bom-audit --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cdxgen/cdxgen.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/claude-plugin/skills/bom-audit .opencode/skills/bom-audit && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "bom-audit" agent skill from https://github.com/cdxgen/cdxgen/tree/master/claude-plugin/skills/bom-audit into .opencode/skills/bom-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "bom-audit", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
bom-audit- GitHub stars
- 1.1k
- Token cost
- ~2.4k tokens
- SKILL.md length
- 734 words
- Files
- 1
- Skills in repo
- 17
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Runs supply-chain risk analysis on CycloneDX BOMs with cdx-audit predictive auditing and cdxgen --bom-audit embedded rules, covering npm and PyPI package compromise posture, CI permission risk…
- Works in 5 steps: direct runtime dependencies → explicit CycloneDX scope=required → stronger source evidence via… → …
- Asked to audit an SBOM
- SKILL.md covers Predictive audit of an…, Direct BOM audit, Embedded audit during generation and Rule categories, plus 4 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Bom Audit is an agent skill from cdxgen/cdxgen. Runs supply-chain risk analysis on CycloneDX BOMs with cdx-audit predictive auditing and cdxgen --bom-audit embedded rules, covering npm and PyPI package compromise posture, CI permission risk, dependency source integrity, license policy violations, and SARIF or JSON reporting for code scanning. Use when asked to audit an SBOM, assess supply-chain or dependency risk, check for compromised or malicious packages, triage which dependencies to review first, or produce SARIF from a BOM.
Its SKILL.md is about 2.4k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Security, covering Supply chain security. It works with npm. The repository describes itself as: Creates CycloneDX Bill of Materials (BOM) for your projects from source and container images. Supports many languages and package managers. Integrate in your CI/CD pipeline with…. The licence is Apache-2.0.
When your agent uses it
- Asked to audit an SBOM
- Assess supply-chain
- Dependency risk
- Check for compromised
Example prompts
- “/bom-audit”
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- direct runtime dependencies
- explicit CycloneDX scope=required
- stronger source evidence via evidence.occurrences
- non-development ahead of development-only packages
- non-platform-specific ahead of platform-constrained packages
What it can do on your machine
Read from SKILL.md and the folder at commit e256966. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are bash).
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
cdxgen.github.io
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Bom Audit loads about 2.4k tokens when it runs. Until then it costs about 124 tokens; SKILL.md has 734 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from cdxgen/cdxgen at commit e256966, republished under its Apache-2.0 licence (© cdxgen). 734 words, ~2,410 tokens.
Download SKILL.mdSave it as
.claude/skills/bom-audit/SKILL.md (or your agent's skills folder).- name
- bom-audit
- description
- Runs supply-chain risk analysis on CycloneDX BOMs with cdx-audit predictive auditing and cdxgen --bom-audit embedded rules, covering npm and PyPI package compromise posture, CI permission risk, dependency source integrity, license policy violations, and SARIF or JSON reporting for code scanning. Use when asked to audit an SBOM, assess supply-chain or dependency risk, check for compromised or malicious packages, triage which dependencies to review first, or produce SARIF from a BOM.
Audit a BOM for supply-chain risk
Two distinct mechanisms. Choose deliberately.
| Want | Use |
|---|---|
| Findings embedded while the BOM is generated | cdxgen --bom-audit |
| Analysis of a BOM that already exists | cdx-audit |
| Forward-looking review prioritization for npm/PyPI | cdx-audit (predictive) |
| Rule evaluation against the supplied BOM itself | cdx-audit --direct-bom-audit |
Read reference/safety.md first. Predictive auditing clones upstream repositories and generates child SBOMs, so it does real network work — confirm with the user before a large run.
Predictive audit of an existing BOM
cdx-audit --bom /absolute/path/to/bom.json
cdx-audit --bom-dir /absolute/path/to/boms --report json --report-file /absolute/path/to/audit.json
cdx-audit --bom /absolute/path/to/bom.json --report sarif --report-file /absolute/path/to/audit.sarifReporters: console (default), json, sarif. Use SARIF for code-scanning
uploads.
Predictive mode extracts npm and PyPI package URLs from the BOM's components, generates a child SBOM for each upstream, and evaluates compromise posture. Cargo/Rust BOMs are also worth auditing this way when the goal is upstream review prioritization.
Exit code 3 means at least one target reached --fail-severity (default
high) or above. That is a policy signal, not a crash — report it as such.
Start narrow
For large BOMs or a triage-first workflow:
cdx-audit --bom /absolute/path/to/bom.json --scope required --max-targets 25| Flag | Effect |
|---|---|
--scope required | Only components with CycloneDX scope=required; a missing scope is treated as required |
--scope all | Default |
--max-targets <n> | Safety limit on unique npm/PyPI purls analyzed |
--min-severity | Filter console/SARIF output (low, medium, high, critical) |
--fail-severity | Severity that triggers exit code 3 (default high) |
Trusted publishing
# broader baseline, including packages that already carry trusted publishing metadata
cdx-audit --bom /absolute/path/to/bom.json --scope required --include-trusted --max-targets 50
# inspect only that subset
cdx-audit --bom /absolute/path/to/bom.json --only-trustedNever pass --include-trusted together with --only-trusted. Use
--include-trusted only when the user explicitly wants the broader baseline.
Reuse work across runs
cdx-audit --bom /absolute/path/to/bom.json \
--workspace-dir /absolute/path/to/workspace \
--reports-dir /absolute/path/to/reports--workspace-dir reuses cloned repositories and cached child SBOMs.
--reports-dir persists per-target artifacts plus an aggregate JSON report. Use
both when the user expects iterative analysis.
Other useful flags: --allowlist-file (purl prefixes to exclude from target
selection, on top of the built-in allowlist),
--skip-default-branch-recheck, --prioritize-direct-runtime,
--rules-dir for custom rules, and --introspect for a per-BOM build-fidelity
verdict inferred from BOM structure alone.
How the queue is ordered
Queue order is explainable. When trimmed, it prioritizes:
- direct runtime dependencies
- explicit CycloneDX
scope=required - stronger source evidence via
evidence.occurrences - non-development ahead of development-only packages
- non-platform-specific ahead of platform-constrained packages
These affect which packages are audited first, not final severity. Final severity comes from child SBOM findings plus conservative corroboration logic. Do not present queue position as a risk score.
Score rationale
CDXGEN_THINK_MODE=true cdx-audit --bom /absolute/path/to/bom.json --scope required --max-targets 10Prints lightweight score and rationale summaries per package.
Direct BOM audit
Evaluate rules against the supplied BOM itself rather than generating child SBOMs:
cdx-audit --bom /absolute/path/to/bom.json --direct-bom-audit
cdx-audit --bom /absolute/path/to/hbom.json --direct-bom-audit --categories hbom
cdx-audit --bom /absolute/path/to/aibom.json --direct-bom-audit --categories ai-bom
cdx-audit --bom /absolute/path/to/bom.evinse.json --direct-bom-audit --categories golemIn direct mode, --categories applies to the supplied BOM. Default is
obom-runtime for OBOMs and all categories otherwise. In predictive mode it
applies to the generated child SBOMs, defaulting to ai-agent,
ci-permission, dependency-source, package-integrity.
Embedded audit during generation
cdxgen -o /absolute/path/to/bom.json --bom-audit /absolute/path/to/project
cdxgen -o /absolute/path/to/bom.json --bom-audit --bom-audit-categories ci-permission /absolute/path/to/projectFindings land in the BOM's annotations[]. Related flags mirror cdx-audit:
--bom-audit-categories, --bom-audit-min-severity,
--bom-audit-fail-severity, --bom-audit-scope, --bom-audit-max-targets,
--bom-audit-include-trusted, --bom-audit-only-trusted,
--bom-audit-rules-dir.
Unknown categories are rejected, not ignored. Aliases such as ai-inventory
and hbom expand to their built-in category sets.
Show full SKILL.md (277 more words)Show less
Rule categories
| Category | Covers |
|---|---|
ci-permission | GitHub Actions/GitLab CI privilege and supply-chain risk |
dependency-source | Non-registry, local, or mutable dependency sources |
package-integrity | Deprecated, yanked, tampered, or suspicious packages |
golem-security | Go Evinse/Golem evidence findings |
asar-archive | Electron ASAR archive integrity and contents |
container-risk | Container image risk |
rootfs-hardening | Offline host repository trust, privileged helpers, service drift |
obom-runtime | Live OS runtime artifacts |
hbom-security | Hardware security posture |
host-topology | Merged hardware plus runtime host view |
mcp-server | MCP server exposure and auth posture |
ai-agent | AI instruction and skill files |
ai-inventory | Alias for ai-agent + mcp-server |
ai-bom | Umbrella AI-BOM pack |
ai-security, ai-governance, ai-performance | AI-specific rule packs |
ai-provenance | Alias enabling ai-provenance + ai-oversight |
cbom-security, cbom-compliance | Weak crypto, cipher modes, key sizes, protocol versions |
vscode-extension, chrome-extension | IDE and browser extension risk |
Aliases worth remembering: cbom / crypto-bom for both CBOM packs, hbom for
the full HBOM pack, ai-inventory for AI agent plus MCP.
Full rule tables with IDs and severities: https://cdxgen.github.io/cdxgen/#/BOM_AUDIT.
License policy
cdx-audit --bom /absolute/path/to/bom.json --license-policy /absolute/path/to/policy.yamlEvaluates every component license and reports prohibited and warning-level
violations as a separate table. Error-level (prohibited) violations cause a
non-zero exit, independent of --fail-severity.
cdxgen --license-policy applies the same policy at generation time.
Dry-run-friendly categories
In dry-run mode the formulation-centric categories are the ones that still
produce meaningful output, since they read declared configuration rather than
resolved dependency trees. ci-permission is the clearest example.
Reporting findings to the user
- Lead with what reached
--fail-severity, not with the total count. - Name the rule ID (
CI-002,PKG-007) so the user can look it up. - Say when a clean result reflects conservative analysis rather than proven absence — especially for MCP and AI categories.
- If exit code 3 fired, state which target caused it.
Exploring findings
In cdxi (see bom-explore): .auditfindings and .auditactions.
© cdxgen, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in claude-plugin/skills/bom-audit of cdxgen/cdxgen.
Open the folder on GitHubat commit e256966
Compare with similar skills
Bom Audit next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Bom Audit this skillcdxgen/cdxgen | 1.1k | — | ~2.4k | Automated safety check: Pass | Apache-2.0 | |
| Vex Authoringrelizaio/rearm | 127 | — | ~2.9k | Automated safety check: Pass | AGPL-3.0 | |
| Dependency Update Auditbacknotprop/plannotator | 9.2k | — | ~1.8k | Automated safety check: Pass | Apache-2.0 | |
| Supply Chain Risk Auditortrailofbits/skills | 7.4k | — | ~1.7k | Automated safety check: Notes | CC-BY-SA-4.0 | |
| Corpus Sweepnubjs/nub | 4.4k | — | ~2.4k | Automated safety check: Pass | MIT | |
| Dependency Auditbriiirussell/cybersecurity-skills | 413 | — | ~3.2k | Automated safety check: Warn | MIT |
Similar skills
Dependency Update Audit
backnotprop/plannotator
Audits outdated npm and Bun packages for supply chain integrity before bumping them, deferring risky ones and logging every decision.
- Official
Supply Chain Risk Auditor
trailofbits/skills
Audits a project's dependencies for supply-chain risk: version-matched advisories for direct dependencies and the full lockfile tree, abandoned or archived upstreams, npm publisher concentration…
Corpus Sweep
nubjs/nub
Run a large sharded measurement sweep over npm packages (the build-jail catalog probe, or any harness that installs thousands of package-versions and records a verdict per run).
Dependency Audit
briiirussell/cybersecurity-skills
Audit project dependencies, frameworks, languages, and dev tools for known vulnerabilities, CVEs, and security anti-patterns.
Platform Trust
inkline/inkline
Inkline's platform & trust surface — the styleframe license boundary, supply-chain and secrets hygiene, npm distribution integrity, and the future Studio/commercial direction.
More from cdxgen/cdxgen
All 17 skills in this repoAI Bom
cdxgen/cdxgen
Generates AI-BOM, MCP inventory, AI skill inventory, and AI authorship provenance documents with cdxgen, cataloging models, inference services, Hugging Face purls, MCP servers and their…
Bom Evidence
cdxgen/cdxgen
Enriches an existing CycloneDX BOM with occurrence, callstack, reachability, data-flow, and crypto-flow evidence using cdxgen evinse, including Go analysis via Golem and Rust analysis via Rusi, and…
Bom Explore
cdxgen/cdxgen
Explores and triages a CycloneDX BOM interactively with the cdxi REPL, using built-in commands for dependency trees, licenses, services, cryptographic assets, audit findings, evidence occurrences…
Bom Signing
cdxgen/cdxgen
Signs and verifies CycloneDX BOMs using cdxgen's native JSON Signature Format (JSF) implementation via cdx-sign and cdx-verify, supporting granular component, service, and annotation signatures…
Bom Convert Validate
cdxgen/cdxgen
Converts CycloneDX BOMs to SPDX 3.0.1 JSON-LD or between CycloneDX spec versions with cdx-convert, and validates BOMs against JSON schema, deep consistency checks, and OWASP SCVS and EU Cyber…
Bom Slimmer
cdxgen/cdxgen
Reviews a codebase's direct dependencies and designs lightweight, low-risk, zero-dependency custom replacements using cdxgen SBOM evidence, occurrence/callstack usage data, and license and…
Related
Works with
Categories
Questions about Bom Audit
What does Bom Audit do?
Runs supply-chain risk analysis on CycloneDX BOMs with cdx-audit predictive auditing and cdxgen --bom-audit embedded rules, covering npm and PyPI package compromise posture, CI permission risk…. Bom Audit is an agent skill from cdxgen/cdxgen. Runs supply-chain risk analysis on CycloneDX BOMs with cdx-audit predictive auditing and cdxgen --bom-audit embedded rules, covering npm and PyPI package compromise posture, CI permission risk, dependency source integrity, license policy violations, and SARIF or JSON reporting for code scanning.
When should I use Bom Audit?
Bom Audit fits situations like: asked to audit an SBOM; assess supply-chain; dependency risk; check for compromised.
How do I install Bom Audit in Claude Code?
Run `npx skills add cdxgen/cdxgen --skill bom-audit -a claude-code`. Or copy the skill folder (claude-plugin/skills/bom-audit in cdxgen/cdxgen) into .claude/skills/bom-audit in your project. Claude Code loads it when a task matches its description.
How do I install Bom Audit in Codex?
Run `npx skills add cdxgen/cdxgen --skill bom-audit -a codex`. Or copy the skill folder (claude-plugin/skills/bom-audit in cdxgen/cdxgen) into .agents/skills/bom-audit in your project. Codex loads it when a task matches its description.
Can I use Bom Audit in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add cdxgen/cdxgen --skill bom-audit -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/bom-audit, .gemini/skills/bom-audit, .github/skills/bom-audit and .opencode/skills/bom-audit in your project.
What does Bom Audit need to run?
SKILL.md names no scripts, command-line tools or credentials: Bom Audit is instructions for the agent only.
Does Bom Audit access the network?
SKILL.md names 1 domain. As links in the text: cdxgen.github.io. This is read from the text; nothing was executed.
Is Bom Audit safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Bom Audit use?
Bom Audit is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Bom Audit use?
About 2.4k tokens (SKILL.md is roughly 9.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Bom Audit?
Skills that share tags, products or a category with Bom Audit: Vex Authoring (relizaio/rearm, 127 stars), Dependency Update Audit (backnotprop/plannotator, 9.2k stars), Supply Chain Risk Auditor (trailofbits/skills, 7.4k stars) and Corpus Sweep (nubjs/nub, 4.4k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Bom Audit?
cdxgen (a GitHub organization) maintains it in cdxgen/cdxgen, which has 1,085 GitHub stars. The repository holds 17 skills in this directory. The repository was last updated on October 7, 2026.
Source: cdxgen/cdxgen on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.