Is the Auditing skill free?

Yes. The skill itself is free from OdradekAI/bundles-forge. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Auditing SkillProof Score?

8.8/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 5/5.

How do I install Auditing?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Auditing with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Auditing

Scores a bundle-plugin or skill for structure, quality, and security, with a diagnostic report

by OdradekAI · OdradekAI/bundles-forge

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 8.8/10
Tested: Jul 31, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 59891a5

Cloned the repo and ran the actual `bundles-forge audit-skill --json` CLI (pure Python 3.9+, no external deps) twice. On the auditing skill itself it returned overall_score 6.8, exit 0, flagging Q16 (external CLI declared but no Prerequisites section). I then planted a deliberately flawed skill (dir 'mytool' vs name 'data-exporter', terse description, a `cat ~/.ssh/id_rsa` and curl exfiltration); the tool correctly returned status FAIL, exit 2, and specific check IDs S9, Q5, Q10/Q11, and SC1 critical (sensitive file ref at SKILL.md:11). Baseline ad-hoc prose review caught the ssh/curl danger but produced no reproducible score, exit code, or convention-level checks (Q5 'Use when', S9). Note: the scanner false-positives on its own audit_security.py pattern definitions, which the docs honestly acknowledge as a static-matcher limitation; friction is that the `bundles-forge` command is not inside the skill folder, so the whole repo/plugin must be installed.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 7/10
Docs & honesty 5/5

What Auditing does

Runs a scored diagnostic audit over a Claude Code bundle-plugin project or a single skill, checking structure, version sync, skill quality, cross-references, workflow integration, and security patterns, then emits a categorized report. Auto-detects scope (full project vs single skill vs workflow) from the target path. Triggers when the user asks to audit, security-scan, or quality-check a bundle-plugin or a SKILL.md before releasing, after changes, or after adding third-party skills.

How to install Auditing

git clone --depth 1 https://github.com/OdradekAI/bundles-forge.git /tmp/auditing-src
mkdir -p ~/.claude/skills
cp -R /tmp/auditing-src/skills/auditing ~/.claude/skills/auditing
# The skill drives the `bundles-forge` CLI, which lives at repo root (/tmp/auditing-src/bin/bundles-forge),
# NOT inside the skill folder. Pure Python 3.9+, zero pip deps.
# Make the command available:  export PATH="/tmp/auditing-src/bin:$PATH"
# Or call a check directly:    python /tmp/auditing-src/skills/auditing/scripts/audit_skill.py --json <skill-dir>
# Full-project audit (audit_plugin) also needs skills/releasing/scripts/bump_version.py from the same repo,
# which is why cloning the whole repo (not just the skill dir) is required.

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Auditing

/auditing Scores a bundle-plugin or skill for structure, quality, and security, with a diagnostic report

It also activates on plain-language prompts like these:

Audit this bundle-plugin before release
Check for version drift across these skills
Review this workflow integration for security risks

Frequently asked questions

Is the Auditing skill free?: Yes. The skill itself is free from OdradekAI/bundles-forge. SkillProof publishes the install command and an independent test verdict at no cost.
Does Auditing work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 31, 2026. Verdict: Tested · Works. Cloned the repo and ran the actual `bundles-forge audit-skill --json` CLI (pure Python 3.9+, no external deps) twice. On the auditing skill itself it returned overall_score 6.8, exit 0, flagging Q16 (external CLI declared but no Prerequisites section). I then planted a deliberately flawed skill (dir 'mytool' vs name 'data-exporter', terse description, a `cat ~/.ssh/id_rsa` and curl exfiltration); the tool correctly returned status FAIL, exit 2, and specific check IDs S9, Q5, Q10/Q11, and SC1 critical (sensitive file ref at SKILL.md:11). Baseline ad-hoc prose review caught the ssh/curl danger but produced no reproducible score, exit code, or convention-level checks (Q5 'Use when', S9). Note: the scanner false-positives on its own audit_security.py pattern definitions, which the docs honestly acknowledge as a static-matcher limitation; friction is that the `bundles-forge` command is not inside the skill folder, so the whole repo/plugin must be installed.
What is the Auditing SkillProof Score?: 8.8/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 5/5.
How do I install Auditing?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Auditing with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.