Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add LucasDuys/forge/plugin install forgeWrote 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/commands/lucasduys/forge/skills-audit)<a href="https://agentmods.dev/commands/lucasduys/forge/skills-audit"><img src="https://agentmods.dev/badge/commands/lucasduys/forge/skills-audit.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00021 | $0.00639 |
| Opus 5 | $0.00010 | $0.00319 |
| Sonnet 5 | $0.00004 | $0.00128 |
| Haiku 4.5 | $0.00002 | $0.00064 |
Grade A, and why
skills-audit scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Forge Skills Audit
List every skill and slash-command visible to the current Forge install, with source + path + status. Output is designed to be copy-paste-ready into a "skills cleanup" PR description.
How to run
Invoke the inventory script. Default output is a fixed-width table; pass
--json for machine-readable output.
node "${CLAUDE_PLUGIN_ROOT}/scripts/forge-skills-audit.cjs"
The script walks:
~/.claude/skills/— user-level skills (sourceuser-skills, plusarchivedwhen the path sits under_archived-*/orarchived/).~/.claude/plugins/cache/<marketplace>/<plugin>/<ver>/skills/— every plugin-shipped skill (sourceplugin:<plugin>).~/.claude/commands/— user-level slash commands.~/.claude/plugins/cache/<marketplace>/<plugin>/<ver>/commands/— every plugin-shipped command.
Status values
| Status | Meaning |
|---|---|
| active | Healthy, loadable, not flagged. |
| duplicate | Same name appears in ≥ 2 sources (e.g. user-skills and a plugin, or two plugins). Resolve by deleting the stale copy. |
| deprecated | SKILL.md description starts with Deprecated. The skill loader may still pick it up; prefer the replacement noted in the description. |
| archived | Path contains _archived-*/ or archived/. Kept for reference; should not be invoked. |
Presenting the result
Render the table output verbatim under a ### Skills Audit (<date>) heading
in the PR description. Follow it with the summary line the script prints
(totals: ... + status: ...). Call out any duplicate rows as action
items for the cleanup PR.
If a user asks for JSON (or wants to pipe the output into another tool), run:
node "${CLAUDE_PLUGIN_ROOT}/scripts/forge-skills-audit.cjs" --json
Edge cases
- If the script exits non-zero, read stderr; the most common cause is a
corrupt
plugin.jsonorSKILL.mdthat broke the underlyingdiscoverCapabilitieswalk. Surface the error to the user; do not try to "fix" the skill file from this command. - If the table is empty,
~/.claude/probably does not exist on this machine (e.g. running inside an ephemeral sandbox). Let the user know. - Never use em dashes in generated output (per project style).
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.
- 6d ago First seen · 62 lines · 21 tokens per session scan A b46b40e3ef06
skills-audit is a command published in the GitHub repository LucasDuys/forge (55 stars, last pushed 1mo ago), licensed MIT. It adds 21 tokens to every session and 639 once invoked, about $0.0001 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.
Other commands, from other repositories
pull-repos
Pull all repos (parent + marketplace clones + configured project repos).
security-scan
Run security audit on codebase.
test-suite
Run comprehensive test suite with coverage analysis.
standardize-claude-md
Add missing toolkit sections (Related Global Rules, Quick Start) to existing CLAUDE.md.
help
Explain Ralph Wiggum technique and available commands.
spreadsheet-audit
Perform a 6-step audit of an Excel spreadsheet for formula correctness, formatting consistency, data integrity, boss-auditable simplicity, and spec compliance. Uses the excel-screenshot MCP server tools — no Excel installation required.