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 AleksandarBisevac/claude-plugins/plugin install auditWrote 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/aleksandarbisevac/claude-plugins/version)<a href="https://agentmods.dev/commands/aleksandarbisevac/claude-plugins/version"><img src="https://agentmods.dev/badge/commands/aleksandarbisevac/claude-plugins/version/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/commands/aleksandarbisevac/claude-plugins/version"><img src="https://agentmods.dev/badge/commands/aleksandarbisevac/claude-plugins/version.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00055 | $0.00676 |
| Opus 5.5 | $0.00022 | $0.00270 |
| Sonnet 5.5 | $0.00011 | $0.00135 |
| Haiku 4.5 | $0.00006 | $0.00068 |
Grade A, and why
version scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 21d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/audit:version — which build is running, and is there a newer one
Run
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/status/audit-version.py" $ARGUMENTS
Print its stdout verbatim, in your own reply and inside a fenced block — a tool result is collapsed behind the tool call, so running the command is not delivering it. Do NOT re-format, summarize or re-tabulate it: every line carries the file or service it was read from, and a summary that drops those sources drops the thing that makes the lines checkable.
Pass $ARGUMENTS through unchanged. --offline skips the network; --json prints one object.
What it reads
- running — the
plugin.jsonof the copy this command runs from, with its path. - marketplace — the marketplace this copy was installed from, what that clone offers,
when it was last refreshed, and whether it auto-updates. Read from Claude Code's own
record (
known_marketplaces.jsonunderCLAUDE_CONFIG_DIR, else~/.claude) — a file Claude Code writes and does not document, which the line says. A copy run from a checkout names no marketplace, and says where it runs from. - installed — every installed copy of this plugin, by scope and project, with those older
than the running copy marked (
installed_plugins.json, the same caveat). - published — the newest release on the repository
plugin.jsonnames: one unauthenticated request to the GitHub API, five seconds at most, and nothing about your project is sent (SECURITY.md→ Outbound network). An unreachable feed is reported as such.
What it concludes
The verdict is drawn only from what was read: up to date, a newer release is published (exit 1, so a script can ask), running ahead of the newest release (an unreleased build), or could not be asked — never "up to date" when the feed did not answer. When a newer release is published and the marketplace is known, it prints the commands:
claude plugin marketplace update <marketplace>
claude plugin update audit@<marketplace>
then restart Claude Code (or run /reload-plugins)
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.
- 21d ago First seen · 55 lines · 55 tokens per session scan A fd525495e39f
version is a command published in the GitHub repository AleksandarBisevac/claude-plugins (4 stars, last pushed 3d ago), licensed MIT. It adds 55 tokens to every session and 676 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-28.
Other commands, from other repositories
post
Post the current OCR review to a GitHub PR.
show
Display a past OCR review session.
overlay-apply
Apply NIST 800-53 overlays (FedRAMP, DoD, Privacy, etc.) to existing baselines.
pillar-guidance
Deep dive guidance on DORA's 5 pillars and implementation requirements.
dpia
Data Protection Impact Assessment (DPIA) guidance and execution.
research
Start or resume an academic research project — idea through literature, methodology, writing, feedback, and publishing.