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/logs)<a href="https://agentmods.dev/commands/aleksandarbisevac/claude-plugins/logs"><img src="https://agentmods.dev/badge/commands/aleksandarbisevac/claude-plugins/logs.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 | $0.00089 | $0.01509 |
| Opus 5 | $0.00044 | $0.00754 |
| Sonnet 5 | $0.00018 | $0.00302 |
| Haiku 4.5 | $0.00009 | $0.00151 |
Grade A, and why
logs scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/audit:logs — clean the feeds this plugin writes
Run
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/status/audit-logs.py" --project "$(pwd)" $ARGUMENTS
Print its stdout verbatim. Do NOT re-format, summarize or re-tabulate it. It already renders one line per fact with an aligned label column, and the two counts it exists to show are positional.
Pass $ARGUMENTS through unchanged. If the user typed no verb, pass prune — it is the
only one, and the command refuses a bare invocation on purpose (see below).
What it prunes, and what it will not
The file is <logsDir>/plan-gate-events.jsonl: one JSON line per verdict the plan gate
reaches, written by the hooks and rendered by the panel's Plan gate card. prune
removes the rows that no longer belong, in three named classes:
- outside this repository — the row's
fileresolves outside the consuming repo. The plugin manages and references only that repo, so such a row is not the feed's to keep. These can no longer be produced (the gates allow an out-of-scope path before recording it), so what is left is history to clear. - unreadable — the line is not a JSON object. The panel's reader already drops these silently, so they take up the file while showing up nowhere.
- older than DAYS — only when
--older-thanis given. There is no default, and that is a decision rather than an omission: the feed already self-trims by size, so age has no growth problem left to solve, and "old" is not the same claim as "does not belong" — a deny from last quarter is still a true record of this repo. A default here would be a number with no basis.
The blast radius is one file. Its path is derived from the same logsDir +
filename the writer uses, so no argument this command takes can widen it. The journal
(docs/audit/journal/) is deliberately out of reach: that is the tamper-evident trail, it
is append-only on purpose, and a command that could prune it could edit the evidence.
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.
- 7d ago First seen · 108 lines · 89 tokens per session scan A cbe5fcaf0194
logs is a command published in the GitHub repository AleksandarBisevac/claude-plugins (4 stars, last pushed 6d ago), licensed MIT. It adds 89 tokens to every session and 1,509 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 2026-08-31.
Other commands, from other repositories
post
Post the current OCR review to a GitHub PR.
show
Display a past OCR review session.
history
List past OCR review sessions.
overlay-apply
Apply NIST 800-53 overlays (FedRAMP, DoD, Privacy, etc.) to existing baselines.
sdlc
Master orchestrator for the complete 5-phase SDLC pipeline. Runs all phases sequentially with approval gates and handoffs between each phase. Organizes artifacts into handoffs/, docs/, and projects/ directories.
pillar-guidance
Deep dive guidance on DORA's 5 pillars and implementation requirements.