Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/AleksandarBisevac/claude-pluginsWrote 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/guide)<a href="https://agentmods.dev/commands/aleksandarbisevac/claude-plugins/guide"><img src="https://agentmods.dev/badge/commands/aleksandarbisevac/claude-plugins/guide/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/guide"><img src="https://agentmods.dev/badge/commands/aleksandarbisevac/claude-plugins/guide.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 | $0.00043 | $0.00320 |
| Opus 5.5 | $0.00017 | $0.00128 |
| Sonnet 5.5 | $0.00009 | $0.00064 |
| Haiku 4.5 | $0.00004 | $0.00032 |
Grade A, and why
guide 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 1mo 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.
What it actually says
/audit:guide — ask the plugin about itself
Spawn the plugin's guide agent (Agent tool, subagent_type: "audit:guide") with the
user's question as the prompt, verbatim:
$ARGUMENTS
- If the question above is empty, do not spawn anything. Ask the user what they want to
know about the plugin (one line), and mention the zero-token alternative: the panel's help
drawer (
/audit:panel) already carries every config key's description. - Relay the agent's answer as-is, citations included. Do not answer from your own knowledge and do not strip the citations — a claim about what the gate does is only worth keeping if it names the doc line it came from.
- The agent is mechanically read-only (Read/Grep/Glob) and cheap (
model: haiku); it never changes anything, so there is nothing to confirm with the user before spawning it.
The conversational half of the plugin's help lives here; the zero-token half is the panel's help drawer. When the drawer answers the question, prefer pointing there — it costs nothing.
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.
- 1mo ago Changed · +1 lines 50e32569e174
- 1mo ago First seen · 27 lines · 43 tokens per session scan A c56ac4f00e21
guide is a command published in the GitHub repository AleksandarBisevac/claude-plugins (4 stars, last pushed yesterday), licensed MIT. It adds 43 tokens to every session and 320 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 2026-08-31.
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.