agentmods.dev

panel

panel is a command for Claude Code from AleksandarBisevac/claude-plugins. It costs 79 tokens per session (4,042 once invoked), scanned A, original, MIT.

A local control-panel command for visually managing audit configuration and the manifest's composition settings. It can open, stop, or report the status of the panel, which discovers available skills and agents.

In plain words
What is it for?
Use it to open the audit panel, check its current status, stop it, or adjust review skills, task-specific skills and models, and build commands.
Why use it?
It avoids editing configuration files by hand and provides live validation while changing the audit setup. The status command also shows whether the panel is running and where to access it.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; mentions subagents; mentions Claude Code.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the audit plugin — 2 skills, 20 commands, 4 agents, 4 hooks shipped together

not rated 4repo today A scan 79 tokens original MIT

Good fit Use it to open the audit panel, check its current status, stop it, or adjust review skills, task-specific skills and models, and build commands.

Compare 6 commands from other repositories ↓
View source ↗ AleksandarBisevac/claude-plugins aleksandarbisevac.github.io
Install

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.

Claude Code
/plugin marketplace add AleksandarBisevac/claude-plugins
Claude Code
/plugin install audit

Made for: Claude Code.

Or install audit, the plugin that ships this one along with the rest of its 2 skills, 20 commands, 4 agents, 4 hooks.

Wrote 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.

agentmods badge for panel

README.md
[![agentmods](https://agentmods.dev/badge/commands/aleksandarbisevac/claude-plugins/panel.svg)](https://agentmods.dev/commands/aleksandarbisevac/claude-plugins/panel)
Your own site
<a href="https://agentmods.dev/commands/aleksandarbisevac/claude-plugins/panel"><img src="https://agentmods.dev/badge/commands/aleksandarbisevac/claude-plugins/panel.svg" alt="Measured on agentmods" height="20"></a>
Per session 79 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,042 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00079 $0.04042
Opus 5 $0.00039 $0.02021
Sonnet 5 $0.00016 $0.00808
Haiku 4.5 $0.00008 $0.00404

Measured 8d ago against content hash ffd0487e45e7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

panel 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 8d 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.

plugins/audit/commands/panel.md · 209 lines

How it starts

The opening of the file, as written. The whole thing — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/audit:panel — the control panel (open · stop · status)

Read ${CLAUDE_PLUGIN_ROOT}/reference/manifest-conventions.md first (read-only preflight 1–2; no lock — the panel itself takes the manifest lock only when it writes the manifest, and refuses if one is held). Let PANEL="${CLAUDE_PLUGIN_ROOT}/scripts/panel/panel-server.py".

Dispatch on $ARGUMENTS:

  • stop → run python3 "$PANEL" --project "$(pwd)" --stop and print the result.
  • status → run python3 "$PANEL" --project "$(pwd)" --status and print the result.
  • otherwise (open) →
    1. Launch it detached so it survives this turn, passing --port <n> through from $ARGUMENTS if given. Stderr goes to a per-project log, never to /dev/null — see Why the launch keeps its stderr below; the append (2>>) and the log's name are both load-bearing, so copy the two lines as they stand: 
      mkdir -p "$(pwd)/.claude"
nohup python3 "$PANEL" --project "$(pwd)" >/dev/null 2>>"$(pwd)/.claude/audit-panel.log" &
    2. Wait ~1s, then read the live URL back: 
      sleep 1; python3 "$PANEL" --project "$(pwd)" --status
    3. Tell the user exactly what --status said, and nothing it did not say. It reports one of three states and they are not interchangeable:
      • panel RUNNING: <url> (PID n) → the panel is up; their browser opens automatically. Stop it anytime with /audit:panel stop (or /audit:panel status to check). It's per-project — launching again just points at the already-running one, so it never leaves an untracked process behind.
      • panel not running with an its last launch left this on stderr … line → the launch FAILED and that line is the reason. Report the reason; do not report a launch.
      • panel not running with no such line → nothing was started and nothing was recorded.
    4. If --status prints stop and relaunch to pick it up, say so: the panel that is up assembled its page from an older build of the plugin, and the controls that shipped since are missing from it until it is stopped and started again.

Read the full file on GitHub · 209 lines

Changes

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.

  1. 8d ago First seen · 209 lines · 79 tokens per session scan A ffd0487e45e7

Subscribe to this mod's changes

panel is a command published in the GitHub repository AleksandarBisevac/claude-plugins (4 stars, last pushed today), licensed MIT. It adds 79 tokens to every session and 4,042 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.

Claude Codeagentic-aiauditazure-devopsclaude-code-pluginclaude-code-plugins-marketplace
Related

Other commands, from other repositories

post

Post the current OCR review to a GitHub PR.

spencermarx/open-code-review · 11 tokens

show

Display a past OCR review session.

spencermarx/open-code-review · 7 tokens

history

List past OCR review sessions.

spencermarx/open-code-review · 6 tokens

overlay-apply

Apply NIST 800-53 overlays (FedRAMP, DoD, Privacy, etc.) to existing baselines.

GRCEngClub/claude-grc-engineering · 24 tokens

pillar-guidance

Deep dive guidance on DORA's 5 pillars and implementation requirements.

GRCEngClub/claude-grc-engineering · 13 tokens

dpia

Data Protection Impact Assessment (DPIA) guidance and execution.

GRCEngClub/claude-grc-engineering · 12 tokens