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/Jamie-BitFlight/claude_skillsWrote 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/jamie-bitflight/claude_skills/arl-expert-panel)<a href="https://agentmods.dev/commands/jamie-bitflight/claude_skills/arl-expert-panel"><img src="https://agentmods.dev/badge/commands/jamie-bitflight/claude_skills/arl-expert-panel/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/jamie-bitflight/claude_skills/arl-expert-panel"><img src="https://agentmods.dev/badge/commands/jamie-bitflight/claude_skills/arl-expert-panel.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 | $0.00019 | $0.01610 |
| Opus 5 | $0.00010 | $0.00805 |
| Sonnet 5 | $0.00004 | $0.00322 |
| Haiku 4.5 | $0.00002 | $0.00161 |
Grade A, and why
arl-expert-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 12d 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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ARL Expert Panel
You are the orchestrator for the Autonomous Refinement Loop (ARL) expert panel process.
Step 0: Load the Protocol
Read the full instructions document:
plugins/plugin-creator/skills/arl/references/ARL-agent-instructions.md
This document is the protocol for the entire process. Every decision you make must align with it. Do not proceed until you have read it completely.
Step 1: Load the Research Context
Read both primary research files referenced in the instructions:
plugins/plugin-creator/skills/arl/references/autonomous-refinement-loop-research.md
plugins/plugin-creator/skills/arl/references/human-out-of-loop-prerequisites.md
Step 2: Detect Session State
Determine whether this is a fresh start or a continuation.
Check for an existing Q&A file:
Search for files matching **/arl/references/qa-*.md or **/arl/references/QA-*.md in the repository.
If no Q&A file exists — FRESH START:
- Report to the user: "No prior Q&A file found. Starting the expert panel from Phase 1."
- Create the Q&A file at:
plugins/plugin-creator/skills/arl/references/qa-expert-panel.md - Initialize it with a header, the date, and a section for each question group from Section 6 of the instructions (marked as "NOT YET DISCUSSED").
- Proceed to Step 3.
If a Q&A file exists — CONTINUATION:
- Read the Q&A file completely.
- Identify which question groups have been discussed and which have not.
- Identify which R-requirements (R1–R10) have been addressed and which have not.
- Identify which phase the process is in (Phase 1, 2, 3, or 4).
- Report to the user: "Found existing Q&A file. Phase [N] in progress. [X/5] question groups discussed. [Y/10] R-requirements addressed. Resuming from [specific point]."
- Proceed to the appropriate step.
Step 3: Ensure Framework Repositories
Before checking prerequisites, read the repo manifest:
plugins/plugin-creator/skills/arl/references/expert-repos.md
For each repository listed in the manifest (except sam-expert which is in-repo):
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.
- 12d ago First seen · 156 lines · 19 tokens per session scan A eabf714b1946
arl-expert-panel is a command published in the GitHub repository Jamie-BitFlight/claude_skills (66 stars, last pushed today), licensed MIT. It adds 19 tokens to every session and 1,610 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
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.