Borrowing it
Nothing to install: this file belongs to TheAstrelo/Claude-Pipeline. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/TheAstrelo/Claude-Pipeline/main/.claude/commands/ar.mdgit clone --depth 1 https://github.com/TheAstrelo/Claude-PipelineWrote 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/theastrelo/claude-pipeline/ar)<a href="https://agentmods.dev/commands/theastrelo/claude-pipeline/ar"><img src="https://agentmods.dev/badge/commands/theastrelo/claude-pipeline/ar/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/theastrelo/claude-pipeline/ar"><img src="https://agentmods.dev/badge/commands/theastrelo/claude-pipeline/ar.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 | $0.00000 | $0.00590 |
| Opus 5.5 | $0.00000 | $0.00236 |
| Sonnet 5.5 | $0.00000 | $0.00118 |
| Haiku 4.5 | $0.00000 | $0.00059 |
Grade B, and why
ar scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
SESSION_DIR=$(cat .claude/artifacts/current.txt 2>/dev/null) How it starts
The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run adversarial review on the current design.
Prerequisites
Check that design exists:
SESSION_DIR=$(cat .claude/artifacts/current.txt 2>/dev/null)
if [ -z "$SESSION_DIR" ] || [ ! -f "$SESSION_DIR/design.md" ]; then
echo "ERROR: No design.md found. Run /design first."
exit 1
fi
If no design exists, stop and tell the user to run /design first.
Adversarial Review
Use the adversarial-coordinator agent.
Input: Read design.md from the current session directory.
Process:
Run 3 critique passes with different perspectives:
Pass 1: Architect Critic
- Focus: Scalability, coupling, consistency, performance
- Question: "What architectural flaws exist? What scales poorly?"
Pass 2: Skeptic Critic
- Focus: Edge cases, error states, security, concurrency
- Question: "What assumptions are untested? What edge cases break this?"
Pass 3: Implementer Critic
- Focus: Clarity, types, state management, testability
- Question: "What's ambiguous? What will cause bugs during build?"
After all passes, synthesize findings and identify consensus issues.
Severity Levels
- HIGH: Production bugs, security issues, or architectural debt
- MEDIUM: Developer friction, maintenance burden, or edge case failures
- LOW: Style preferences or theoretical concerns
Verdict Rules
REVISE_DESIGN if:
- Any HIGH severity issue
- 3+ MEDIUM severity issues
- Consensus issue (raised by 2+ critics)
APPROVED if:
- No HIGH issues
- Fewer than 3 MEDIUM issues
- All concerns are LOW or mitigated
Output
After review, report:
## Adversarial Review Complete
**Session:** {session-directory}
**Verdict:** [APPROVED | REVISE_DESIGN]
### Consensus Issues
[Issues raised by multiple critics - highest priority]
### High Severity
[List any HIGH severity issues]
### Summary
- Architect: [N issues]
- Skeptic: [N issues]
- Implementer: [N issues]
### Next Step
[If APPROVED] Run `/plan` to create the implementation plan.
[If REVISE_DESIGN] Address the required changes and run `/design` again.
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.
- 2mo ago First seen · 112 lines · 0 tokens per session scan B 138deae50783
ar is a command published in the GitHub repository TheAstrelo/Claude-Pipeline (47 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 590 tokens. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
review-pr
Comprehensive PR review using specialized agents.
code-review
Code review a pull request.
refactor-clean
Refactor provided code for cleanliness, maintainability, and alignment with SOLID principles and modern best practices — no over-engineering.
review-branch
Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.
audit
Audit closed tickets for regressions against today's code (unchanged, evolved, implemented wrong, not implemented), plus duplicate and groupable open ones.
rev
Invoke Code Reviewer for code quality, security, requirements validation, and best practices review.