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.
npx agentmods add commands/saski/arnesto/review-prgit clone --depth 1 https://github.com/saski/arnestoWrote 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/saski/arnesto/review-pr)<a href="https://agentmods.dev/commands/saski/arnesto/review-pr"><img src="https://agentmods.dev/badge/commands/saski/arnesto/review-pr.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 | $0.00000 | $0.03368 |
| Opus 5 | $0.00000 | $0.01684 |
| Sonnet 5 | $0.00000 | $0.00674 |
| Haiku 4.5 | $0.00000 | $0.00337 |
Grade A, and why
review-pr 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 5d 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 — 497 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review PR
Command: /review-pr
Provides an interactive, AI-assisted code review experience that helps reviewers understand changes, ask questions, provide feedback, and optionally implement fixes directly in the IDE.
What This Command Does
This command orchestrates a comprehensive PR review workflow:
- Checks out the PR branch locally
- Analyzes all changes in the PR
- Reads the PR review document (if available)
- Summarizes changes at a high level
- Offers post-summary options including file-by-file walkthrough
- Allows questions and comments as you go
- Posts line-specific comments via GitHub API
- Enables direct fixes with optional sub-PRs
- Tracks review time for metrics
Workflow Steps
Phase 0: Initialize Review
- Ask for PR number or URL
- Record review start timestamp
- Create review tracking: `.pr-review-metrics.json`
- Fetch PR details using gh CLI
- Checkout PR branch
- Pull latest changes
Phase 1: Analysis & Summary
- Identify all changed files using git diff
- Read PR_REVIEW_DOC.md if it exists (or similar PR description document)
- Analyze complexity of changes
- Generate high-level summary:
- What changed and why
- Key files modified
- Complexity concerns
- Test coverage status
- Blocking issues flagged by submitter
- Present summary to reviewer
Phase 2: Post-Summary Options
After presenting the summary, offer these options:
=== Review Options ===
How would you like to proceed?
1. **File-by-file walkthrough** - See each file's diff one at a time with "next" navigation
2. **Show all diffs at once** - Display all changes in one view
3. **Jump to specific file** - Go directly to a file of interest
4. **Ask questions first** - Discuss the changes before diving in
5. **Post a general comment** - Add a PR-level comment
Choose option (1/2/3/4/5):
Phase 3: File-by-File Walkthrough
When the user chooses the file-by-file walkthrough:
For each changed file (1 of N):
- Show file path, lines added/removed
- Display summary of changes in that file
- Show the diff with syntax highlighting
- Wait for user input before proceeding
User can respond with:
- "next" - Move to next file
- "skip" - Skip to next file without commenting
- "comment [line#] <message>" - Add line-specific comment
- "question" - Ask about this file
- "fix this" - Propose or implement a fix
- "show full" - Show full diff without truncation
- "done" - Exit walkthrough and go to completion
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.
- 5d ago First seen · 497 lines · 0 tokens per session scan A 58aa47105fc8
review-pr is a command published in the GitHub repository saski/arnesto (5 stars, last pushed 9d ago), licensed Unlicense. It costs nothing until one of its globs matches a file; then it loads 3,368 tokens. 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
ops-sweep
Sweep all repos/sessions via git deltas and refresh the Agentic Ops Ledger (low-token). Use at session end, or when asked to update the ledger, document progress, or recommend next prompts.
santa-loop
Adversarial dual-review convergence loop — two independent model reviewers must both approve before code ships.
milestone-list
PitWay: List every milestone with a concise one-line status.
fix
Universal debugging and fix application with semantic code analysis.
harness-adopt
Apply Harness Starter Kit to the current target repository with the prompt-first adoption workflow.
make-this
Install the Multi-Agent Loop Kit into the current repo and run the setup interview.