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/chohra-med/expo_boilerplateWrote 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/chohra-med/expo_boilerplate/review-code)<a href="https://agentmods.dev/commands/chohra-med/expo_boilerplate/review-code"><img src="https://agentmods.dev/badge/commands/chohra-med/expo_boilerplate/review-code.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 5.1 | $0.00050 | $0.01471 |
| Opus 5 | $0.00025 | $0.00736 |
| Sonnet 5 | $0.00010 | $0.00294 |
| Haiku 4.5 | $0.00005 | $0.00147 |
Grade A, and why
review-code 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.
How it starts
The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/review-code — read the rules, fix the changed files
This command reads every relevant code rule and best practice, finds what changed, and edits those files until they comply. Unlike /scan and /review-changes (read-only reports), /review-code applies the fixes.
Scope: $ARGUMENTS (default: uncommitted changes + branch diff vs base).
Procedure
1. Load the rules (read, don't skim)
Read the full enforceable rule set before touching code:
ai_rules/rules/frequent_rules.md← the most-violated rules + pre-commit checklist (READ FIRST)ai_rules/globalRules.md(routing) andai_rules/rules/best-practices.md- Then, per changed-file category, load only the matching packs (same mapping as
.claude/skills/best-practices-scan/SKILL.md§2):- screens/components →
design-system.md(+ Callstack RN: lists, re-renders, animations) - hooks →
best-practices.md(+ Callstack RN: atomic-state, profile-react) - store →
state-rtk.md· services →best-practices.md(+ Callstack RN: memory-leaks) - theme/tokens →
design-system.md§10 · tests →testing.md
- screens/components →
- Best-practices source: Callstack
react-native-best-practicesskill at~/.claude/plugins/marketplaces/callstack-agent-skills/skills/react-native-best-practices/references/
2. Gather scope
Same scoping as the scan skill:
BASE=$(git remote show origin 2>/dev/null | awk '/HEAD branch/{print $NF}') # often development or main
git diff --name-only "${BASE:-main}...HEAD"
git status --porcelain | awk '{print $2}'
Combine + dedupe. Exclude node_modules/, ios/, android/, dist/, coverage/, .expo/, lock files, generated files.
Overrides: staged → git diff --cached; session → files touched this session; file:<path> → one file; branch → branch diff only; all → full tree (slow, ask first). If scope is empty → say "no changes to review" and stop.
3. Detect, then FIX (surgical only)
For each changed file, find violations (static greps from the scan skill §3 + AI-judgment §4) and edit the file to fix them. Touch only what the rule requires — do not reformat or refactor unrelated lines. Apply at minimum:
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.
- 8d ago First seen · 67 lines · 50 tokens per session scan A c9e3b6a19eae
review-code is a command published in the GitHub repository chohra-med/expo_boilerplate (32 stars, last pushed 6d ago), licensed MIT. It adds 50 tokens to every session and 1,471 once invoked, about $0.0003 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
arc-audit
Audit a React Native Expo project for mobile UX issues, performance problems, and architecture violations. Use to check code quality against arc-skill best practices. Trigger when the user asks to review code, check for issues, wants a health check, mentions touch targets, accessibility, performance audit, or says 'is…
prp-commit
Quick commit with natural language file targeting: describe what to commit in plain English.
resolve_pr_parallel
Resolve all PR comments using parallel processing.
pr-description
Write a pull request description that helps reviewers: what changed, why, and how to verify, from a diff.
unforgit-curate
Review and improve Unforgit memory quality.
pr-package
Prepare a clean delivery package for GitHub from the real git diff vs an explicit base branch, persisted as PRPACKAGE.md (or PRPACKAGE. .md for multi-repo tasks). Produces branch name, commit messages, fetch, checkout, add, commit, and push commands, PR title and body, and reviewer attention points; never invents work…