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/synaptiai/synapti-marketplaceWrote 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/synaptiai/synapti-marketplace/gh-review)<a href="https://agentmods.dev/commands/synaptiai/synapti-marketplace/gh-review"><img src="https://agentmods.dev/badge/commands/synaptiai/synapti-marketplace/gh-review/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/synaptiai/synapti-marketplace/gh-review"><img src="https://agentmods.dev/badge/commands/synaptiai/synapti-marketplace/gh-review.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 | $0.01627 |
| Opus 5 | $0.00000 | $0.00813 |
| Sonnet 5 | $0.00000 | $0.00325 |
| Haiku 4.5 | $0.00000 | $0.00163 |
Grade A, and why
gh-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review PR #$ARGUMENTS
Review a pull request with proper branch checkout and convention checks.
Tool Usage: This workflow uses the AskUserQuestion tool to confirm review decisions, clarify ambiguous findings, and get approval before submitting reviews.
Process
-
Save current branch:
git branch --show-current -
Fetch PR details and any existing reviews/comments:
gh pr view $ARGUMENTS --json title,body,headRefName,baseRefName,additions,deletions,changedFiles,commits,files,reviews gh api repos/synaptiai/synapti-marketplace/pulls/$ARGUMENTS/comments -
Fetch PR conversation (general discussion comments):
gh api repos/{owner}/{repo}/issues/$ARGUMENTS/comments -
Extract and fetch linked issue:
# Extract issue number from PR body (looks for "closes #X", "fixes #X", etc.) gh pr view $ARGUMENTS --json body --jq '.body' | grep -oiE '(closes|fixes|resolves)\s*#[0-9]+' | grep -oE '[0-9]+'If linked issue found:
# Fetch full issue with acceptance criteria gh issue view {linked-issue} --json title,body,comments # Fetch all issue comments gh api repos/{owner}/{repo}/issues/{linked-issue}/comments -
Cross-reference checklist: Create a verification list from issue acceptance criteria to check against implementation
-
If previous reviews or comments exist: This is a follow-up review. You MUST:
- Read through ALL previous review comments
- Track each piece of feedback that was given
- Later verify each item was addressed (fixed or explained)
- Note: You're still doing a FULL review - previous reviewers may have missed things
-
Checkout the PR branch (CRITICAL - never review from wrong branch):
git fetch origin {headRefName} git checkout {headRefName} -
Get the full diff:
gh pr diff $ARGUMENTS -
Read all changed files - use the Read tool on each modified file to understand the full context
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.
- 11d ago First seen · 223 lines · 0 tokens per session scan A d388a6baefbd
gh-review is a command published in the GitHub repository synaptiai/synapti-marketplace (6 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,627 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
create-worktree
Follow these steps to create a git worktree.
release
Release manager for frontend and mobile. Writes App Store notes, user-facing changelog, flags stale docs and landing copy. Actions: notes | changelog | docs | sync.
pr
Prepare and open a pull request the senior way: gate, template, scrubbed, everything visible.
status
The state of play, computed fresh: branch, dirty files, the active sprint, open work, index freshness.
triage
Triages a PR comment — from a bot (Copilot, CI) or a human reviewer. Fetches the comment and diff via gh CLI, classifies it, applies the fix directly to the file if valid, posts a reply on the thread, and resolves it. Run from inside the repo.
done
Finish a task - document, create PR or merge, close.