gh-start-auto

gh-start-auto is a command for Claude Code from synaptiai/synapti-marketplace. It costs 31 tokens per session (5,664 once invoked), scanned B, original, Apache-2.0.

An automated path from a GitHub issue to a pull request, including implementation, repeated review and repair, and final approval to create the pull request.

In plain words
What is it for?
Use it to assign an issue, create a branch, implement the requested change, run review-and-fix cycles, check acceptance criteria and quality gates, and create a pull request.
Why use it?
It removes much of the manual coordination between starting work, checking the result, fixing review findings, and preparing a merge request.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; mentions CLAUDE.md; names the AskUserQuestion tool.

Part of the gh-workflow plugin — 4 skills, 5 commands shipped together

Good fit Use it to assign an issue, create a branch, implement the requested change, run review-and-fix cycles, check acceptance criteria and quality gates, and create a pull request.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/synaptiai/synapti-marketplace/gh-start-auto
Install

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.

Clone the repo
git clone --depth 1 https://github.com/synaptiai/synapti-marketplace

Made for: Claude Code.

Or install gh-workflow, the plugin that ships this one along with the rest of its 4 skills, 5 commands.

Wrote 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.

agentmods badge for gh-start-auto

README.md
[![agentmods](https://agentmods.dev/badge/commands/synaptiai/synapti-marketplace/gh-start-auto/github.svg)](https://agentmods.dev/commands/synaptiai/synapti-marketplace/gh-start-auto)
Your own site
<a href="https://agentmods.dev/commands/synaptiai/synapti-marketplace/gh-start-auto"><img src="https://agentmods.dev/badge/commands/synaptiai/synapti-marketplace/gh-start-auto/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.

agentmods 80×15 button for gh-start-auto

Your own site · 80×15
<a href="https://agentmods.dev/commands/synaptiai/synapti-marketplace/gh-start-auto"><img src="https://agentmods.dev/badge/commands/synaptiai/synapti-marketplace/gh-start-auto.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,664 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00031 $0.05664
Opus 5 $0.00015 $0.02832
Sonnet 5 $0.00006 $0.01133
Haiku 4.5 $0.00003 $0.00566

Measured today against content hash 87d7af2aedcb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade B, and why

gh-start-auto 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 today.

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.

[ -z "$FEATURE_PATTERN" ] && FEATURE_PATTERN=$(jq -r '.conventions.branchPatterns.feature // empty' "$HOME/.claude/settings.gh-workflow.json" 2>/dev/null)
plugins/gh-workflow/commands/gh-start-auto.md · 560 lines

How it starts

The opening of the file, as written. The whole thing — 560 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Autonomous Start Work on Issue #$ARGUMENTS

Fully autonomous pipeline: assigns issue, creates branch, implements, reviews iteratively until zero findings, then creates PR. Only prompts the user for final PR creation approval.

Tool Usage: This workflow uses TaskCreate/TaskUpdate for tracking, dispatches agents for review, and uses AskUserQuestion ONLY for PR creation approval and unrecoverable escalations.

Contract

GOAL: PR created with zero P1/P2/P3 review findings, all acceptance criteria met, all quality gates passed. Testable: gh pr view --json number,state returns a valid open PR AND the final self-review shows 0 findings.

CONSTRAINTS:

  • Read CLAUDE.md before starting; follow all project conventions
  • Never skip quality gates
  • Never leave placeholder/mock/stub code
  • Must iterate review-fix loops until 0 findings or max iterations
  • Only prompt user for PR creation approval (all other decisions auto-defaulted)
  • If max review iterations reached with remaining findings, escalate to user
  • When asserting code behaves a certain way, cite the specific file:line. If unable to cite, mark as UNVERIFIED

FORMAT: Task-based progress tracking using TaskCreate/TaskUpdate.

Read the full file on GitHub · 560 lines

Changes

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.

  1. today First seen · 560 lines · 31 tokens per session scan B 87d7af2aedcb

Subscribe to this mod's changes

gh-start-auto is a command published in the GitHub repository synaptiai/synapti-marketplace (6 stars, last pushed today), licensed Apache-2.0. It adds 31 tokens to every session and 5,664 once invoked, about $0.0002 per session on Opus 5. 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 2026-09-10.