gh-resolve

gh-resolve is a command for Claude Code from synaptiai/synapti-marketplace. It costs 33 tokens per session (3,835 once invoked), scanned B, original, Apache-2.0.

A merge-conflict resolver that examines both versions of conflicting files, chooses a per-file resolution approach, and checks the result.

In plain words
What is it for?
Use it during a merge or rebase to review conflicts, get decisions for ambiguous cases, apply resolutions, and run quality checks afterward.
Why use it?
Merge conflicts happen when separate changes affect the same code. Resolving them without reviewing both sides can silently discard work or leave broken conflict markers.

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 during a merge or rebase to review conflicts, get decisions for ambiguous cases, apply resolutions, and run quality checks afterward.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/synaptiai/synapti-marketplace/gh-resolve"><img src="https://agentmods.dev/badge/commands/synaptiai/synapti-marketplace/gh-resolve.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,835 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 $0.00033 $0.03835
Opus 5 $0.00016 $0.01917
Sonnet 5 $0.00007 $0.00767
Haiku 4.5 $0.00003 $0.00383

Measured today against content hash 57661f657e48, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade B, and why

gh-resolve 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 "$AUTO_RESOLVE" ] && AUTO_RESOLVE=$(jq -r '.conflictResolution.autoResolveTrivial // empty' "$HOME/.claude/settings.gh-workflow.json" 2>/dev/null)
plugins/gh-workflow/commands/gh-resolve.md · 440 lines

How it starts

The opening of the file, as written. The whole thing — 440 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Resolve Merge Conflicts $ARGUMENTS

Detect, classify, and resolve merge conflicts with per-file strategy selection and full verification.

Tool Usage: This workflow uses the AskUserQuestion tool for conflict resolution decisions (delete-modify, competing changes, strategy overrides), TaskCreate/TaskUpdate tools to track per-file resolution progress, and the Skill tool for capability discovery.

Contract

GOAL: All merge conflicts resolved with no orphaned markers, quality checks passing, and merge/rebase completed. Testable: grep -rn '^<<<<<<<\|^=======\|^>>>>>>>' . 2>/dev/null | grep -v '.git/' | grep -v 'node_modules/' returns zero results AND git status --porcelain | grep '^[UAD][UAD]' returns zero results.

CONSTRAINTS:

  • Never silently drop changes from either side of a conflict
  • Always analyze both sides before choosing a resolution strategy
  • Never auto-resolve delete-modify conflicts — require user decision
  • Run quality checks after resolution to verify nothing broke

FORMAT: Conflict analysis table shown first, then per-file resolution with task tracking, then verification summary.

FAILURE CONDITIONS (output is unacceptable if any apply):

  • Changes from either side silently dropped without rationale
  • Orphaned conflict markers remain in any file
  • Delete-modify conflict resolved without user decision via AskUserQuestion
  • Quality checks not run after resolution
  • Merge/rebase not completed after resolving all files

Read the full file on GitHub · 440 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 · 440 lines · 33 tokens per session scan B 57661f657e48

Subscribe to this mod's changes

gh-resolve is a command published in the GitHub repository synaptiai/synapti-marketplace (6 stars, last pushed today), licensed Apache-2.0. It adds 33 tokens to every session and 3,835 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.