ghx

ghx is a skill for Claude Code, Codex from tomzx/agents. It costs 124 tokens per session (3,585 once invoked), scanned A, original, MIT.

An extended command-line tool for GitHub that caches issue and pull-request data and supports detailed review comments. It adds operations such as inline comments, replies, pending reviews, and local comment stashes.

In plain words
What is it for?
Use it to browse cached issues and pull requests, add comments to specific lines or ranges, reply to threads, manage pending reviews, and store review comments locally.
Why use it?
It reduces repeated GitHub API requests and covers review actions that the standard GitHub CLI does not support.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to browse cached issues and pull requests, add comments to specific lines or ranges, reply to threads, manage pending reviews, and store review comments locally.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tomzx/agents/ghx
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.

Any agent
npx skills add tomzx/agents --skill ghx
Clone the repo
git clone --depth 1 https://github.com/tomzx/agents

Made for: Claude Code, Codex.

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 ghx

README.md
[![agentmods](https://agentmods.dev/badge/skills/tomzx/agents/ghx/github.svg)](https://agentmods.dev/skills/tomzx/agents/ghx)
Your own site
<a href="https://agentmods.dev/skills/tomzx/agents/ghx"><img src="https://agentmods.dev/badge/skills/tomzx/agents/ghx/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 ghx

Your own site · 80×15
<a href="https://agentmods.dev/skills/tomzx/agents/ghx"><img src="https://agentmods.dev/badge/skills/tomzx/agents/ghx.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 124 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,585 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00124 $0.03585
Opus 5.5 $0.00050 $0.01434
Sonnet 5.5 $0.00025 $0.00717
Haiku 4.5 $0.00012 $0.00359

Measured 7d ago against content hash bb71bc88c2b3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ghx 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 7d 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.

skills/ghx/SKILL.md · 344 lines

How it starts

The opening of the file, as written. The whole thing — 344 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ghx Skill

ghx is an extended GitHub CLI. It talks to the GitHub GraphQL API directly to provide three kinds of capability:

  1. Cached browsing — fetches issues, pull requests, and their comments and caches every result locally (SQLite at ~/.cache/ghx/cache/cache.db by default, or one JSON file per entry under ~/.cache/ghx/cache/<host>/<owner>/<repo>/ with --storage file) to minimise API calls.
  2. Comment operations — inline review comments, line-range comments, thread replies, pending reviews, and a local "stash" for offline review comments, none of which the standard gh CLI supports.
  3. Remote execution — ghx rpc serve exposes the same operations over JSON-RPC, and --remote <url> runs any command against that server instead of locally.

Prerequisites

Binary

Check whether the binary is on PATH; install from the latest release if not:

if ! command -v ghx &>/dev/null; then
  go install github.com/tomzxcode/ghx@main
fi

Pre-built binaries are also available at https://github.com/TomzxCode/ghx/releases/tag/latest.

Authentication

ghx reads GH_TOKEN or GITHUB_TOKEN from the environment, and falls back to gh auth token (GitHub CLI). Set the token if neither is available:

export GH_TOKEN=<token>

Target repository

All commands accept --repo [HOST/]OWNER/REPO (or -R). When omitted, the repo is auto-detected from the origin remote of the current directory. Confirm the target before running expensive or write operations:

git remote get-url origin

Cached browsing

Pre-populate the cache

Run cache to populate and refresh the local cache, so subsequent list/view commands are served instantly from disk:

ghx cache                            # delta refresh from the last cache write
ghx cache --repo owner/repo
ghx cache --if-stale                 # skip while the cache is newer than --cache-duration (60 min)
ghx cache --if-stale --cache-duration 120   # ... newer than 2 hours
ghx cache --since 2026-09-01         # refresh entries created/updated since a date
ghx cache --type issues              # refresh only issues (or prs)
ghx cache --force                    # discard resume state and do a full re-fetch
ghx cache --retries 5                # retry transient errors (default 2; total attempts = retries + 1)

Read the full file on GitHub · 344 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. 7d ago Changed · +31 lines bb71bc88c2b3
  2. 17d ago Changed · +19 lines c3d93a5da045
  3. 22d ago Changed · -17 lines 51b88bd58d06
  4. 28d ago Changed · +3 lines ceeecf7e5049
  5. 1mo ago First seen · 308 lines · 124 tokens per session scan A cb2bec0fa51a

Subscribe to this mod's changes

ghx is a skill published in the GitHub repository tomzx/agents (13 stars, last pushed yesterday), licensed MIT. It adds 124 tokens to every session and 3,585 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-09-03.

Related

Other skills, from other repositories

pr

Draft a PR body from OMC's paper trail — the smallest visual that proves the change, evidence consumed from the verify protocol (never re-collected), reversibility from the ADR test on the diff, glossary language throughout.

Yeachan-Heo/oh-my-claudecode · 47 tokens

merge-batch

Prepare and merge an owner-selected PR batch with contributor credit and exact-candidate admission. Use for a pasted PR list; combined focused validation is diagnostic, and every actual landing still requires its applicable checks and authorization.

diegosouzapw/OmniRoute · 46 tokens

otto-pr-review-loop

Run Polly and OCR on a PR until all findings settle.

omnigent-ai/omnigent · 17 tokens

engram-branch-pr

PR creation workflow for Engram following the issue-first enforcement system. Trigger: When creating a pull request, opening a PR, or preparing changes for review.

Gentleman-Programming/engram · 37 tokens

github-contributor

A step-by-step guide for contributing code, tests, documentation, or build changes to open-source projects you do not maintain. It explains how to prepare a pull request that follows the project’s rules and is easier for maintainers to review.

daymade/claude-code-skills · 105 tokens

revdiff

Review diffs, files, and documents with inline annotations in a TUI overlay, or answer questions about revdiff usage, configuration, themes, and keybindings. Opens revdiff in agterm/tmux/zellij/herdr/kitty/wezterm/cmux/ghostty/iterm2/emacs-vterm, captures annotations, and addresses them. Works in git, hg, and jj repos…

umputun/revdiff · 248 tokens