gh-discussion-replier

gh-discussion-replier is a skill for Claude Code, Codex from Fu-Jie/openwebui-extensions. It costs 45 tokens per session (1,169 once invoked), scanned A, original, MIT.

A workflow for writing and posting professional English replies to GitHub Discussions using GitHub's GraphQL API. GitHub Discussions are community conversations for questions, ideas, and announcements in a repository.

In plain words
What is it for?
Use it to fetch a discussion's details, check its author's star status, draft a reply for questions or feature requests, and post the response through the GitHub API.
Why use it?
It gathers the discussion context and selects an appropriate response format before posting. It also checks whether the author has starred the repository so the reply can follow the relevant template.

Skill for Claude CodeCodex

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

Good fit Use it to fetch a discussion's details, check its author's star status, draft a reply for questions or feature requests, and post the response through the GitHub API.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/fu-jie/openwebui-extensions/gh-discussion-replier
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 Fu-Jie/openwebui-extensions --skill gh-discussion-replier
Clone the repo
git clone --depth 1 https://github.com/Fu-Jie/openwebui-extensions

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 gh-discussion-replier

README.md
[![agentmods](https://agentmods.dev/badge/skills/fu-jie/openwebui-extensions/gh-discussion-replier/github.svg)](https://agentmods.dev/skills/fu-jie/openwebui-extensions/gh-discussion-replier)
Your own site
<a href="https://agentmods.dev/skills/fu-jie/openwebui-extensions/gh-discussion-replier"><img src="https://agentmods.dev/badge/skills/fu-jie/openwebui-extensions/gh-discussion-replier/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-discussion-replier

Your own site · 80×15
<a href="https://agentmods.dev/skills/fu-jie/openwebui-extensions/gh-discussion-replier"><img src="https://agentmods.dev/badge/skills/fu-jie/openwebui-extensions/gh-discussion-replier.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,169 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00045 $0.01169
Opus 5 $0.00023 $0.00584
Sonnet 5 $0.00009 $0.00234
Haiku 4.5 $0.00005 $0.00117

Measured 10d ago against content hash 1dc4a8152a90, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

gh-discussion-replier scanned grade A 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 10d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/check_discussion_star.sh, scripts/post_discussion_reply.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

r = subprocess.run(['gh', 'api', 'graphql',
.github/skills/gh-discussion-replier/SKILL.md · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Gh Discussion Replier

Overview

The gh-discussion-replier skill enables posting professional English replies to GitHub Discussions. Unlike issues, discussions use the GraphQL API for both reading and posting. This skill handles the full workflow: fetching context, checking star status, composing a reply, and posting.

Workflow

  1. Identify the Discussion: Get the discussion number (e.g., #66) and URL.
  2. Fetch Discussion Content: Use GraphQL to get the title, body, author, and category.
  3. Check Star Status: Run the bundled script to check if the author has starred the repo.
    • Command: bash .github/skills/gh-discussion-replier/scripts/check_discussion_star.sh <discussion_number>
    • Interpretation:
      • Exit code 0: User has starred. Use "Already Starred" templates.
      • Exit code 1: User has NOT starred. Include "Star Request" in the reply.
  4. Select a Template: Load references/templates.md to choose a suitable response pattern based on the discussion category (Ideas, Q&A, General, Show and tell).
  5. Draft the Reply: Compose a concise message based on star status and template.
  6. Post the Comment: Use the GraphQL addDiscussionComment mutation (see below).

Tool Integration

Fetch Discussion Content

import subprocess, json

def get_discussion(owner, repo, number):
    query = '''
    query($owner:String!, $repo:String!, $number:Int!) {
      repository(owner:$owner, name:$repo) {
        discussion(number:$number) {
          id title body
          author { login }
          category { name }
          comments(first:10) { nodes { body author { login } } }
        }
      }
    }
    '''
    r = subprocess.run(['gh', 'api', 'graphql',
        '-f', f'query={query}',
        '-f', f'owner={owner}',
        '-f', f'repo={repo}',
        '-f', f'number={number}'],
        capture_output=True, text=True)
    return json.loads(r.stdout)['data']['repository']['discussion']

Read the full file on GitHub · 128 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 10d ago First seen · 128 lines · 45 tokens per session scan A 1dc4a8152a90

Subscribe to this mod's changes

gh-discussion-replier is a skill published in the GitHub repository Fu-Jie/openwebui-extensions (307 stars, last pushed 5d ago), licensed MIT. It adds 45 tokens to every session and 1,169 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.