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.
npx agentmods add skills/shabaraba/vibing.nvim/github-flow-for-claude-on-webnpx skills add shabaraba/vibing.nvim --skill github-flow-for-claude-on-webgit clone --depth 1 https://github.com/shabaraba/vibing.nvimWrote 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/skills/shabaraba/vibing.nvim/github-flow-for-claude-on-web)<a href="https://agentmods.dev/skills/shabaraba/vibing.nvim/github-flow-for-claude-on-web"><img src="https://agentmods.dev/badge/skills/shabaraba/vibing.nvim/github-flow-for-claude-on-web.svg" alt="Measured on agentmods" 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 | $0.00071 | $0.06054 |
| Opus 5 | $0.00036 | $0.03027 |
| Sonnet 5 | $0.00014 | $0.01211 |
| Haiku 4.5 | $0.00007 | $0.00605 |
Grade A, and why
github-flow-for-claude-on-web 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 6d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
All GitHub operations (PRs, issues, comments, reviews) MUST use the REST API via `curl`: How it starts
The opening of the file, as written. The whole thing — 913 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Flow for Claude Code on the Web
This skill provides comprehensive Git and GitHub operations optimized for Claude Code on the web environment, including branch management, push operations, and GitHub REST API interactions.
⚠️ CRITICAL: Always Use GitHub REST API
NEVER use gh CLI in Claude Code on the web - it is not available.
All GitHub operations (PRs, issues, comments, reviews) MUST use the REST API via curl:
- ✅
curl -s https://api.github.com/repos/OWNER/REPO/pulls/123 - ❌
gh pr view 123(NOT AVAILABLE)
When to Use
This skill is automatically activated when running in Claude Code on the web environment (CLAUDE_CODE_REMOTE=true).
Table of Contents
- GitHub API Operations
- Environment Detection
- Branch Naming Requirements
- Git Push Operations
- Pull Request Creation
- Complete Workflows
- Troubleshooting
GitHub API Operations
Core Principle
ALL GitHub operations must use the REST API. The gh CLI is not available in Claude Code on the web environment.
Common GitHub API Endpoints
Get PR Details
curl -s https://api.github.com/repos/OWNER/REPO/pulls/PR_NUMBER
Get PR Review Comments
# Code review comments
curl -s https://api.github.com/repos/OWNER/REPO/pulls/PR_NUMBER/comments
# Issue comments (general discussion)
curl -s https://api.github.com/repos/OWNER/REPO/issues/PR_NUMBER/comments
Get Repository Info
# Auto-detect from git remote
REMOTE_URL=$(git remote get-url origin)
REPO_FULL=$(echo "$REMOTE_URL" | sed -E 's#.*github\.com[:/]([^/]+/[^/]+)(\.git)?$#\1#')
OWNER=$(echo "$REPO_FULL" | cut -d/ -f1)
REPO=$(echo "$REPO_FULL" | cut -d/ -f2)
curl -s "https://api.github.com/repos/$OWNER/$REPO"
List Issues
# All open issues
curl -s https://api.github.com/repos/OWNER/REPO/issues
# Filter by labels
curl -s "https://api.github.com/repos/OWNER/REPO/issues?labels=bug"
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.
- 6d ago First seen · 913 lines · 71 tokens per session scan A 9c4adb0f18fb
github-flow-for-claude-on-web is a skill published in the GitHub repository shabaraba/vibing.nvim (13 stars, last pushed today), licensed MIT. It adds 71 tokens to every session and 6,054 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
security-pipeline
Use when security verification is needed - pre-commit security checks, vulnerability scanning, STRIDE threat analysis. Integrates with /handoff-verify --security and /commit-push-pr. CWE Top 25 based.
pr-triage
4-phase PR backlog management with audit, deep code review, validated comments, and optional worktree setup. Use when triaging pull requests, catching up on pending code reviews, or managing a backlog of open PRs. Args: 'all' to review all, PR numbers to focus (e.g. '42 57'), 'en'/'fr' for language, no arg = audit…
git-ai-archaeology
Analyze AI config evolution in a git repo. Use when mapping AI adoption history, finding when configs were first introduced, charting commit velocity by month, or identifying maturity phases in a project's AI tooling.
land-and-deploy
Merge PR, wait for CI, verify deploy, run canary. The complete landing pipeline.
review-pr
Perform a comprehensive code review of a pull request.
source-command-update-infos-release
Update Codex releases tracking (guide + landing + version bump).