Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Github Push

ASecurity

Push a local directory to a GitHub repository without needing the raw personal access token. Use when the user wants to publish, upload, or push files or a project to GitHub and a GitHub connector credential is stored in the Secure Vault. Works from any machine via the GitHub git-database API — no git CLI credentials needed.

2 stars
0 votes
0 copies
0 views
Added 9/29/2026
ai-agentspythonbashnodegitapidatabase

Works with

cliapi

Security Analysis

A100/100

Pro scans all 2 files and shows the line behind each finding

Scanned 9/29/2026

$npx -y skills add aicodedecode/awesome-muse-skills --skill github-push --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Github Push?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Github Push
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/aicodedecode-github-push/badge)](https://www.skillsdirectory.com/skills/aicodedecode-github-push)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: github-push
description: Push a local directory to a GitHub repository without needing the raw personal access token. Use when the user wants to publish, upload, or push files or a project to GitHub and a GitHub connector credential is stored in the Secure Vault. Works from any machine via the GitHub git-database API — no git CLI credentials needed.
---

# GitHub Push

Pushes a local directory's files to a GitHub repo (`owner/repo`, branch) using the GitHub git-database REST API. Authenticates through the Secure Vault GitHub connector via the authd surrogate exchange — the real token is never exposed; the script fetches a short-lived surrogate (`authdc cred surrogate custom.github`) and sends it as a Bearer header, which authd swaps for the real credential at egress.

## When to use

- The user asked to publish/push/upload a local project or folder to their GitHub repo.
- A GitHub connector credential is already stored (via `credentials.request_api_access` with provider `github`).
- The git CLI can't be authenticated (e.g., no credential helper, mobile-driven workflows, sandboxed machines).

## How it works

`scripts/push_repo.py` performs the equivalent of an initial (or updating) push:

1. Verifies the repo exists and reads its default branch.
2. Walks the local directory (skips `.git/`, `node_modules/`, `.next/`, `out/`, `.DS_Store`), creating one git blob per file via `POST /repos/{owner}/{repo}/git/blobs` (parallel, base64-encoded). On repeat pushes it diffs first: local git blob SHAs are compared against the branch's remote tree, so unchanged files are skipped with zero API calls.
3. Creates the tree **incrementally** (in chunks of 100 entries chained via `base_tree`) — GitHub times out on very large single tree creations, and full slash-paths in entries auto-create intermediate trees.
4. Creates a commit via `POST .../git/commits`, parented on the branch tip if the branch already exists.
5. Creates or fast-forward-updates `refs/heads/{branch}`.

## Usage

```bash
python3 ~/workspace/skills/github-push/scripts/push_repo.py \
  --dir /path/to/project \
  --owner <github-username> \
  --repo <repo-name> \
  --branch main \
  --message "Initial commit"
```

Options:
- `--dir` (required): local directory to push.
- `--owner`, `--repo` (required): target `owner/repo`.
- `--branch`: defaults to the repo's default branch.
- `--message`: commit message (default: "Push via github-push skill").
- `--workers`: parallel blob-upload workers (default: 12).

## Notes

- Requires the `custom.github` connector credential (api_hosts `api.github.com`, `github.com`) and the `authdc` CLI on PATH.
- The token needs `Contents: read and write` on the target repo (fine-grained PAT scoped to that repo is enough).
- Large pushes: blob API accepts files up to ~100 MB; trees are built incrementally in chunks of 100 entries chained via `base_tree` (GitHub times out on very large single tree creations).
- Never print or log the surrogate token; it is short-lived but treat it as sensitive.
- If the API returns 401/403, the credential is missing, expired, or lacks scope — ask the user to reconnect via the Secure Vault card rather than retrying blindly.

Attribution

aicodedecodeaicodedecode
View sourceSee grades on GitHubMore from aicodedecode →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698461 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →