push

push is a skill for Claude Code from saffron-health/libretto. It costs 21 tokens per session (1,004 once invoked), scanned A, a copy of push-everything, MIT.

A workflow for committing code changes and sending them to a shared Git repository, with a pull request when needed. A pull request is a proposed change that teammates can review before it is merged.

In plain words
What is it for?
Use it to create a branch when needed, commit changes, push them, and create or update a pull request with a suitable release-note label.
Why use it?
It removes the manual steps and branch decisions involved in sharing finished work. It also keeps the pull request description aligned with the complete set of changes.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: installed under .agents/ (shared by several agents).

Part of the libretto plugin — 24 skills shipped together

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.

agentmods
npx agentmods add skills/saffron-health/libretto/push
Any agent
npx skills add saffron-health/libretto --skill push
Clone the repo
git clone --depth 1 https://github.com/saffron-health/libretto

Made for: Claude Code.

Or install libretto, the plugin that ships this one along with the rest of its 24 skills.

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 push

README.md
[![agentmods](https://agentmods.dev/badge/skills/saffron-health/libretto/push.svg)](https://agentmods.dev/skills/saffron-health/libretto/push)
Your own site
<a href="https://agentmods.dev/skills/saffron-health/libretto/push"><img src="https://agentmods.dev/badge/skills/saffron-health/libretto/push.svg" alt="Measured on agentmods" height="20"></a>
Per session 21 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,004 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 86% copy Near-identical to another mod 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 $0.00021 $0.01004
Opus 5 $0.00010 $0.00502
Sonnet 5 $0.00004 $0.00201
Haiku 4.5 $0.00002 $0.00100

Measured 6d ago against content hash 210931e476fd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

push 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 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.

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.

Origin

This is a copy

86% identical to push-everything — 12 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.agents/skills/push/SKILL.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Branch handling

If on main, checkout a new branch first.

If on a non-main branch where the existing PR is already merged, the uncommitted changes are likely unrelated to that branch. In this case:

  1. Checkout main and pull
  2. Create a new branch with a name describing the uncommitted changes
  3. Continue with the commit and PR workflow below

Commit and PR workflow

Commit the changes. Use gh cli to check if a PR exists for this branch. If no PR exists, create one with an appropriate title and description. If a PR exists, query its current title and description and update them if the new changes warrant it. Push the changes.

When writing or updating a PR title and description, always base them on the full diff against main (git diff main...HEAD), not just the most recent commits. The title and description should accurately summarize the entire set of changes in the PR.

Release note labels

When creating or updating a PR in this repo, make sure it has a changelog label so GitHub Releases can categorize it correctly.

Prefer one of:

  • enhancement
  • bug
  • documentation

If the correct label is unclear, prefer enhancement.

If the PR should be excluded from release notes, use skip-changelog.

Use skip-changelog for PRs focused only on developer tooling changes, such as agent skills, workflow plumbing, local tooling, or similar maintenance that should not appear in user-facing release notes.

PR body formatting

When the PR body contains Markdown code spans/backticks, parentheses, angle brackets, or shell-sensitive characters, do not pass it directly via --body "..." because shells can mangle it.

Use --body-file with stdin/heredoc instead:

cat <<'EOF' | gh pr create --base main --head <branch> --title "<title>" --body-file -
## Summary
- item with `code`
EOF

Use the same pattern for updates:

cat <<'EOF' | gh pr edit <branch-or-number> --body-file -
## Updated Summary
- item with `code`
EOF

CI and review gating

Read the full file on GitHub · 92 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. 6d ago First seen · 92 lines · 21 tokens per session scan A 210931e476fd

Subscribe to this mod's changes

push is a skill published in the GitHub repository saffron-health/libretto (886 stars, last pushed 15d ago), licensed MIT. It adds 21 tokens to every session and 1,004 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to push-everything, differing in 12 lines, and is treated as a copy.