upstream-cherry-pick

upstream-cherry-pick is a skill for Claude Code from lifeinchords/claude-code-skills. It costs 132 tokens per session (4,332 once invoked), scanned A, original, MIT.

A workflow for finding useful changes in a project repository and safely copying them back to an upstream template repository. An upstream template is the starting codebase that other projects clone or fork.

In plain words
What is it for?
Reviewing commits, classifying them as reusable, possibly reusable, or unsuitable, and cherry-picking selected changes into a template with GitHub and command-line checks.
Why use it?
It helps teams decide which changes are reusable and avoid accidental changes to Git history or repository state.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Cursor.

Good fit Reviewing commits, classifying them as reusable, possibly reusable, or unsuitable, and cherry-picking selected changes into a template with GitHub and command-line checks.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/lifeinchords/claude-code-skills/upstream-cherry-pick
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 lifeinchords/claude-code-skills --skill upstream-cherry-pick
Clone the repo
git clone --depth 1 https://github.com/lifeinchords/claude-code-skills

Made for: Claude Code.

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 upstream-cherry-pick

README.md
[![agentmods](https://agentmods.dev/badge/skills/lifeinchords/claude-code-skills/upstream-cherry-pick/github.svg)](https://agentmods.dev/skills/lifeinchords/claude-code-skills/upstream-cherry-pick)
Your own site
<a href="https://agentmods.dev/skills/lifeinchords/claude-code-skills/upstream-cherry-pick"><img src="https://agentmods.dev/badge/skills/lifeinchords/claude-code-skills/upstream-cherry-pick/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 upstream-cherry-pick

Your own site · 80×15
<a href="https://agentmods.dev/skills/lifeinchords/claude-code-skills/upstream-cherry-pick"><img src="https://agentmods.dev/badge/skills/lifeinchords/claude-code-skills/upstream-cherry-pick.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 132 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,332 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.
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 $0.00132 $0.04332
Opus 5 $0.00066 $0.02166
Sonnet 5 $0.00026 $0.00866
Haiku 4.5 $0.00013 $0.00433

Measured 9d ago against content hash d5a30f041b00, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

upstream-cherry-pick 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 9d ago.

The scan reads SKILL.md. This mod also ships 5 executable files (scripts/check-deps.sh, scripts/conflict-backup.sh, scripts/detect-mode.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.

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.

.claude/skills/upstream-cherry-pick/SKILL.md · 454 lines

How it starts

The opening of the file, as written. The whole thing — 454 lines — stays where its author put it; the contents beside it link to each section on GitHub.

IMPORTANT: Always invoke scripts with relative paths from the project root, never absolute paths. Permission rules use relative patterns -- absolute paths will not match and will trigger a prompt.

Purpose

Situations where a template repository that gets cloned or forked to start new projects. Over time, project repos accumulate improvements that could flow back to the template for other projects to inherit.

This skill guides Claude through safely identifying reusable agentic patterns in a project repo and bringing them into an upstream template repo with clear operator decisions (mode + delivery) and strict safety gates (no surprise git state changes).

Prerequisites (Dependencies + local repos)

This skill requires:

  • gh - GitHub CLI for repo verification and commit preview
  • jq - JSON processor for parsing script outputs
  • git - Version control system for cherry-picking operations
  • bash - Shell for running scripts (currently supports bash; future: fish, zsh)
  • brew - macOS package manager for installing dependencies
  • Standard Unix utilities (typically preinstalled): grep, sed, awk, cut, tr, wc, head, dirname, date, cp, mkdir, file
  • Checksum utility for backups: shasum (macOS) or sha256sum (Linux)

This skill also assumes:

  • macOS (Linux may work but is not currently tested/supported)
  • A local project repo (derived from the template, containing candidate commits)
  • A local template repo (the upstream destination, with push access)

Scripts

This skill includes executable scripts in .claude/skills/upstream-cherry-pick/scripts/ that handle deterministic operations:

check-deps.sh - Verifies required tools are installed

bash .claude/skills/upstream-cherry-pick/scripts/check-deps.sh
# Returns JSON with status: ok, missing, declined, or error

# Exit codes: 
# 0=aall deps present or installed successfully
# 1=missing deps and operator declined install (or brew missing)
# 2=install failed
# 3 unsupported OS (currently macOS-only installer)
# On macOS, offers to install missing deps via brew

Read the full file on GitHub · 454 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. 9d ago First seen · 454 lines · 132 tokens per session scan A d5a30f041b00

Subscribe to this mod's changes

upstream-cherry-pick is a skill published in the GitHub repository lifeinchords/claude-code-skills (2 stars, last pushed 4mo ago), licensed MIT. It adds 132 tokens to every session and 4,332 once invoked, about $0.0007 per session on Opus 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 2026-08-31.

Related

Other skills, from other repositories

prowler-commit

Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.

prowler-cloud/prowler · 33 tokens

gh-auth-isolation

Safely manage multiple GitHub identities (EMU + personal) in agent workflows.

github/gh-aw · 20 tokens

comet-github

A routing guide for Comet-related GitHub work. It directs requests about pull requests, issues, CI failures, ideas, and fixes to the appropriate review or implementation process.

rpamis/comet · 72 tokens

github-skill

Work with GitHub via the gh CLI — clone repositories, create/list/merge pull requests, create/list issues, and run any other gh command (API calls, workflow runs, releases, repo administration). List operations return parsed JSON.

zeenie-ai/OpenCompany · 51 tokens

re0-merge

Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…

LilMGenius/paperthin · 70 tokens

nvca-chart-release

Release NVCA Operator chart changes from the native monorepo source to the vendored Helm chart. Use when updating the vendored NVCA Operator chart, changing NVCA image refs, publishing helm-nvca-operator, or validating the chart against a self-managed control plane.

NVIDIA/nvcf · 61 tokens