ma-handoff

ma-handoff is a skill for Claude Code from JeonJe/claude-plugins. It costs 75 tokens per session (947 once invoked), scanned A, original, MIT.

A handoff procedure for moving an approved implementation task into a project’s Git worktree, the local directory containing a checked-out branch. It validates the branch, prepares the worktree, runs setup, and writes planning and handoff documents.

In plain words
What is it for?
Use it for approved implementation tickets to validate the project and branch, create or continue a worktree, collect setup details, and generate the required PLAN and HANDOFF files.
Why use it?
It reduces mistakes when transferring approved work between a planning workspace and the repository where developers will implement it.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the ma-pipeline plugin — 8 skills shipped together

Good fit Use it for approved implementation tickets to validate the project and branch, create or continue a worktree, collect setup details, and generate the required PLAN and HANDOFF files.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jeonje/claude-plugins/ma-handoff
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 JeonJe/claude-plugins --skill ma-handoff
Clone the repo
git clone --depth 1 https://github.com/JeonJe/claude-plugins

Made for: Claude Code.

Or install ma-pipeline, the plugin that ships this one along with the rest of its 8 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 ma-handoff

README.md
[![agentmods](https://agentmods.dev/badge/skills/jeonje/claude-plugins/ma-handoff/github.svg)](https://agentmods.dev/skills/jeonje/claude-plugins/ma-handoff)
Your own site
<a href="https://agentmods.dev/skills/jeonje/claude-plugins/ma-handoff"><img src="https://agentmods.dev/badge/skills/jeonje/claude-plugins/ma-handoff/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 ma-handoff

Your own site · 80×15
<a href="https://agentmods.dev/skills/jeonje/claude-plugins/ma-handoff"><img src="https://agentmods.dev/badge/skills/jeonje/claude-plugins/ma-handoff.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 947 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 $0.00075 $0.00947
Opus 5 $0.00037 $0.00474
Sonnet 5 $0.00015 $0.00189
Haiku 4.5 $0.00007 $0.00095

Measured 9d ago against content hash 5bbc73f2a257, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

ma-handoff 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.

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.

plugins/ma-pipeline/skills/ma-handoff/SKILL.md · 56 lines

How it starts

The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/ma-handoff

Run handoff only for approved impl tickets. PRD/design/review remain workspace SSOTs; handoff moves only PLAN (plus HANDOFF.md) into the implementation repo.

This is a procedural skill: execute the steps below directly with git and shell commands. A deterministic execution engine is not included in v1 — verify each step's stated condition yourself before proceeding.

Args

/ma-handoff --key <ISSUE_KEY> --project <PROJECT_KEY> [--resume] [--dry-run]
  • key: required, matching the configured issueKeyPattern (e.g. PROJ-123)
  • project: required (workspace config project key)
  • --resume: continue from a previous incomplete run
  • --dry-run: validate intent and plan without mutating filesystem/repo

References index

File When to read
config/branch-naming.md Step 2 — branch/worktree decision rules
config/setup-interview.md Step 3 — setup collection and failure policy
templates/handoff-doc.md Step 4 — HANDOFF/PLAN format

Workflow

  1. Validate the contract. Scope is impl (per the ma skill's scope gate (../ma/references/scope-gate.md)); gates.implementationApproval.status == "approved" in {stateRoot}/{key}/state.json; the approval records this project with base, target, and — when the project defines modules — primaryModule and affectedModules; plan review passed; base/target are valid branch names. Any missing element halts with the exact missing field.
  2. Resolve refs and the worktree path per config/branch-naming.md. Run git fetch origin in the target repo and branch from the tip of origin/{base}, never from a stale local branch. A local base holding commits absent from origin is a conflict to report, not something to discard silently. Then:
    git -C {projectPath} branch {target} origin/{base}
    git -C {projectPath} worktree add {worktreePath} {target}
    
  3. Run setup commands collected per config/setup-interview.md, only from the workspace config (setup of module dependencies first, then the primary/affected modules, then project-level). Record per-command cwd/status/exit code. Any failure leaves the phase incomplete but resumable.
  4. Package PLAN and write HANDOFF per templates/handoff-doc.md: move the approved PLAN from {contextRoot}/{domain}/plan/{key}-{project}.md to {worktreePath}/{docsPath}/{key}/PLAN.md (the worktree becomes PLAN SSOT; remove the original), write {worktreePath}/HANDOFF.md, and append the audit log at {contextRoot}/{domain}/handoff/{key}.md.
  5. Record state. Update {stateRoot}/{key}/state.json worktrees[project] with path, base, target, baseCommit, and planPath. Report success with those values, or the failed step with its recovery action.

Read the full file on GitHub · 56 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. 9d ago First seen · 56 lines · 75 tokens per session scan A 5bbc73f2a257

Subscribe to this mod's changes

ma-handoff is a skill published in the GitHub repository JeonJe/claude-plugins (3 stars, last pushed 1mo ago), licensed MIT. It adds 75 tokens to every session and 947 once invoked, about $0.0004 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

git-advanced

Use when performing complex git operations -- rebasing, cherry-picking, resolving merge conflicts, bisecting bugs, managing stashes, cleaning history, or working with monorepos. Goes beyond basic commit/push/pull.

Sagargupta16/claude-skills · 50 tokens

repo-polish

Use when setting up new repositories, auditing existing ones, or preparing repos for public visibility. Generates .gitignore, .env.example, README, and LICENSE files. Detects committed secrets and flags security issues.

Sagargupta16/claude-skills · 46 tokens

oss-contrib

Use when contributing to open source projects from forked repositories. Handles upstream sync, CONTRIBUTING.md compliance, code style matching, PR preparation, and project-specific patterns. Activates for fork management, PR template filling, and upstream workflow compliance.

Sagargupta16/claude-skills · 52 tokens

renovate-triage

Use when triaging open Renovate PRs across your own repos into merge / close / defer. Activates on "renovate triage", "review dep PRs", "monthly deps", or on the 1st of a month if deps are grouped monthly.

Sagargupta16/claude-skills · 62 tokens

review-pr

Review a Pull Request in one of two postures: an expository "tour guide" that walks through changes in logical order, or an adversarial audit that assumes the change is wrong until proven safe and hunts for the failure mode. Triggers: "review PR #123", "adversarial review", "walk me through this PR", "PR tour guide"…

jontsai/claude-plugins · 139 tokens

release

This skill should be used when the user wants to create a new release — bump version, tag, push, create GitHub release, and optionally publish to npm. Use when user says "release", "bump version", "publish", "cut a release", or "release candidate".

NikiforovAll/claude-code-marketplace · 60 tokens