fork-join

fork-join is a skill for Claude Code from tranhieutt/software_development_department. It costs 39 tokens per session (1,584 once invoked), scanned A, original, MIT.

A coordination workflow that splits a large task into independent pieces, gives each piece to a separate coding agent, then combines the results. It uses isolated Git worktrees so parallel changes do not interfere.

In plain words
What is it for?
It is for running independent feature, research, or code changes in parallel and merging the completed work into one branch.
Why use it?
It removes the manual work of dividing parallel tasks, collecting results, resolving branches, and cleaning up temporary workspaces.

Skill for Claude Code

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

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is bash .claude/hooks/fork-join.sh fork fj/<slug>-<N> .worktrees/fj-<slug>-<N>.

Good fit It is for running independent feature, research, or code changes in parallel and merging the completed work into one branch.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/tranhieutt/software_development_department
agentmods
npx agentmods add skills/tranhieutt/software_development_department/fork-join

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 fork-join

README.md
[![agentmods](https://agentmods.dev/badge/skills/tranhieutt/software_development_department/fork-join/github.svg)](https://agentmods.dev/skills/tranhieutt/software_development_department/fork-join)
Your own site
<a href="https://agentmods.dev/skills/tranhieutt/software_development_department/fork-join"><img src="https://agentmods.dev/badge/skills/tranhieutt/software_development_department/fork-join/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 fork-join

Your own site · 80×15
<a href="https://agentmods.dev/skills/tranhieutt/software_development_department/fork-join"><img src="https://agentmods.dev/badge/skills/tranhieutt/software_development_department/fork-join.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,584 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 $0.00039 $0.01584
Opus 5 $0.00019 $0.00792
Sonnet 5 $0.00008 $0.00317
Haiku 4.5 $0.00004 $0.00158

Measured 7d ago against content hash ea30449e3438, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

fork-join 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 7d 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.

.claude/skills/fork-join/SKILL.md · 211 lines

How it starts

The opening of the file, as written. The whole thing — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/fork-join — Parallel Worktree Execution

You are the Fork-Join Coordinator. Your job is to:

  1. Decompose $ARGUMENTS into fully independent work units
  2. Create isolated git worktrees (one per unit)
  3. Launch parallel subagents (one per worktree)
  4. Collect and verify all outputs
  5. Merge all branches sequentially into the current branch
  6. Clean up worktrees

You do NOT implement anything yourself. You fork, coordinate, verify, and join.


Phase 1 — Identify Independent Units

Read CLAUDE.md for project context. Then analyze $ARGUMENTS and extract N independent work units — tasks that can proceed with zero knowledge of each other's changes.

Dependency test (apply to every pair):

  • Do they touch the same file? → Sequential, not parallel
  • Does unit B need unit A's output as input? → Sequential
  • Do they import from each other? → Sequential
  • Can both run from the same current HEAD without conflicts? → ✅ Parallel-safe

List each unit with:

  • ID: fork-01, fork-02, etc.
  • Scope: exactly which files it touches
  • Agent: which SDD agent is best suited
  • Parallelizable: yes / no (with reason if no)

If fewer than 2 units are parallelizable, stop and say:

"This task has sequential dependencies. Use /orchestrate instead of /fork-join."


Phase 2 — Confirm Plan

Present to the user:

## Fork-Join Plan: [task description]

Base branch: [current branch]

| Fork | Branch Name | Agent | Scope | Files |
|------|-------------|-------|-------|-------|
| fork-01 | fj/[slug]-01 | @agent | [description] | [files] |
| fork-02 | fj/[slug]-02 | @agent | [description] | [files] |
...

Estimated: N parallel workers × ~[time] → merge in sequence

Proceed? Type y to fork all worktrees and launch agents.

Wait for y.


Phase 3 — Fork All Worktrees

For each work unit, run:

bash .claude/hooks/fork-join.sh fork fj/<slug>-<N> .worktrees/fj-<slug>-<N>

After forking, display the worktree map:

Worktrees ready:
  fork-01 → .worktrees/fj-slug-01  (branch: fj/slug-01)
  fork-02 → .worktrees/fj-slug-02  (branch: fj/slug-02)
  ...

Read the full file on GitHub · 211 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. 7d ago First seen · 211 lines · 39 tokens per session scan A ea30449e3438

Subscribe to this mod's changes

fork-join is a skill published in the GitHub repository tranhieutt/software_development_department (72 stars, last pushed 3mo ago), licensed MIT. It adds 39 tokens to every session and 1,584 once invoked, about $0.0002 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 2026-09-03.

Related

Other skills, from other repositories

changelog

Generates and maintains changelogs following Keep a Changelog format. Use when updating release notes, finishing tasks, or tagging versions. For version bumps, see semantic-versioning.

tuliosousapro/SaaS-blueprint · 39 tokens

conventional-commits

Enforces Conventional Commits format for git commit messages. Use when formatting commits or validating message structures. For git commands, see git-control.

tuliosousapro/SaaS-blueprint · 34 tokens

git-control

Standardizes git operations, branch management, and disaster recovery. Use when committing, branching, or resolving conflicts. For commit formatting, see conventional-commits.

tuliosousapro/SaaS-blueprint · 35 tokens

ship-preflight

Stage ⑤.a Ship sub — release-preflight gate. Runs harnessed release-preflight (read-only: CHANGELOG [Unreleased] non-empty + version + git-clean + tag-absent). A failing gate blocks shipping. Nothing is pushed/published/tagged here.

easyinplay/harnessed · 62 tokens

semantic-versioning

Manages project versioning following Semantic Versioning (SemVer) principles. Calculates increments based on changes and synchronizes version across documentation and metadata. Use when the user asks to "bump the version", "prepare a release", or when the changelog skill calls for a release.

tuliosousapro/SaaS-blueprint · 63 tokens

storozh

Advisory semantic guard over a changeset manifest before it lands in shared state. Use after a multi-repo session produces a changeset-manifest (mirabilis C1) and before the co-sign push gate — classify each unit's routing against the darwin routing-policy (C3) and NLI-check each unit against the shield corpus (claims…

AlexShchuka/neuro-matrix · 104 tokens