parallel-work

A workflow for developing separate, independent stories at the same time in isolated copies of a Git project. A Git worktree is a separate working folder connected to the same project history.

In plain words
What is it for?
Use it to start, monitor, and clean up parallel development streams, then combine finished work into the main branch with the matching merge workflow.
Why use it?
It lets multiple coding sessions work without changing each other's files. It also points out when stories depend on each other or would create difficult merge conflicts.

Skill for Claude CodeCodex

Part of the exosuit plugin — 44 skills, 1 command, 9 agents, 10 hooks 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/joris887/exosuit/parallel-work
Any agent
npx skills add joris887/exosuit --skill parallel-work
Clone the repo
git clone --depth 1 https://github.com/joris887/exosuit

Made for: Claude Code, Codex.

Or install exosuit, the plugin that ships this one along with the rest of its 44 skills, 1 command, 9 agents, 10 hooks.

Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,003 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00082 $0.02003
Opus 5 $0.00041 $0.01001
Sonnet 5 $0.00016 $0.00401
Haiku 4.5 $0.00008 $0.00200

Measured 3d ago against content hash edda93cdc89d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

parallel-work 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 3d ago.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/new-worktree.sh, scripts/open-worktree-terminals.sh, scripts/worktree-status.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/parallel-work/SKILL.md · 202 lines

How it starts

The opening of the file, as written. The whole thing — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.


parallel-work

Manage parallel development streams. Each stream is an isolated copy of the project (a git worktree) on its own branch, so multiple Claude Code sessions can build different stories at the same time without touching each other's files.

When Parallel Work Makes Sense (and When It Doesn't)

Parallel work is opt-in, never required. The default workflow is one branch, one story at a time — that keeps the user fully aware of every change.

Good fit:

  • Stories are self-contained: no dependencies on each other, no shared hot files
  • Each story is a complete outcome on its own (outcome over output)
  • The user is comfortable reviewing several streams of change

Bad fit — advise sequential work instead:

  • Stories depend on each other (one needs the other's code or schema)
  • Stories touch the same files or the same module's core
  • The stories are parts of one mechanism (they should be ONE story, not parallel streams)

The start command checks this before creating anything (see below). When in doubt, recommend sequential: merging conflicting parallel work costs more than it saves.

Commands

Status (default, or "status"/"list")

Run the status script:

bash "${CLAUDE_PLUGIN_ROOT:-.claude}/skills/parallel-work/scripts/worktree-status.sh"

Show all active streams with their branches, their parent (from git config branch.<name>.exosuitParent), and ahead/behind counts vs the parent:

### Active Streams

| Path | Branch | Parent | Ahead/Behind parent |
|------|--------|--------|---------------------|
| [path] | [branch] | [parent or "-"] | [+N/-M] |

**Options:**
- `/parallel-work start` — create new parallel streams
- `/merge-up` (inside a stream) — publish its work to the parent
- `/merge-down` (inside a stream) — pull the parent's accumulated work in
- `/parallel-work cleanup` — remove finished streams

Start — Create Parallel Streams

Read the full file on GitHub · 202 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. 3d ago First seen · 202 lines · 82 tokens per session scan A edda93cdc89d

Subscribe to this mod's changes

parallel-work is a skill published in the GitHub repository joris887/exosuit (4 stars, last pushed 13d ago), licensed MIT. It adds 82 tokens to every session and 2,003 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

issue-triage

Issue triage: audit open issues, categorize, detect duplicates, cross-ref PRs, risk assessment, post comments. Args: "all" for deep analysis of all, issue numbers to focus (e.g. "42 57"), "en"/"fr" for language, no arg = audit only in French.

rtk-ai/rtk · 70 tokens

ship

Build, commit, push & version bump workflow - automates the complete release cycle.

rtk-ai/rtk · 16 tokens

pr-review

Batch review des PRs RTK par ordre de complexité croissante (XS → S → M → L). Pour chaque PR : vérifie l'état (conflits, CLA, reviews), lit le diff complet, analyse le code en contexte, présente un résumé avec lien + taille + recommandation. Attend validation explicite avant tout merge. Poste des commentaires…

rtk-ai/rtk · 128 tokens

rtk-triage

Triage complet RTK : exécute issue-triage + pr-triage en parallèle, puis croise les données pour détecter doubles couvertures, trous sécurité, P0 sans PR, et conflits internes. Sauvegarde dans claudedocs/RTK-YYYY-MM-DD.md. Args: "en"/"fr" pour la langue (défaut: fr), "save" pour forcer la sauvegarde.

rtk-ai/rtk · 96 tokens

code-simplifier

Review RTK Rust code for idiomatic simplification. Detects over-engineering, unnecessary allocations, verbose patterns. Applies Rust idioms without changing behavior.

rtk-ai/rtk · 36 tokens

build-teaql-app

Build or change a TeaQL application in Java, Rust, Go, Swift, Python, C#/.NET, or TypeScript, including Kotlin/JVM applications that consume Java-generated libraries. Mandatory order: first draft and save a complete KSML model, then verify the client and evaluate that saved model, repair it through repeated evaluation…

teaql/teaql-agent-kit · 112 tokens