parallel-lifecycle

A workflow for running and testing features inside separate Git worktrees, which are alternate checkouts of one repository, with isolated ports, browsers, and databases.

In plain words
What is it for?
Provision a worktree, load its .env.worktree settings, run a development server, and test it through Chrome DevTools Protocol or Playwright.
Why use it?
It prevents parallel agent sessions from using the wrong server, browser, or data by giving each worktree a shared environment contract.

Skill for Claude CodeCodex

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/devotts/parallel-lifecycle/parallel-lifecycle
Any agent
npx skills add DevOtts/parallel-lifecycle --skill parallel-lifecycle
Clone the repo
git clone --depth 1 https://github.com/DevOtts/parallel-lifecycle

Made for: Claude Code, Codex.

Per session 157 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 989 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00157 $0.00989
Opus 5 $0.00078 $0.00495
Sonnet 5 $0.00031 $0.00198
Haiku 4.5 $0.00016 $0.00099

Measured yesterday against content hash 37a47d2c146b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

parallel-lifecycle scanned grade A with 1 finding 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 yesterday.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

until curl -sf "http://127.0.0.1:$PORT" >/dev/null; do sleep 0.5; done
SKILL.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

parallel-lifecycle

Give every git worktree its own isolated, disposable runtime, so N parallel coding sessions never fight over port 3000, the database, or the browser. Everything keys off one generated contract file, .env.worktree.

Claude Code gets the full plugin: a SessionStart hook provisions each worktree automatically and a SessionEnd hook tears it down. On every other tool, this skill is the workflow and you run the provisioning script yourself (one command). The behavior is identical; only the auto-wiring differs.

0. Preflight (every session)

Confirm the worktree is provisioned:

test -f .env.worktree && cat .env.worktree || echo "NOT PROVISIONED"

If NOT PROVISIONED and you are inside a linked worktree (git rev-parse --git-dir != --git-common-dir), provision it once:

bash worktree-bootstrap.sh        # the bundled Layer 0 script

Then load the contract before any dev/test command:

set -a; source .env.worktree; set +a

.env.worktree carries APP_PORT / PORT, CDP_URL, and DATABASE_URL. Ports are deterministic free ports, written once — never auto-incremented (that silently points the test harness at the wrong URL).

1. Pick the browser model

Situation Model What to do
Testing your own app 1 (default) Use the worktree's ephemeral Chrome on $CDP_URL. Fully parallel.
Must use the real logged-in / anti-detection Chrome 3 (serialize) Drive it through your real-Chrome flow AND wrap the run in flock /tmp/cdp-9222.lock so only one session uses it at a time.

2. Run the app on the worktree's port

npm run dev                                   # framework reads PORT from env
until curl -sf "http://127.0.0.1:$PORT" >/dev/null; do sleep 0.5; done

3. Drive the worktree's Chrome (not :9222)

Connect over CDP to $CDP_URL. The repo ships a Playwright helper (connect.py) that reads the contract and returns a page. For authenticated flows, inject a saved Playwright storageState — never the real profile.

Read the full file on GitHub · 87 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. yesterday First seen · 87 lines · 157 tokens per session scan A 37a47d2c146b

Subscribe to this mod's changes

parallel-lifecycle is a skill published in the GitHub repository DevOtts/parallel-lifecycle (3 stars, last pushed 1mo ago), licensed MIT. It adds 157 tokens to every session and 989 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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

pinchtab

Use this skill when a task needs browser automation through PinchTab: open a website, inspect interactive elements, click through flows, fill out forms, scrape page text, reuse a dedicated automation profile with user approval, export screenshots or PDFs, manage multiple browser instances, or fall back to the HTTP API…

pinchtab/pinchtab · 94 tokens

pinchtab-mcp

Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.

pinchtab/pinchtab · 52 tokens

pinchtab-stealth-score

Run the PinchTab stealth-score sweep against 15 bot-detection / fingerprint sites (sannysoft, rebrowser, deviceandbrowserinfo, iphey, whoer, browserscan, pixelscan, fingerprint-scan, incolumitas, fvision, amiunique, browserleaks, creepjs, coveryourtracks, fingerprint-demo). Starts a Docker PinchTab container per…

pinchtab/pinchtab · 168 tokens

tmux

Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.

the-open-agent/openagent · 22 tokens

argent-device-interact

Interact with an iOS simulator, Android emulator, or Chromium (CDP) app using argent MCP tools. Use when tapping UI elements, performing gestures, scrolling/swiping, typing text, pressing hardware buttons, launching apps, opening URLs, taking screenshots, waiting for an element to appear or disappear, or checking…

software-mansion/argent · 73 tokens

argent-metro-debugger

Debug a JS runtime via CDP using argent debugger tools. Primary path is React Native via Metro (iOS / Android / Vega); a subset of the tools (debugger-connect, debugger-status, debugger-evaluate, debugger-log-registry) also drive a Chromium (CDP) app's renderer (an Electron app, or any Chromium browser exposing CDP)…

software-mansion/argent · 104 tokens