claude-parallel-writers SKILL.md skillA

claude-parallel-writers from nicholas-greenwood/agentic-engineering-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add nicholas-greenwood/agentic-engineering-skills/claude-parallel-writers@git:20261103.0e28fa2

Pins git:20261103.0e28fa2 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
nicholas-greenwood/agentic-engineering-skills
Path
claude-parallel-writers/SKILL.md
Versions recorded
1
Latest version
git:20261103.0e28fa2, committed Nov 3, 2026
Size
1,819 bytes
Repository stars
3
License
MIT

run parallel claude code writers, such as PR owners or dependency workers, as desktop sessions in their own worktrees, with sub-agents as the fallback.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

how a claude code orchestrator runs parallel writers, such as PR owners or dependency workers, each in its own worktree. codex does not use this skill: it runs parallel writers as new threads

- the app refuses `start_session` in any turn the user's own message didn't start, including turns a writer's message or note wakes. so start every writer your calling skill plans in the turn that invoked it
- `start_session` with `initiation: "user_asked"`, `use_worktree: true` and a short `name`
- a session's worktree can start from a stale local branch, so each prompt names the writer's base and tells it to reset its new branch to the freshly fetched base before it starts
- add your session id from `get_session` with `self` to each prompt, and tell the writer to send its result there with `SendMessage` before it ends its turn. the app's notes on writers' turns arrive only once every writer is idle and quote 400 characters, so read them as session status, never as results
- follow up with `SendMessage` to the writer's `local_…` session id
- for a writer that comes up later, or when `start_session` fails, use the first that works:
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add nicholas-greenwood/agentic-engineering-skills/claude-parallel-writers@sha256:5a3ba9e4e027dced

The line at the top of this page pins the label git:20261103.0e28fa2, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_ayds57am3zkcrcks.svg)](https://markdownregistry.com/a/art_ayds57am3zkcrcks)

2 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on Nov 3, 2026.

versioncommittedcommitsizeaudit
git:20261103.0e28fa2 latest2026-11-03 0e28fa2 1,819 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (1819 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

nicholas-greenwood/agentic-engineering-skills · 3 stars · license MIT · pushed 2026-11-07 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_ayds57am3zkcrcks
GET https://markdownregistry.com/api/v1/resolve?ref=nicholas-greenwood/agentic-engineering-skills/claude-parallel-writers
GET https://markdownregistry.com/api/v1/blob/5a3ba9e4e027dceddae34169808ecf1bdc02834f2cd8ba36eae693c11c8c4b51

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from nicholas-greenwood/agentic-engineering-skills

AGENTS.md AGENTS.md file
nicholas-greenwood/agentic-engineering-skills · AGENTS.md
git:20261027.18c3e07 · audit A · 3 stars
agent-browser-diff SKILL.md skill
nicholas-greenwood/agentic-engineering-skills · agent-browser-diff/SKILL.md · use when you need to verify code changes preserve UI appearance
git:20261029.4ede94a · audit A · 3 stars
ai-code-review-catalog SKILL.md skill
nicholas-greenwood/agentic-engineering-skills · ai-code-review-catalog/SKILL.md · available code reviewers, review prompts and model routing
git:20261105.38b36df · audit A · 3 stars
cross-harness-sub-agent SKILL.md skill
nicholas-greenwood/agentic-engineering-skills · cross-harness-sub-agent/SKILL.md · spawn a cross harness sub-agent
git:20261020.a5a8115 · audit A · 3 stars
helper-sub-agents SKILL.md skill
nicholas-greenwood/agentic-engineering-skills · helper-sub-agents/SKILL.md · shared rules for the helper sub-agents an orchestrating skill spawns
git:20261029.d5c74a0 · audit A · 3 stars
llm-evaluation SKILL.md skill
nicholas-greenwood/agentic-engineering-skills · llm-evaluation/SKILL.md · use when evaluating LLMs, prompts or workflows
git:20261027.5707fc6 · audit A · 3 stars
loop SKILL.md skill
nicholas-greenwood/agentic-engineering-skills · loop/SKILL.md · deliver a PR through implementation, review and validation rounds
git:20261107.27e854a · audit A · 3 stars
orchestrate-multi-pr-work SKILL.md skill
nicholas-greenwood/agentic-engineering-skills · orchestrate-multi-pr-work/SKILL.md · orchestrate multi-PR work
git:20261107.870f787 · audit A · 3 stars
plan SKILL.md skill
nicholas-greenwood/agentic-engineering-skills · plan/SKILL.md · use when user asks to write a plan or says "chat plan"/"md plan"/"linear plan"
git:20261103.11a0a1b · audit A · 3 stars
pr SKILL.md skill
nicholas-greenwood/agentic-engineering-skills · pr/SKILL.md · use before opening a PR or writing PR description
git:20261107.6259e5b · audit A · 3 stars
propose-refactor SKILL.md skill
nicholas-greenwood/agentic-engineering-skills · propose-refactor/SKILL.md · propose a refactor plan for an area
git:20261105.5786e71 · audit A · 3 stars
record-video SKILL.md skill
nicholas-greenwood/agentic-engineering-skills · record-video/SKILL.md · use when recording browser workflows in our app, external sites, dashboards or prototypes for PRs, evidence…
git:20261024.47ed487 · audit A · 3 stars

Every file in nicholas-greenwood/agentic-engineering-skills

Browse by kind, by grade A, or by owner.