What is gh-stack-parallel-work?

A coordination policy for implementing large changes across stacked GitHub pull requests, where each dependent pull request contains one layer of the work. It covers work spanning areas such as authentication, backend code, frontend code, and tests.

Use it when coordinating multi-layer `gh stack` work, deciding how to divide the layers, and assigning parallel implementation work.

It clarifies when stacked pull requests apply and keeps parallel work aligned with the official stack workflow and safe command forms.

How sabbour/agentweaver configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to sabbour/agentweaver. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/sabbour/agentweaver/dev/.github/skills/gh-stack-parallel-work/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/sabbour/agentweaver

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/sabbour/agentweaver/gh-stack-parallel-work/github.svg)](https://agentmods.dev/skills/sabbour/agentweaver/gh-stack-parallel-work)

Your own site

<a href="https://agentmods.dev/skills/sabbour/agentweaver/gh-stack-parallel-work"><img src="https://agentmods.dev/badge/skills/sabbour/agentweaver/gh-stack-parallel-work/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/sabbour/agentweaver/gh-stack-parallel-work"><img src="https://agentmods.dev/badge/skills/sabbour/agentweaver/gh-stack-parallel-work.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,212 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.

Model	Per session	Once invoked
Fable 5.1	$0.00019	$0.02212
Opus 5.5	$0.00008	$0.00885
Sonnet 5.5	$0.00004	$0.00442
Haiku 4.5	$0.00002	$0.00221

Measured 29d ago against content hash 2260765d7c03, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

gh-stack-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 29d 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.

.github/skills/gh-stack-parallel-work/SKILL.md · 205 lines

How it starts

The opening of the file, as written. The whole thing — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Scope

Use this overlay whenever work may use gh stack, dependent PR layers, or a large feature spanning auth, backend, frontend, and tests. It overrides generic agent ownership guidance, not the official gh stack operational guidance.

An actual stacked PR has two or more logical PR layers. A local one-branch tracking setup or an ordinary one-branch PR is not a stack. Use the normal Agentweaver PR workflow for ordinary PRs.

gh stack v0.1.0 is optional and only fits a genuinely dependent, strictly linear cohort. It is never the admission queue for independent issues. Independent changes use the temporary integration branch workflow below.

Ponytail implementation evidence

Coding agents use ponytail by default. After implementation they must:

run the exact affected validation from CONTRIBUTING.md;
rubber-duck the tested result, naming load-bearing assumptions, reused or deleted complexity, and any flaw found and fixed; then
stop and hand the exact branch tip to a different agent for ponytail-review.

The reviewer writes .squad/.scratch/ponytail-gates/<head-sha>.json using this contract:

{
  "kind": "agentweaver.ponytail-review/v1",
  "head_sha": "40-character commit SHA",
  "implementer": "agent or contributor",
  "reviewer": "different agent or contributor",
  "implementer_validation": {
    "commands": ["exact command"]
  },
  "rubber_duck": {
    "assumptions": ["load-bearing assumption"],
    "simplifications": ["what was deleted or reused"],
    "flaw": "what was fixed, or an explicit statement that none was found"
  },
  "findings": [
    {
      "id": "PT-001",
      "confidence": "high",
      "summary": "unnecessary complexity",
      "location": "repo/path:line",
      "waiver": {
        "justification": "why this complexity is necessary",
        "approved_by": "accountable approver"
      }
    }
  ]
}

Omit waiver when none exists. Admission is derived: every high-confidence finding must have an explicit waiver with a non-empty justification and accountable approver, or the gate blocks. Lower-confidence findings remain review feedback. Git and PR history are the authoritative timestamps; the gate does not self-attest ceremony times or a redundant verdict. Validate the file against the exact candidate tip:

Read the full file on GitHub · 205 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.

29d ago Changed · +2 lines 2260765d7c03
1mo ago Changed · +24 lines 7d98a89d47c5
1mo ago Changed · +85 lines c58bfae6345d
1mo ago First seen · 94 lines · 19 tokens per session scan A c50b553ca872

Subscribe to this mod's changes

gh-stack-parallel-work is a skill published in the GitHub repository sabbour/agentweaver (7 stars, last pushed today), licensed MIT. It adds 19 tokens to every session and 2,212 once invoked, about $0.0001 per session on Opus 5.5. 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.

Git and workflow Project management agent-orchestration ai-agents aks dotnet human-in-the-loop kubernetes

gh-assign-issues

Use to assign GitHub issues to a milestone and/or owners in bulk, verifying each.

Hmbown/CodeWhale · 24 tokens

merge-review

Reviews pending fleet worktree merges before they're accepted. Reads the merge-check queue, detects file-level conflicts between branches, proposes a safe merge order, and surfaces reconciliation plans for overlapping changes.

SethGammon/Citadel · 40 tokens

ship-it

Worktree-side implementation orchestrator for an OpenSpec change. Idempotent: gates automated scenarios on filesystem reality, owns the red-test fix loop, runs the docker harness with always-teardown, then drives ship-change inline. Escape hatch writes SHIPITBLOCKED.md. Runnable headless. Triggers: "ship it", "build…

BlackBeltTechnology/pi-agent-dashboard · 92 tokens

agentweaver: Skill for Claude Code