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.
npx agentmods add skills/sabbour/agentweaver/gh-stack-parallel-worknpx skills add sabbour/agentweaver --skill gh-stack-parallel-workgit clone --depth 1 https://github.com/sabbour/agentweaverWhat 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 | $0.00019 | $0.01006 |
| Opus 5 | $0.00010 | $0.00503 |
| Sonnet 5 | $0.00004 | $0.00201 |
| Haiku 4.5 | $0.00002 | $0.00101 |
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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 94 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.
Authoritative operational reference
Before deciding whether work belongs in a stack, or choosing its layers' count, order, or content, coordinators must read the official stack-design reference. Read the official gh-stack skill before running any stack command. It is authoritative for command syntax and flags, command behavior and side effects, errors and recovery, non-interactive forms, remote selection, and stack-design references.
In particular, coordinators must use the official safe non-interactive forms: JSON view
output, automatic PR submission, and explicit branch names for initialization and added
layers. The official skill and command-specific gh stack <command> --help define
supported flags and remote selection. Its multi-remote --remote <name> rule applies
only to supported push, submit, sync, rebase, and link operations; init
does not accept --remote. Do not invent flags or rely on interactive prompts.
Coordinator-owned stack lifecycle
Only the coordinator owns feature stack topology and lifecycle. The coordinator:
- analyzes dependencies and chooses atomic, ordered review layers;
- centrally initializes the stack once, with exact ordered branch names, and adds later layers centrally;
- gives every agent an isolated worktree, assigned branch, lower-layer dependency, and full stack context;
- serializes stack commands. A stack state can be locked, so agents and coordinators do not run competing operations against the same stack;
- submits, synchronizes, rebases, pushes, and links the stack; and
- coordinates review, merge readiness, and recovery.
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.
- 2d ago First seen · 94 lines · 19 tokens per session scan A c50b553ca872
gh-stack-parallel-work is a skill published in the GitHub repository sabbour/agentweaver (5 stars, last pushed 2d ago), licensed MIT. It adds 19 tokens to every session and 1,006 once invoked, about $0.0001 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.
Other skills, from other repositories
auditing-kubernetes-cluster-rbac
Auditing Kubernetes cluster RBAC configurations to identify overly permissive roles, wildcard permissions, dangerous ClusterRoleBindings, service account abuse, and privilege escalation paths using kubectl, rbac-tool, KubiScan, and Kubeaudit.
agent-workflow-playbook
AI Agent Workflow & Skill Architecture Guide — turn expert work into measurable, reusable agent systems. Covers workflow discovery, skill decomposition, harness design, evaluation, human escalation, observability, cost control, and multi-agent orchestration. Includes a measured marketing-delivery case: 15 people × 3–4…
dotnet-microsoft-agent-framework
Build .NET AI agents and multi-agent workflows with Microsoft Agent Framework using the right agent type, threads, tools, workflows, hosting protocols, and enterprise guardrails.
dotnet-microsoft-extensions-ai
Build provider-agnostic .NET AI integrations with Microsoft.Extensions.AI, IChatClient, embeddings, middleware, structured output, vector search, and evaluation.
dotnet-orleans
Build or review distributed .NET applications with Orleans grains, silos, persistence, streaming, reminders, placement, testing, and cloud-native hosting.
mcaf-dotnet
Primary entry skill for C# and .NET tasks. Detect the repo's language version, test runner, quality stack, and architecture rules; route to the right .NET subskills; and run the repo-defined post-change quality pass after any code change. Use when the user asks to implement, debug, review, or refactor .NET code, or…