Borrowing it
Nothing to install: this file belongs to shep-ai/shep. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/shep-ai/shep/main/.claude/skills/shep-kit-parallel-task/SKILL.mdgit clone --depth 1 https://github.com/shep-ai/shepWrote 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.
[](https://agentmods.dev/skills/shep-ai/shep/shep-kit-parallel-task)<a href="https://agentmods.dev/skills/shep-ai/shep/shep-kit-parallel-task"><img src="https://agentmods.dev/badge/skills/shep-ai/shep/shep-kit-parallel-task/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.
<a href="https://agentmods.dev/skills/shep-ai/shep/shep-kit-parallel-task"><img src="https://agentmods.dev/badge/skills/shep-ai/shep/shep-kit-parallel-task.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00081 | $0.02018 |
| Opus 5.5 | $0.00032 | $0.00807 |
| Sonnet 5.5 | $0.00016 | $0.00404 |
| Haiku 4.5 | $0.00008 | $0.00202 |
Grade A, and why
shep-kit:parallel-task 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 1mo 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 — 255 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Parallel Task via Git Worktree
Create an isolated worktree in .worktrees/ branched from up-to-date main, with spec directory scaffolded.
When to Use
- Working on an independent task that doesn't block or depend on current work
- Need isolation from the current branch's in-progress changes
- Running long builds/tests while continuing other work
Workflow
digraph parallel_task {
rankdir=TB;
node [shape=box];
start [label="Start" shape=ellipse];
get_desc [label="User provides high-level\ntask description"];
derive [label="Derive dir name, branch name,\nand feature name from description"];
create_wt [label="create-worktree.sh\n<dir-name> <branch-name>"];
install [label="pnpm install in worktree"];
init_spec [label="Run init-feature.sh\ninside worktree"];
fix_yaml [label="Patch feature.yaml\nwith correct branch name"];
fill_spec [label="Fill spec.md with\nrequirements (if provided)"];
commit [label="git add + commit\nspec scaffold"];
open_editor [label="Open editor in worktree"];
success [label="Report: editor opening..." shape=ellipse];
fail [label="Report: manual instructions" shape=ellipse];
start -> get_desc;
get_desc -> derive;
derive -> create_wt;
create_wt -> install;
install -> init_spec;
init_spec -> fix_yaml;
fix_yaml -> fill_spec;
fill_spec -> commit;
commit -> open_editor;
open_editor -> success [label="success"];
open_editor -> fail [label="fail"];
}
Steps
1. Get Task Description
The user provides a high-level description of what the parallel task is about.
Examples:
- "fix the version display bug in settings"
- "add retry logic to the agent HTTP calls"
- "refactor DI container registration"
2. Derive Names
From the description, generate:
- Dir name: Short kebab-case identifier for the worktree directory (e.g.,
fix-version-display,add-agent-retry,refactor-di-container) - Branch name: Conventional branch name using the project's prefix conventions (e.g.,
fix/version-display,feat/agent-retry,refactor/di-container) - Feature name: Kebab-case name for the spec directory (same as dir name or adjusted)
What ships with it
1 file 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.
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.
- 1mo ago First seen · 255 lines · 81 tokens per session scan A 33a85565f1b6
shep-kit:parallel-task is a skill published in the GitHub repository shep-ai/shep (267 stars, last pushed yesterday), licensed MIT. It adds 81 tokens to every session and 2,018 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
git-advanced-workflows
Master advanced Git workflows including rebasing, cherry-picking, bisect, worktrees, and reflog to maintain clean history and recover from any situation. Use when managing complex Git histories, collaborating on feature branches, or troubleshooting repository issues.
workflow-patterns
Use this skill when implementing tasks according to Conductor's TDD workflow, handling phase checkpoints, managing git commits for tasks, or understanding the verification protocol.
block-no-verify-hook
Configure a PreToolUse hook to prevent AI agents from skipping git pre-commit hooks with --no-verify and other bypass flags. Use when setting up Claude Code projects that enforce commit quality gates.
turborepo-caching
Configure Turborepo for efficient monorepo builds with local and remote caching. Use when setting up Turborepo, optimizing build pipelines, or implementing distributed caching.
odh-llm-d-release
Orchestrate the opendatahub-io release for all llm-d components in one cycle. Collects upstream(llm-d) versions, auto-discovers the release tracker issue, then spawns parallel sub-agents — one per component (release branch, Konflux onboarder workflow, PR validation, approve+merge, Quay image verify, GitHub draft…
aipcc-commit-suggest
Generate AIPCC Commits style commit messages or summarize existing commits.