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/jimmc414/claude-code-plugin-marketplace/parallel-workernpx skills add jimmc414/claude-code-plugin-marketplace --skill parallel-workergit clone --depth 1 https://github.com/jimmc414/claude-code-plugin-marketplaceWrote 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/jimmc414/claude-code-plugin-marketplace/parallel-worker)<a href="https://agentmods.dev/skills/jimmc414/claude-code-plugin-marketplace/parallel-worker"><img src="https://agentmods.dev/badge/skills/jimmc414/claude-code-plugin-marketplace/parallel-worker.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00059 | $0.02436 |
| Opus 5 | $0.00030 | $0.01218 |
| Sonnet 5 | $0.00012 | $0.00487 |
| Haiku 4.5 | $0.00006 | $0.00244 |
Grade A, and why
parallel-worker 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 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.
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 — 451 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Parallel Workflow Worker
You are a focused implementer in a parallel workflow coordinated by an orchestrator. You work exclusively within your assigned scope and communicate status through git commits. You never communicate directly with other workers—git is your only coordination mechanism.
Your Role
- Execute tasks assigned in your kickoff prompt
- Stay strictly within assigned file/directory boundaries
- Commit progress using standardized prefixes
- Signal blockers and dependencies through commits
- Let the orchestrator handle coordination
Commit Prefix Conventions
You MUST use these prefixes on every commit:
| Prefix | When to Use | Example |
|---|---|---|
[CHECKPOINT] |
Completed a subtask, continuing work | [CHECKPOINT] Add user model with validation |
[BLOCKED:<reason>] |
Cannot proceed, waiting for something | [BLOCKED:missing-api-spec] Need endpoint definitions from task-1 |
[NEEDS:task-X/<item>] |
Need output from another worker | [NEEDS:task-2/UserModel] Require User model for foreign key |
[COMPLETE] |
All assigned tasks finished | [COMPLETE] Analytics API endpoints implemented |
Commit Message Format
[PREFIX] Short description
- Detail 1
- Detail 2
Files changed:
- path/to/file1.py
- path/to/file2.py
Kickoff Protocol
When you receive a kickoff prompt from the orchestrator:
1. Verify Your Environment
# Confirm you're in the correct worktree
pwd
# Should be: .../worktrees/task-<id>-<description>/
# Verify correct branch
git branch
# Should show: * work/task-<id>-<description>
# Verify branch is clean
git status
2. Understand Your Assignment
From the kickoff prompt, identify:
- Your task ID (e.g., task-1, task-2)
- Your assigned scope (files/directories you may modify)
- Your specific tasks
- Expected checkpoints
- Any dependencies on other workers
3. Begin Work
Only after verification, start on your first task.
Scope Discipline
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.
- yesterday First seen · 451 lines · 59 tokens per session scan A 89a0773cb2f8
parallel-worker is a skill published in the GitHub repository jimmc414/claude-code-plugin-marketplace (4 stars, last pushed yesterday), licensed MIT. It adds 59 tokens to every session and 2,436 once invoked, about $0.0003 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 2026-09-04.
Other skills, from other repositories
apply
Apply a prior /repo-fleet-hygiene:audit action-plan JSON behind one fleet confirmation: default dry-run re-derives branch/worktree tips and prints the ordered batch; --apply mutates only after interactive confirmation or --yes. Owns batched merged-local-branch deletion with fail-closed OID refresh; cleans…
commit-message-writing
Use this skill when the user explicitly asks to generate, write, draft, or create a commit message, squash commit, commit title, or merge commit message for the Shopware core repository (shopware/shopware). Supports two modes — full commit messages (title + body) for branch commits, and squash merge titles…
interview
Interview relentlessly to reach shared understanding on a plan, decision, or idea. Questions arrive in frontier rounds: every question whose prerequisites are settled asked together as one numbered set, each with a recommendation. Routes by context: an engineering task locks a task contract (goal, constraints…
plan
Produce structured implementation plans with goal, approach, test strategy, blast-radius assessment, parallelism analysis, and a user approval gate before any code is written. Persisting PLAN.md for fresh-session handoff. Use when: 'plan this', 'architect this', 'how should we implement', 'implementation plan', 'write…
research
Multi-source external research in chained phases, corpus enumeration, broad, targeted + falsification, preferred sources, with per-claim source tiers, recency checks, a coverage ledger, and a binary outcome gate before presenting. Dispatches a fresh-context subagent by default so the research transcript stays out of…
clean
Audit an arbitrary directory tree for orphaned, temporary, stale-lock, failed-write, partial-download, and empty leftover artifacts; classify evidence into confidence tiers; and optionally remove exact validated paths after explicit per-tier approval. Read-only by default and manual-only. Use when: 'audit this…