pcc-opus

pcc-opus is a skill for Claude Code from Kasempiternal/Claude-Agent-System. It costs 39 tokens per session (3,345 once invoked), scanned A, original, MIT.

A coordinator for complex coding tasks that sends exploration and implementation work to multiple Claude Opus agents in parallel. Opus is a Claude model designed for demanding reasoning tasks.

In plain words
What is it for?
Use it for critical or complex coding tasks where thorough exploration and high-quality implementation are important.
Why use it?
It reduces the need for one agent to investigate every part of a difficult task in sequence. Parallel work can explore more possible solutions before implementation.

Skill for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: model in frontmatter; names the AskUserQuestion tool.

Part of the cas plugin — 19 skills, 3 hooks, 2 MCP servers shipped together

Good fit Use it for critical or complex coding tasks where thorough exploration and high-quality implementation are important.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kasempiternal/claude-agent-system/pcc-opus
Install

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.

Any agent
npx skills add Kasempiternal/Claude-Agent-System --skill pcc-opus
Clone the repo
git clone --depth 1 https://github.com/Kasempiternal/Claude-Agent-System

Made for: Claude Code.

Or install cas, the plugin that ships this one along with the rest of its 19 skills, 3 hooks, 2 MCP servers.

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.

agentmods badge for pcc-opus

README.md
[![agentmods](https://agentmods.dev/badge/skills/kasempiternal/claude-agent-system/pcc-opus/github.svg)](https://agentmods.dev/skills/kasempiternal/claude-agent-system/pcc-opus)
Your own site
<a href="https://agentmods.dev/skills/kasempiternal/claude-agent-system/pcc-opus"><img src="https://agentmods.dev/badge/skills/kasempiternal/claude-agent-system/pcc-opus/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.

agentmods 80×15 button for pcc-opus

Your own site · 80×15
<a href="https://agentmods.dev/skills/kasempiternal/claude-agent-system/pcc-opus"><img src="https://agentmods.dev/badge/skills/kasempiternal/claude-agent-system/pcc-opus.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,345 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00039 $0.03345
Opus 5 $0.00019 $0.01673
Sonnet 5 $0.00008 $0.00669
Haiku 4.5 $0.00004 $0.00334

Measured 9d ago against content hash f88ccda5abb0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

pcc-opus 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 9d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

  • pcc — 89% identical, 69 lines differ
claude-agent-system-plugin/skills/pcc-opus/SKILL.md · 435 lines

How it starts

The opening of the file, as written. The whole thing — 435 lines — stays where its author put it; the contents beside it link to each section on GitHub.

██████╗  ██████╗ ██████╗
██╔══██╗██╔════╝██╔════╝
██████╔╝██║     ██║
██╔═══╝ ██║     ██║
██║     ╚██████╗╚██████╗
╚═╝      ╚═════╝ ╚═════╝

  ⚔ Parallel Coordinator ⚔
      ◈ OPUS EDITION ◈
     CLAUDE AGENT SYSTEM

MANDATORY: Output the banner above verbatim as your very first message to the user, before any tool calls or other output.

You are entering ORCHESTRATOR MODE (OPUS EDITION). You are Opus, the orchestrator. Your role is to COORDINATE and DELEGATE - you should do minimal direct work yourself. Instead, you spawn agents to do the actual exploration and implementation work in parallel.

This is the OPUS EDITION: Both exploration AND implementation use Opus agents for maximum quality and reasoning depth.

Your Role: Orchestrator

  • You are the BRAIN, not the HANDS
  • You spawn agents to do exploration and implementation
  • You synthesize results and make decisions
  • You maximize parallelization at all times
  • You NEVER implement code directly - you delegate to agents

Phase 1: Task Understanding

First, clearly state your understanding of the task: $ARGUMENTS

If the task is unclear, use AskUserQuestion to clarify before proceeding.


Phase 2: Parallel Exploration (2-6 Opus Agents)

SCOUT MODEL: Opus (maximum quality exploration for complex codebases)

DYNAMIC AGENT COUNT: Based on task complexity, spawn 2 to 6 Explore agents in parallel using the Task tool with subagent_type='Explore' and model='opus'.

Determining Agent Count

Assess the task and decide how many scouts are needed:

Complexity Agent Count When to Use
Simple 2 Single-file changes, typo fixes, small config updates
Low 3 Single-module changes, simple feature additions
Medium 4 Multi-file changes within one area, moderate features
High 5 Cross-module changes, complex features
Very High 6 Architecture changes, major refactors, system-wide impact

CRITICAL: Launch ALL chosen agents in a SINGLE message with multiple Task tool calls.

Read the full file on GitHub · 435 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.

  1. 9d ago First seen · 435 lines · 39 tokens per session scan A f88ccda5abb0

Subscribe to this mod's changes

pcc-opus is a skill published in the GitHub repository Kasempiternal/Claude-Agent-System (15 stars, last pushed 1mo ago), licensed MIT. It adds 39 tokens to every session and 3,345 once invoked, about $0.0002 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 2026-08-30.

Related

Other skills, from other repositories

audit

Project health audit and health check — architecture, performance, tests, dependencies, code quality. Use when assessing overall project health, before releases, or after refactors.

oliver-kriska/claude-elixir-phoenix · 35 tokens

review

Review code with parallel agents — tests, security, Ecto, LiveView, Oban. Use after implementation to catch bugs and anti-patterns before committing.

oliver-kriska/claude-elixir-phoenix · 34 tokens

pr-review

Address feedback left on a GitHub pull request: fetch unresolved review threads, make agreed Elixir/Phoenix code fixes, reply, and resolve. Use for a PR URL/number or reviewer comments. NOT for pre-PR review, findings triage, or CI monitoring.

oliver-kriska/claude-elixir-phoenix · 59 tokens

phx-pr-review

Address feedback left on a GitHub pull request: fetch unresolved review threads, make agreed Elixir/Phoenix code fixes, reply, and resolve. Use for a PR URL/number or reviewer comments. NOT for pre-PR review, findings triage, or CI monitoring.

oliver-kriska/claude-elixir-phoenix · 61 tokens

boundaries

Analyze Phoenix context boundaries and module coupling via mix xref. Use when checking cross-context calls, validating dependencies, before splitting modules, or reviewing architecture.

oliver-kriska/claude-elixir-phoenix · 33 tokens

challenge

Challenge mode reviews - rigorous questioning before approving changes. Use when you want thorough scrutiny of Ecto changes, LiveView events, OTP designs, or PR readiness.

oliver-kriska/claude-elixir-phoenix · 34 tokens