siege

siege is a skill for Claude Code from Kasempiternal/Claude-Agent-System. It costs 52 tokens per session (5,168 once invoked), scanned B, original, MIT.

An external orchestration workflow that starts separate Claude sessions to do work and independently check it. It makes stop decisions from recorded checks rather than from the orchestrator’s own review.

In plain words
What is it for?
Use it to run repeated worker-and-reviewer iterations when the required Claude agent-team environment is available.
Why use it?
It separates execution from verification so the same worker does not judge its own result.

Skill for Claude Code

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

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

Good fit Use it to run repeated worker-and-reviewer iterations when the required Claude agent-team…

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/kasempiternal/claude-agent-system/siege.svg)](https://agentmods.dev/skills/kasempiternal/claude-agent-system/siege)
Your own site
<a href="https://agentmods.dev/skills/kasempiternal/claude-agent-system/siege"><img src="https://agentmods.dev/badge/skills/kasempiternal/claude-agent-system/siege.svg" alt="Measured on agentmods" height="20"></a>
Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,168 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. 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 $0.00052 $0.05168
Opus 5 $0.00026 $0.02584
Sonnet 5 $0.00010 $0.01034
Haiku 4.5 $0.00005 $0.00517

Measured 7d ago against content hash 749feadffa10, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade B, and why

siege scanned grade B with 1 finding 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 7d 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

Read `~/.claude/settings.json`. Verify `env.CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS` is `"1"`.
claude-agent-system-plugin/skills/siege/SKILL.md · 520 lines

How it starts

The opening of the file, as written. The whole thing — 520 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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

       ⚔ Fortress Orchestrator ⚔
         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 SIEGE ORCHESTRATOR MODE. You are a thin orchestrator loop — you spawn external claude -p sessions for workers and verifiers, read their structured result files from disk, and make arithmetic exit decisions only. You NEVER read source code, judge quality, or implement anything.

This is SIEGE: A three-tier architecture — orchestrator (you), workers (fresh sessions), and verifiers (independent sessions). Workers can't refuse re-spawning. Verifiers evaluate work they didn't produce. Exit decisions are arithmetic, not judgment.

Your Role: Thin Orchestrator

  • You spawn claude -p sessions via Bash and read their result files from disk
  • You grep result files for structured fields (P1_CHECKED, TEST_EXIT_CODE, etc.)
  • You make decisions using ONLY arithmetic comparisons on parsed numbers
  • You NEVER read project source code, review implementations, or judge quality
  • All heavy work happens in spawned sessions; you are an arithmetic-only outer loop

Phase 0: Prerequisites

Step 1: Locate Skill Directory

Use Glob to find your templates: Glob("**/skills/siege/templates/worker-full-prompt.md"). Extract the parent directory path (everything before /templates/). Store as SIEGE_SKILL_DIR.

Step 1.5: Locate Monitor Script (REQUIRED)

Set MONITOR_SCRIPT = {SIEGE_SKILL_DIR}/../../scripts/siege-monitor.py

Verify via Bash: test -f "{MONITOR_SCRIPT}" && echo "found" || echo "missing"

  • If missing: STOP. Tell the user:
    SIEGE ERROR: Monitor script not found at {MONITOR_SCRIPT}
    The monitor is required — it detects worker completion and prevents hangs.
    Reinstall the plugin: /plugin update cas
    
    Do NOT proceed without the monitor.
  • If found: Display SIEGE: Progress monitor found

Read the full file on GitHub · 520 lines

Files

What ships with it

6 files 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.

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. 7d ago First seen · 520 lines · 52 tokens per session scan B 749feadffa10

Subscribe to this mod's changes

siege is a skill published in the GitHub repository Kasempiternal/Claude-Agent-System (15 stars, last pushed 1mo ago), licensed MIT. It adds 52 tokens to every session and 5,168 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). 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

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

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

codex-loop

Fix Elixir/Phoenix code until Codex CLI review comes back clean — bounded review, fix, verify loop before opening a PR. Use when codex is installed and you want an external cross-model critic on your changes before pushing.

oliver-kriska/claude-elixir-phoenix · 52 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

codex-ab

Run an A/B codex review experiment — holistic codex review vs 3 focused dimension passes (security, ecto, liveview) on the branch diff, classify findings, report a panel-value verdict. Use when the branch is fresh, before any codex review runs.

oliver-kriska/claude-elixir-phoenix · 60 tokens