Coding Agent System - unified memory, tasks, rules, and skills.

MITAuto-check passedAgent Workflows

Install Cas

skills CLI
$ npx skills add codingagentsystem/cas --skill cas -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install codingagentsystem/cas cas --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/codingagentsystem/cas.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/cas .claude/skills/cas && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
cas
GitHub stars
176
Token cost
~723 tokens
SKILL.md length
338 words
Files
1
Skills in repo
7
Repo updated
First seen
Licence
MIT

At a glance

Coding Agent System - unified memory, tasks, rules, and skills.

  • You need to remember something
  • SKILL.md covers WHEN TO USE CAS (ALWAYS), Task Tools (USE INSTEAD OF…, Memory Tools and Search Tools, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Search past context

What it does

Cas is an agent skill from codingagentsystem/cas. Coding Agent System - unified memory, tasks, rules, and skills. Use when you need to remember something, track work, search past context, or manage tasks. (project)

Its SKILL.md is about 720 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows. It works with Model Context Protocol. The repository describes itself as: Multi-agent orchestration for Claude Code. Persistent memory, tasks, rules, and skills that make AI agents actually coordinate. The licence is MIT.

When your agent uses it

  • You need to remember something
  • Search past context

Example prompts

  • “/cas”

What it can do on your machine

Read from SKILL.md and the folder at commit a0a4b5a. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Cas loads about 723 tokens when it runs. Until then it costs about 42 tokens; SKILL.md has 338 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~42
When it runs · the whole SKILL.md, loaded when a task matches
~723

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from codingagentsystem/cas at commit a0a4b5a, republished under its MIT licence (© codingagentsystem). 338 words, ~723 tokens.

Download SKILL.mdSave it as .claude/skills/cas/SKILL.md (or your agent's skills folder).
name
cas
description
Coding Agent System - unified memory, tasks, rules, and skills. Use when you need to remember something, track work, search past context, or manage tasks. (project)
managed_by
cas

CAS - Coding Agent System

IMPORTANT: Use CAS MCP tools instead of built-in tools for task and memory management.

CAS provides persistent memory and task management across sessions. Built-in tools like TodoWrite are ephemeral and don't persist.

WHEN TO USE CAS (ALWAYS)

  • Task tracking: Use mcp__cas__task with action: create instead of TodoWrite
  • Planning tasks: Use mcp__cas__task with action: create and blocked_by for dependencies
  • Storing learnings: Use mcp__cas__memory with action: remember to store context
  • Searching context: Use mcp__cas__search with action: search to find past work

Task Tools (USE INSTEAD OF TodoWrite)

Creating Tasks

Use mcp__cas__task with action: create and parameters:

  • title (required) - Task title
  • priority - 0=critical, 1=high, 2=medium (default), 3=low, 4=backlog
  • start - Set to true to start immediately (RECOMMENDED)
  • notes - Initial working notes
Managing Tasks

All task operations use mcp__cas__task with different actions:

  • action: ready - Show tasks ready to work on
  • action: blocked - Show blocked tasks
  • action: list - List all tasks
  • action: show - Show task details (requires id)
  • action: update - Update notes as you work (requires id)
  • action: close - Close with resolution (requires id)
Task Dependencies
  • action: dep_add - Add blocking dependency (requires id, to_id)
  • action: dep_list - List dependencies (requires id)

Memory Tools

All memory operations use mcp__cas__memory with different actions:

  • action: remember - Store a memory entry (requires content)
  • action: get - Get entry details (requires id)
  • action: helpful - Mark as helpful (requires id)
  • action: harmful - Mark as harmful (requires id)

Search Tools

Use mcp__cas__search with different actions:

  • action: search - Search memories (requires query)
  • action: context - Get full session context

Iteration Loops

Use loops for long-running repetitive tasks. The loop blocks session exit and re-injects your prompt until completion.

Use mcp__cas__coordination with different actions:

  • action: loop_start - Start a loop (requires prompt, session_id, optional completion_promise and max_iterations)
  • action: loop_status - Check current loop status (requires session_id)
  • action: loop_cancel - Cancel active loop (requires session_id)

To complete a loop, output <promise>DONE</promise> (or your custom promise text).

Rules & Skills

Use mcp__cas__rule and mcp__cas__skill with different actions:

  • rule action: list - Show active rules
  • rule action: helpful - Promote rule to proven (requires id)
  • skill action: list - Show enabled skills

© codingagentsystem, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/cas of codingagentsystem/cas.

Open the folder on GitHubat commit a0a4b5a

Compare with similar skills

Cas next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Cas compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Cas this skillcodingagentsystem/cas176—~723Automated safety check: PassMIT
MCP Server Builderanthropics/skills180k62 repos~2.3kAutomated safety check: PassApache-2.0
MCP Server BuildershareAI-lab/learn-claude-code78k5 repos~1.2kAutomated safety check: PassMIT
MCP Integration for Pluginsanthropics/claude-plugins-official37k11 repos~3.1kAutomated safety check: PassApache-2.0
Fastmcp Client CLIPrefectHQ/fastmcp28k1 repos~823Automated safety check: PassApache-2.0
MemPalace Memory SearchMemPalace/mempalace59k—~1.4kAutomated safety check: PassMIT

Similar skills

  • MCP Server Builder

    anthropics/skills

    Official

    Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.

    180k GitHub starsUsed in 62 repos~2.3k tokens
    Agent WorkflowsAuto-check passed
  • MCP Server Builder

    shareAI-lab/learn-claude-code

    Walks through building MCP servers in Python or TypeScript that expose tools, resources and prompts to Claude, with templates, registration and testing.

    78k GitHub starsUsed in 5 repos~1.2k tokens
    Agent WorkflowsAuto-check passed
  • MCP Integration for Plugins

    anthropics/claude-plugins-official

    Official

    Explains how to bundle Model Context Protocol servers in a Claude Code plugin, covering config files, stdio, SSE, HTTP and WebSocket server types, and authentication.

    37k GitHub starsUsed in 11 repos~3.1k tokens
    Agent WorkflowsAuto-check passed
  • Fastmcp Client CLI

    PrefectHQ/fastmcp

    Query and invoke tools on MCP servers using fastmcp list and fastmcp call.

    28k GitHub starsUsed in 1 repo~823 tokens
    Agent WorkflowsAuto-check passed
  • MemPalace Memory Search

    MemPalace/mempalace

    Mines project files and conversation exports into a local, searchable memory palace and recalls past work by semantic search through the mempalace CLI.

    59k GitHub stars~1.4k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Crush Configuration

    charmbracelet/crush

    Explains how to configure the Crush coding agent with crushrc or crush.json, covering providers, models, LSPs, MCP servers, hooks, permissions and config precedence.

    29k GitHub stars~3.7k tokensUpdated today
    Agent WorkflowsAuto-check passed

More from codingagentsystem/cas

  • Cas Search

    codingagentsystem/cas

    Search across CAS content (memories, tasks, rules, skills, code).

    176 GitHub stars~516 tokensUpdated 6 mo ago
    Auto-check passed
  • Cas Supervisor

    codingagentsystem/cas

    Factory supervisor guide for multi-agent EPIC orchestration.

    176 GitHub stars~1.8k tokensUpdated 6 mo ago
    Auto-check passed
  • Cas Worker

    codingagentsystem/cas

    Factory worker guide for task execution in CAS multi-agent sessions.

    176 GitHub stars~1.2k tokensUpdated 6 mo ago
    Auto-check passed
  • Cas Memory Management

    codingagentsystem/cas

    How to store and retrieve persistent memories using CAS. An agent skill from codingagentsystem/cas.

    176 GitHub stars~255 tokensUpdated 6 mo ago
    Auto-check passed
  • Cas Supervisor Checklist

    codingagentsystem/cas

    Quick startup checklist for factory supervisors. An agent skill from codingagentsystem/cas.

    176 GitHub stars~349 tokensUpdated 6 mo ago
    Auto-check passed
  • Cas Task Tracking

    codingagentsystem/cas

    How to track work using CAS tasks instead of built-in TodoWrite.

    176 GitHub stars~279 tokensUpdated 6 mo ago
    Auto-check passed

Categories

Questions about Cas

What does Cas do?

Coding Agent System - unified memory, tasks, rules, and skills. Cas is an agent skill from codingagentsystem/cas. Coding Agent System - unified memory, tasks, rules, and skills.

When should I use Cas?

Cas fits situations like: you need to remember something; search past context.

How do I install Cas in Claude Code?

Run `npx skills add codingagentsystem/cas --skill cas -a claude-code`. Or copy the skill folder (.claude/skills/cas in codingagentsystem/cas) into .claude/skills/cas in your project. Claude Code loads it when a task matches its description.

How do I install Cas in Codex?

Run `npx skills add codingagentsystem/cas --skill cas -a codex`. Or copy the skill folder (.claude/skills/cas in codingagentsystem/cas) into .agents/skills/cas in your project. Codex loads it when a task matches its description.

Can I use Cas in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add codingagentsystem/cas --skill cas -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/cas, .gemini/skills/cas, .github/skills/cas and .opencode/skills/cas in your project.

What does Cas need to run?

SKILL.md names no scripts, command-line tools or credentials: Cas is instructions for the agent only.

Does Cas access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Cas safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Cas use?

Cas is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Cas use?

About 723 tokens (SKILL.md is roughly 2.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Cas?

Skills that share tags, products or a category with Cas: MCP Server Builder (anthropics/skills, 180k stars), MCP Server Builder (shareAI-lab/learn-claude-code, 78k stars), MCP Integration for Plugins (anthropics/claude-plugins-official, 37k stars) and Fastmcp Client CLI (PrefectHQ/fastmcp, 28k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Cas?

codingagentsystem (a GitHub organization) maintains it in codingagentsystem/cas, which has 176 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on March 12, 2026.

Source: codingagentsystem/cas on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.