A coding-agent add-on for evidence-based research, delegated agent work, parallel tasks, and controlled approval of sensitive actions such as deleting files or pushing Git changes.

It is for coordinating coding-agent work, protecting confidential values, running independent tasks in parallel, and requiring approval before selected Git or file actions.

It adds checks around research, delegation, secrets, and potentially risky repository operations.

cas — Plugin for Claude Code by Kasempiternal: A coding-agent add-on for evidence-based research, delegated agent work…

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.

Claude Code

/plugin marketplace add Kasempiternal/Claude-Agent-System

agentmods

npx agentmods add plugins/kasempiternal/claude-agent-system/cas

Clone the repo

git clone --depth 1 https://github.com/Kasempiternal/Claude-Agent-System

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/plugins/kasempiternal/claude-agent-system/cas.svg)](https://agentmods.dev/plugins/kasempiternal/claude-agent-system/cas)

Your own site

<a href="https://agentmods.dev/plugins/kasempiternal/claude-agent-system/cas"><img src="https://agentmods.dev/badge/plugins/kasempiternal/claude-agent-system/cas.svg" alt="Measured on agentmods" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan A 0 findings. Scan, not verified.

Origin unknown No closer match found in the catalogue.

Security

Grade A, and why

cas 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.

.claude-plugin/marketplace.json#cas · 6 lines

What it actually says

{
  "name": "cas",
  "version": "7.37.0",
  "description": "Evidence-driven research, guarded Codex delegation, explicit native parallelism, secret protection, and approval gates for rm, commit, and push.",
  "source": "./claude-agent-system-plugin"
}

Files

What ships with it

1 file beside marketplace.json#cas 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.

marketplace.json 583 B

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.

yesterday First seen · 6 lines scan A ba23679c3f13

Subscribe to this mod's changes

cas is a plugin published in the GitHub repository Kasempiternal/Claude-Agent-System (15 stars, last pushed 1mo ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-09-03.

Building agents Commits Git and workflow ai-agents automation claude claude-code claude-code-plugin

manifest-dev-tools

Tools for prompts and PRs alongside the manifest workflow. Includes collaborative PR walkthroughs, autonomous PR review with independent per-gate manifest verification, author-side PR babysitting that forwards /do verification policy, gap-calibrated prompt engineering, cross-boundary context handoff, incremental…

doodledood/manifest-dev · not measured

privacy-guard

Keeps private infrastructure details out of public repositories. Ships the privacy-guard skill: session rules for what must never cross the public boundary, plus a per-repo pre-commit gate built on a gitignored local denylist and gitleaks. The denylist is never committed, so the hook is a no-op for external…

fvadicamo/dev-agent-skills · not measured

github-workflow

Git commit, PR creation, review, and merge skills following Conventional Commits.

fvadicamo/dev-agent-skills · not measured

odin

ODIN - advanced code agent with diagram-first engineering and atomic commit workflows for surgical precision in software development.

OutlineDriven/odin-claude-plugin · not measured

gates

Four stateless PreToolUse gates, a PostToolUse JSON-config guard, and a docs-consolidation trigger. Denies a git commit that changes code without staging its covering docs (per-plugin README/CLAUDE.md pairs, or the nearest README/CLAUDE/AGENTS walking up); asks before a new-project scaffold command (npm create vite…

jasonm4130/claude-skills · not measured

coding

Opinionated Claude Code workflow skills: clear and unambiguous technical writing (write-clearly), iterative planning (replan), proof-based code review (review, review-staged, second-opinion), disciplined Conventional-Commit staging (gitplan, stage), and the Technical Project Plan workflow (tpp, handoff…

photostructure/coding-skills · not measured