agentmods.dev

gpt-architect

gpt-architect is a skill for Claude Code from Kasempiternal/Claude-Agent-System. It costs 70 tokens per session (2,872 once invoked), scanned A, original, MIT.

A delegation tool that sends focused coding or investigation tasks from Claude Code to a connected Codex agent.

In plain words
What is it for?
Use it for one-off or session-long delegation of non-trivial implementation and investigation tasks, after checking that the Codex connection is available.
Why use it?
It separates project direction and review from the hands-on repository work delegated to Codex.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: reads .claude/ paths; mentions subagents; names the NotebookEdit tool.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

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

not rated 15repo 1mo ago A scan 70 tokens original MIT

Good fit Use it for one-off or session-long delegation of non-trivial implementation and investigation tasks, after checking that the Codex connection is available.

Compare 6 skills from other repositories ↓
View source ↗ Kasempiternal/Claude-Agent-System kasempiternal.github.io
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add Kasempiternal/Claude-Agent-System
Claude Code
/plugin install cas

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 gpt-architect

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/kasempiternal/claude-agent-system/gpt-architect"><img src="https://agentmods.dev/badge/skills/kasempiternal/claude-agent-system/gpt-architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,872 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 $0.00070 $0.02872
Opus 5 $0.00035 $0.01436
Sonnet 5 $0.00014 $0.00574
Haiku 4.5 $0.00007 $0.00287

Measured 9d ago against content hash a2060588d1ca, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

gpt-architect 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/codex-preflight.cjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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-agent-system-plugin/skills/gpt-architect/SKILL.md · 127 lines

How it starts

The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GPT Architect

Use the connected normal codex MCP directly. Claude owns scope, architecture, review, and user communication; Codex performs the focused repository task.

Session mode

  • Every new session starts off. /gpt-architect on enables this routing for the current Claude session only; Claude then decides which non-trivial tasks benefit from delegation.
  • /gpt-architect off disables session routing immediately. A one-shot /gpt-architect <task> delegates only that request and does not alter session mode.
  • Session state lives only in the conversation transcript. Never create a global, project, path, or flag-file activation. The Claude status line derives GPT-A ON or GPT-A OFF from the latest explicit session command.

Preflight and setup

The normal codex MCP is a separate, user-configured backend — the plugin does not bundle it. Before enabling session mode, before a one-shot /gpt-architect <task>, and before any delegation on a session that has not yet delegated, confirm it is available. Run the cross-platform preflight (macOS, Linux, and Windows):

node "${CLAUDE_PLUGIN_ROOT}/skills/gpt-architect/scripts/codex-preflight.cjs" check

  • VERDICT: READY — the Codex CLI is installed, authenticated, and registered as an MCP. Proceed.

  • VERDICT: NEEDS_SETUP — the MISSING: line names what is absent (CLI, AUTH, and/or MCP). Run setup automatically, without a confirmation prompt:

    node "${CLAUDE_PLUGIN_ROOT}/skills/gpt-architect/scripts/codex-preflight.cjs" setup

    Setup installs the Codex CLI (Homebrew on macOS/Linux when present, otherwise npm install -g @openai/codex — the universal path that also covers Windows) and registers it at user scope with claude mcp add codex -s user -- codex mcp-server. This configures the codex MCP backend; it does not create any /gpt-architect activation state, which remains transcript-only.

Two constraints to state honestly, never gloss over:

  • A newly registered MCP loads only at session start. After setup, the codex tools are not live in the current session. Tell the user to restart Claude Code and re-run the preflight; no delegation can occur until then. You may still record session mode as ON so it is active after the restart.
  • Authentication (codex login) is interactive (browser or API key). Setup drives it only when run in a real terminal; when invoked from a tool call it cannot, so ask the user to run ! codex login. If setup cannot install (no Homebrew and no npm) or cannot register (no claude CLI on PATH), it prints exact manual commands — relay them and do not claim success.

Read the full file on GitHub · 127 lines

Files

What ships with it

1 file 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. 9d ago First seen · 127 lines · 70 tokens per session scan A a2060588d1ca

Subscribe to this mod's changes

gpt-architect is a skill published in the GitHub repository Kasempiternal/Claude-Agent-System (15 stars, last pushed 1mo ago), licensed MIT. It adds 70 tokens to every session and 2,872 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 2026-08-30.

Backend and APIsClaude CodeCode reviewResearchai-agentsautomationclaudeclaude-code-plugin
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

ash-framework

Ash Framework — resources, actions, policies, aggregates, calculations, AshPhoenix.Form, LiveView, migrations. Use when generating resources via mix ash.codegen, editing changes, checks, types, validations, or domain code interfaces.

oliver-kriska/claude-elixir-phoenix · 48 tokens

liveview-patterns

Build LiveView: async data (assignasync), PubSub (check connected?), phx-change events, form components/modals/uploads, streams for lists, livepatch. Use when handling interactions, debugging events, or tracking Presence.

oliver-kriska/claude-elixir-phoenix · 51 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

oban

Oban job processing — workers, perform/1 (OSS) and process/1 (Pro), queues, cron, retries, unique jobs, idempotency, Oban Pro (Workflow, Batch, Chunk, Smart Engine), Testing. Use when writing Oban workers, queue config, or debugging jobs.

oliver-kriska/claude-elixir-phoenix · 64 tokens

tidewave-integration

Tidewave MCP runtime tools — debugging, smoke testing, live state inspection, SQL queries, hex docs. Use when evaluating code in a running Phoenix app.

oliver-kriska/claude-elixir-phoenix · 38 tokens