gapt

gapt is a skill for Claude Code, Codex from CocoRoF/Geny. It costs 39 tokens per session (412 once invoked), scanned A, original, Apache-2.0.

A guide for using GAPT, a system of separate, persistent project and sandbox spaces. These spaces can hold code, run commands in isolated environments, build projects, and deploy them independently of the current chat workspace.

In plain words
What is it for?
Use it when a task needs an independent named project, an isolated build environment, persistent workspace state, command execution, or deployment.
Why use it?
It keeps longer-running or isolated work separate from the current session while preserving it for later use. It also describes the project, workspace, command, and deployment workflow.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/cocorof/geny/gapt
Any agent
npx skills add CocoRoF/Geny --skill gapt
Clone the repo
git clone --depth 1 https://github.com/CocoRoF/Geny

Made for: Claude Code, Codex.

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 gapt

README.md
[![agentmods](https://agentmods.dev/badge/skills/cocorof/geny/gapt.svg)](https://agentmods.dev/skills/cocorof/geny/gapt)
Your own site
<a href="https://agentmods.dev/skills/cocorof/geny/gapt"><img src="https://agentmods.dev/badge/skills/cocorof/geny/gapt.svg" alt="Measured on agentmods" 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 412 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00039 $0.00412
Opus 5 $0.00019 $0.00206
Sonnet 5 $0.00008 $0.00082
Haiku 4.5 $0.00004 $0.00041

Measured 4d ago against content hash 02994b3be8f6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

gapt 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 4d 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.

backend/skills/bundled/gapt/SKILL.md · 45 lines

What it actually says

GAPT — independent project & sandbox spaces

GAPT gives you isolated, persistent project spaces separate from this chat session: a place to create code that persists, run builds in an isolated container, or deploy — distinct from your own per-session workspace.

Pick your path

  • You have the gapt_* tools → do it yourself. Start with gapt_overview to see what exists, then create a project / workspace and work in it.
  • You do NOT have the gapt_* tools but have a gapt sub-worker → delegate the whole GAPT task to it with a clear, self-contained instruction, then relay its result.

Each project is fully isolated and persists across sessions.

Detailed tool reference

For the exact arguments, return values, and step-by-step recipes for each gapt_* tool (create/list/run/deploy, polling workspace status, the project→workspace→command→deploy flow), load the bundled reference on demand: call this skill again with resource="REFERENCE.md". Don't pull it unless you need the specifics — the summary above covers the common case.

Scope

Use this only for separate, named, persistent project spaces — not for ordinary file/shell work in your current session (that's your normal Read/Write/Bash / your own workspace).

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. 4d ago First seen · 45 lines · 39 tokens per session scan A 02994b3be8f6

Subscribe to this mod's changes

gapt is a skill published in the GitHub repository CocoRoF/Geny (10 stars, last pushed 5d ago), licensed Apache-2.0. It adds 39 tokens to every session and 412 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 2026-08-31.

Related

Other skills, from other repositories

agent_management

This Skill provides a complete management guide for OpenSquad Agents, covering the full workflow of creation, configuration, deployment, and troubleshooting.

opensquad-ai/opensquad · 0 tokens

Collaboration Management

Complete guide to multi-agent collaboration card management, including starting collaborations, joining teams, and creating custom collaboration cards.

opensquad-ai/opensquad · 25 tokens

collaboration-workflow

Complete guide to the OpenSquad multi-agent collaboration system with user authorization gates. Use this skill when starting a collaboration session, coordinating multiple agents, managing the collaboration board, or when you need to understand how to use boardupdate, boardlist, and other collaboration tools. Triggers…

opensquad-ai/opensquad · 89 tokens

mcp_auto_deploy

Allows the agent to self-configure and deploy MCP servers. Covers central config, per-agent sync, web UI visibility, registration diagnostics, and validation.

opensquad-ai/opensquad · 36 tokens

external-im-integration

Connect OpenSquad agents to external IM platforms (Feishu/Lark, QQ, Telegram). Covers plugin service setup, adapter processes, Gateway auth, workspace path fixes, and troubleshooting. Uses Feishu as the reference example.

opensquad-ai/opensquad · 50 tokens

opensquad_intro

When you need to understand how to use OpenSquad, its architectural design, or its features, load this skill to get a system overview and documentation navigation guide.

opensquad-ai/opensquad · 37 tokens