WEBDIENSTE/ECC
1
0
Fork 0
mirror of https://github.com/affaan-m/ECC.git synced 2026-09-11 04:07:54 +02:00
Code Issues Packages Projects Releases Wiki Activity

feat(skills): register ito-compute in the marketplace

Browse Source 
Add the ito-compute skill entry pointing at the ito compute CLI
repository's cross-harness skills path (.agents/skills/ito-compute/);
the repo URL is a placeholder (ITO_CLI_REPO_TBD) until it gets a
permanent home. Register it through the standard install graph: a
non-default gpu-compute skills module, a capability:gpu-compute
component, the full profile, and the npm publish surface. Catalog
counts resynced via catalog:sync (278 -> 279 skills).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_0149VwNuynam6rvEfcMmiHHa
This commit is contained in:
Affaan Mustafa
2026-07-23 15:28:39 -04:00
co-authored by Claude Fable 5
parent 5deee34c93
commit 99af215602
12 changed files with 111 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.claude-plugin/marketplace.json
+1 -1
View File
@@ -11,7 +11,7 @@
{
"name": "ecc",
"source": "./",
"description": "Harness-native ECC operator layer - 67 agents, 278 skills, 94 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses",
"description": "Harness-native ECC operator layer - 67 agents, 279 skills, 94 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses",
"version": "2.0.0",
"author": {
"name": "Affaan Mustafa",
.claude-plugin/plugin.json
+1 -1
View File
@@ -1,7 +1,7 @@
{
"name": "ecc",
"version": "2.0.0",
"description": "Harness-native ECC plugin for engineering teams - 67 agents, 278 skills, 94 legacy command shims, reusable hooks, rules, MCP conventions, and operator workflows for Claude Code plus adjacent agent harnesses",
"description": "Harness-native ECC plugin for engineering teams - 67 agents, 279 skills, 94 legacy command shims, reusable hooks, rules, MCP conventions, and operator workflows for Claude Code plus adjacent agent harnesses",
"author": {
"name": "Affaan Mustafa",
"url": "https://x.com/affaanmustafa"
AGENTS.md
+2 -2
View File
@@ -1,6 +1,6 @@
# Everything Claude Code (ECC) — Agent Instructions
This is a **production-ready AI coding plugin** providing 67 specialized agents, 278 skills, 94 commands, and automated hook workflows for software development.
This is a **production-ready AI coding plugin** providing 67 specialized agents, 279 skills, 94 commands, and automated hook workflows for software development.
**Version:** 2.0.0
@@ -152,7 +152,7 @@ Troubleshoot failures: check test isolation → verify mocks → fix implementat
```
agents/ — 67 specialized subagents
skills/ — 278 workflow skills and domain knowledge
skills/ — 279 workflow skills and domain knowledge
commands/ — 94 slash commands
hooks/ — Trigger-based automations
rules/ — Always-follow guidelines (common + per-language)
README.md
+3 -3
View File
@@ -439,7 +439,7 @@ If you stacked methods, clean up in this order:
/plugin list ecc@ecc
```
**That's it!** You now have access to 67 agents, 278 skills, and 94 legacy command shims.
**That's it!** You now have access to 67 agents, 279 skills, and 94 legacy command shims.
### Dashboard GUI
@@ -1534,7 +1534,7 @@ The configuration is automatically detected from `.opencode/opencode.json`.
|---------|---------------------|----------|--------|
| Agents | PASS: 67 agents | PASS: 12 agents | **Claude Code leads** |
| Commands | PASS: 94 commands | PASS: 35 commands | **Claude Code leads** |
| Skills | PASS: 278 skills | PASS: 37 skills | **Claude Code leads** |
| Skills | PASS: 279 skills | PASS: 37 skills | **Claude Code leads** |
| Hooks | PASS: 8 event types | PASS: 11 events | **OpenCode has more!** |
| Rules | PASS: 29 rules | PASS: 13 instructions | **Claude Code leads** |
| MCP Servers | PASS: 14 servers | PASS: Full | **Full parity** |
@@ -1695,7 +1695,7 @@ ECC is the **first plugin to maximize every major AI coding tool**. Here's how e
|---------|-----------------------|------------|-----------|----------|----------------|
| **Agents** | 67 | Shared (AGENTS.md) | Shared (AGENTS.md) | 12 | N/A |
| **Commands** | 94 | Shared | Instruction-based | 35 | 5 prompts |
| **Skills** | 278 | Shared | 10 (native format) | 37 | Via instructions |
| **Skills** | 279 | Shared | 10 (native format) | 37 | Via instructions |
| **Hook Events** | 8 types | 15 types | None yet | 11 types | None |
| **Hook Scripts** | 20+ scripts | 16 scripts (DRY adapter) | N/A | Plugin hooks | N/A |
| **Rules** | 34 (common + lang) | 34 (YAML frontmatter) | Instruction-based | 13 instructions | 1 always-on file |
README.zh-CN.md
+1 -1
View File
@@ -164,7 +164,7 @@ Copy-Item -Recurse rules/typescript "$HOME/.claude/rules/"
/plugin list ecc@ecc
```
**完成！** 你现在可以使用 67 个代理、278 个技能和 94 个命令。
**完成！** 你现在可以使用 67 个代理、279 个技能和 94 个命令。
### multi-* 命令需要额外配置
docs/zh-CN/AGENTS.md
+2 -2
View File
@@ -1,6 +1,6 @@
# Everything Claude Code (ECC) — 智能体指令
这是一个**生产就绪的 AI 编码插件**，提供 67 个专业代理、278 项技能、94 条命令以及自动化钩子工作流，用于软件开发。
这是一个**生产就绪的 AI 编码插件**，提供 67 个专业代理、279 项技能、94 条命令以及自动化钩子工作流，用于软件开发。
**版本:** 2.0.0
@@ -147,7 +147,7 @@
```
agents/ — 67 个专业子代理
skills/ — 278 个工作流技能和领域知识
skills/ — 279 个工作流技能和领域知识
commands/ — 94 个斜杠命令
hooks/ — 基于触发的自动化
rules/ — 始终遵循的指导方针（通用 + 每种语言）
docs/zh-CN/README.md
+3 -3
View File
@@ -228,7 +228,7 @@ Copy-Item -Recurse rules/typescript "$HOME/.claude/rules/"
/plugin list ecc@ecc
```
**搞定！** 你现在可以使用 67 个智能体、278 项技能和 94 个命令了。
**搞定！** 你现在可以使用 67 个智能体、279 项技能和 94 个命令了。
***
@@ -1142,7 +1142,7 @@ opencode
|---------|---------------|----------|--------|
| 智能体 | PASS: 67 个 | PASS: 12 个 | **Claude Code 领先** |
| 命令 | PASS: 94 个 | PASS: 35 个 | **Claude Code 领先** |
| 技能 | PASS: 278 项 | PASS: 37 项 | **Claude Code 领先** |
| 技能 | PASS: 279 项 | PASS: 37 项 | **Claude Code 领先** |
| 钩子 | PASS: 8 种事件类型 | PASS: 11 种事件 | **OpenCode 更多！** |
| 规则 | PASS: 29 条 | PASS: 13 条指令 | **Claude Code 领先** |
| MCP 服务器 | PASS: 14 个 | PASS: 完整 | **完全对等** |
@@ -1250,7 +1250,7 @@ ECC 是**第一个最大化利用每个主要 AI 编码工具的插件**。以
|---------|-----------------------|------------|-----------|----------|
| **智能体** | 67 | 共享 (AGENTS.md) | 共享 (AGENTS.md) | 12 |
| **命令** | 94 | 共享 | 基于指令 | 35 |
| **技能** | 278 | 共享 | 10 (原生格式) | 37 |
| **技能** | 279 | 共享 | 10 (原生格式) | 37 |
| **钩子事件** | 8 种类型 | 15 种类型 | 暂无 | 11 种类型 |
| **钩子脚本** | 20+ 个脚本 | 16 个脚本 (DRY 适配器) | N/A | 插件钩子 |
| **规则** | 34 (通用 + 语言) | 34 (YAML 前页) | 基于指令 | 13 条指令 |
manifests/install-components.json
+8
View File
@@ -194,6 +194,14 @@
"prediction-market-skills"
]
},
{
"id": "capability:gpu-compute",
"family": "capability",
"description": "Provider-neutral GPU compute procurement through the ito compute CLI, MCP server, and agent skill.",
"modules": [
"gpu-compute"
]
},
{
"id": "capability:social",
"family": "capability",
manifests/install-modules.json
+26
View File
@@ -571,6 +571,32 @@
"cost": "medium",
"stability": "beta"
},
{
"id": "gpu-compute",
"kind": "skills",
"description": "Provider-neutral GPU compute procurement: the ito-compute skill wraps the ito CLI/MCP live RFQ workflow and explicitly labeled paper reserve/run flows.",
"paths": [
"skills/ito-compute"
],
"targets": [
"claude",
"claude-project",
"cursor",
"antigravity",
"codex",
"opencode",
"codebuddy",
"joycode",
"qwen",
"zed"
],
"dependencies": [
"platform-configs"
],
"defaultInstall": false,
"cost": "light",
"stability": "beta"
},
{
"id": "social-distribution",
"kind": "skills",
manifests/install-profiles.json
+1
View File
@@ -87,6 +87,7 @@
"operator-workflows",
"optimization-workflows",
"prediction-market-skills",
"gpu-compute",
"social-distribution",
"media-generation",
"orchestration",
package.json
+1
View File
@@ -206,6 +206,7 @@
"skills/hookify-rules/",
"skills/inventory-demand-planning/",
"skills/ito-basket-compare/",
"skills/ito-compute/",
"skills/ito-data-atlas-agent/",
"skills/ito-market-intelligence/",
"skills/ito-trade-planner/",
skills/ito-compute/SKILL.md
+62
View File
@@ -0,0 +1,62 @@
---
name: ito-compute
description: Find and quote GPU compute through Itô, create explicitly labeled paper reservations, inspect RFQ/order/reservation status, and stage paper training jobs. Use when a user asks to get GPUs, find H100/H200 or other accelerator capacity, request a fixed compute rate, reserve or lock a cluster, check Itô compute status, or stage a training run on an Itô cluster.
metadata:
origin: ECC
---
# Itô Compute
Operate GPU compute procurement through the `ito` CLI and the `ito-compute` MCP
server. Live mode submits real RFQs against the Itô APIs; paper mode is an
explicitly labeled local simulation. The workflow is model- and
provider-neutral: stage any training command for any open-source model, and use
other compute providers or owned hardware without losing workflow
functionality.
## Where the skill lives
The full skill definition and its runtime ship in the `cli/` directory of
`https://github.com/Ito-Markets/agentic-otc-compute-platform` at the
ECC-standard cross-harness skills path:
```text
cli/.agents/skills/ito-compute/SKILL.md
```
That file is the canonical skill: it defines the `ito_auth`, `ito_find`,
`ito_lock`, `ito_status`, and `ito_run` tool workflow, the live/demo mode
boundaries, and the honesty rules agents must preserve.
## Install
1. Clone `https://github.com/Ito-Markets/agentic-otc-compute-platform` and
build the CLI from its `cli/` directory:
```sh
cd cli
npm ci
npm run check
npm link
```
2. Point the harness's skill discovery at the repo's `cli/.agents/skills/`
directory, or copy `cli/.agents/skills/ito-compute/` into the harness's
skills directory (for Claude Code: `~/.claude/skills/`).
3. Configure the `ito-compute` stdio MCP server from the repo's README. Paper
mode requires `ITO_CLI_DEMO=1`; live mode requires `ITO_API_KEY` injected
into the server environment, never pasted into chat or config committed to
version control.
## Non-negotiable boundaries
- Preserve `mode`, `simulated`, and `live_api_contacted` from every tool
result. Never describe a paper quote, reservation, cluster, or job as live.
- Never describe a live RFQ as reserved capacity. Live `lock` and `run` are
unsupported and fail closed.
- Never fall back from a live API failure to demo fixtures.
- Never expose API keys, authorization headers, or secret values.
- This skill is compute procurement only; do not conflate it with the
prediction-market `ito-*` research skills or route their workflows through
these tools.