submcp

submcp is a skill for Claude Code, Codex from Animuni-Express/SubMCP. It costs 65 tokens per session (787 once invoked), scanned C, original, MIT.

A delegation tool that sends bounded, read-only tasks to separate AI agents running through NVIDIA NIM, a service for running AI models. The agents read files and return written reports.

In plain words
What is it for?
Use it to inspect, trace, summarize, or review many files, or to prepare a plan from repository contents.
Why use it?
It keeps large or repetitive file reading out of the main agent's working context. It also helps split independent investigation tasks without allowing those agents to edit files.

Skill for Claude CodeCodex

Part of the submcp plugin — 1 skill, 1 MCP server shipped together

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/animuni-express/submcp/submcp
Any agent
npx skills add Animuni-Express/SubMCP --skill submcp
Clone the repo
git clone --depth 1 https://github.com/Animuni-Express/SubMCP

Made for: Claude Code, Codex.

Or install submcp, the plugin that ships this one along with the rest of its 1 skill, 1 MCP server.

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 submcp

README.md
[![agentmods](https://agentmods.dev/badge/skills/animuni-express/submcp/submcp.svg)](https://agentmods.dev/skills/animuni-express/submcp/submcp)
Your own site
<a href="https://agentmods.dev/skills/animuni-express/submcp/submcp"><img src="https://agentmods.dev/badge/skills/animuni-express/submcp/submcp.svg" alt="Measured on agentmods" height="20"></a>
Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 787 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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 $0.00065 $0.00787
Opus 5 $0.00032 $0.00394
Sonnet 5 $0.00013 $0.00157
Haiku 4.5 $0.00006 $0.00079

Measured 4d ago against content hash 38d1ba6e082a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

submcp scanned grade C with 1 finding 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.

Reaches for credential fileshighPrivilege escalation

SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.

whitelisted templates), `.pem`, `.key`, `.pfx`, `id_rsa`, `credentials`, `.netrc`,
skills/submcp/SKILL.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SubMCP

Delegates bounded subtasks to NIM-hosted sub-agents that read the repo themselves and return a written report. Use it to keep large or mechanical exploration out of your context, not to replace normal edits.

Before first use

Call mcp__submcp__list_agents once per session. It's free (no API call) and tells you:

  • sandbox root (sub-agents can't read outside it)
  • whether write and shell are open (usually both closed → read-only sub-agents)
  • default model, step/timeout budgets

Tools

  • delegate — one sub-agent, one task. Required: task (self-contained instructions
    • desired output format). Optional: profile, files (paths to hand over up front), write (no-op unless server has SUBMCP_ALLOW_WRITE=1), model, max_steps.
  • delegate_parallel — N independent sub-agents at once (capped at SUBMCP_MAX_PARALLEL, default 4). Takes tasks: [str, ...], same profile/files/model applied to all. Always read-only — no write param. Use for "check these 3 files for the same thing" style work, not for chained/sequential steps (task 2 can't see task 1's result).

Profiles: general (default), researcher (read-only, cites what it read), coder (smallest change, matches existing style), reviewer (finds problems, doesn't rewrite).

Writing the task string

Sub-agents start cold — no view of this conversation. Every task must be self-contained: what to look at, what to produce, what "done" means.

  • Good: "Find every call site of load_config under submcp/ and list each as path:line with one line on how the result is used; answer as a markdown list."
  • Bad: "look into that config thing we discussed"

Pass files for anything you already know is relevant — saves the sub-agent a step.

Guardrails (already enforced, don't re-implement)

  • Path confinement to sandbox root (symlinks/.. resolved and checked).
  • Secret files refused for read and write: .env (except .env.example-style whitelisted templates), .pem, .key, .pfx, id_rsa, credentials, .netrc, .npmrc, .pypirc, etc.
  • write=True and shell access are both no-ops unless the operator explicitly opened those gates server-side.

Read the full file on GitHub · 69 lines

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 · 69 lines · 65 tokens per session scan C 38d1ba6e082a

Subscribe to this mod's changes

submcp is a skill published in the GitHub repository Animuni-Express/SubMCP (0 stars, last pushed 1mo ago), licensed MIT. It adds 65 tokens to every session and 787 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 1 finding (reaches for credential files). 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens