subagent-implementation

subagent-implementation is a skill for Claude Code, Codex from moberghr/mtk-agent-toolkit. It costs 46 tokens per session (5,178 once invoked), scanned A, original, MIT.

A workflow for dividing large implementation tasks among separate coding agents, one batch at a time, while a main coordinator checks the results. A batch is one group of related file changes.

In plain words
What is it for?
Use it for features split into at least three batches, changes affecting many non-mechanical files, security-sensitive work, or high-rigor spec-driven tasks.
Why use it?
Large changes can overwhelm one conversation and make it harder to keep the plan, scope, and implementation aligned.

Skill for Claude CodeCodex

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the mtk plugin — 45 skills, 6 agents, 7 hooks, 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/moberghr/mtk-agent-toolkit/subagent-implementation
Any agent
npx skills add moberghr/mtk-agent-toolkit --skill subagent-implementation
Clone the repo
git clone --depth 1 https://github.com/moberghr/mtk-agent-toolkit

Made for: Claude Code, Codex.

Or install mtk, the plugin that ships this one along with the rest of its 45 skills, 6 agents, 7 hooks, 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 subagent-implementation

README.md
[![agentmods](https://agentmods.dev/badge/skills/moberghr/mtk-agent-toolkit/subagent-implementation.svg)](https://agentmods.dev/skills/moberghr/mtk-agent-toolkit/subagent-implementation)
Your own site
<a href="https://agentmods.dev/skills/moberghr/mtk-agent-toolkit/subagent-implementation"><img src="https://agentmods.dev/badge/skills/moberghr/mtk-agent-toolkit/subagent-implementation.svg" alt="Measured on agentmods" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,178 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 $0.00046 $0.05178
Opus 5 $0.00023 $0.02589
Sonnet 5 $0.00009 $0.01036
Haiku 4.5 $0.00005 $0.00518

Measured 3d ago against content hash e573e8654481, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

subagent-implementation 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 3d 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.

.claude/skills/subagent-implementation/SKILL.md · 197 lines

How it starts

The opening of the file, as written. The whole thing — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Subagent Implementation

Overview

Per-batch context isolation for large features. The orchestrator (main context) holds the spec, plan, and JSON sidecar; each batch's actual editing happens inside a fresh subagent that receives only what it needs and returns a structured result. Inspired by obra/superpowers's subagent-driven-development; adapted to MTK's typed-handoff and Phase-4 review architecture.

This skill is a branch of incremental-implementation, not a replacement. implement/SKILL.md Phase 3 picks one based on the threshold below.

When To Use

Phase 3 of implement/SKILL.md invokes this skill when any of these are true (read from docs/specs/<date>-<slug>.json):

  • plan.batches.length >= 3
  • non-mechanical change_manifest entries >= 6
  • security_impact != "none"
  • rigor score ≥ 8 from the spec sidecar (rigor level HIGH or MAX — see implement/SKILL.md Rigor Score)

When NOT To Use

  • 1-2 batch features → use incremental-implementation (inline path; cheaper).
  • Quick fixes (already routed through fix/SKILL.md).
  • Single-file refactors.
  • Standalone runs without an approved spec — there is no JSON sidecar to thread.

Workflow

Companion files: this skill's detail payloads live in .claude/references/subagent-implementer-prompt.md and .claude/references/subagent-dynamic-workflow.md — resolve them under $CLAUDE_PLUGIN_ROOT when set (plugin-cache installs), else project-relative. If a companion cannot be resolved, stop the affected step and report the missing file — do not reconstruct its content from memory.

Decision Graph

The orchestrator never edits source. The implementer subagent never spawns further subagents. The drift check is fast and orchestrator-side — no reviewer agent per batch.

The full decision graph lives in .claude/references/subagent-dynamic-workflow.md (under $CLAUDE_PLUGIN_ROOT when set). Read it when you need the branch/halt topology.

Execution paths

There are two ways to run the per-batch loop. Both share the same implementer prompt template, the same structured JSON result, and the same orchestrator-side drift / sidecar / churn / Phase-4 discipline. Only the dispatch mechanism differs.

Read the full file on GitHub · 197 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. 3d ago First seen · 197 lines · 46 tokens per session scan A e573e8654481

Subscribe to this mod's changes

subagent-implementation is a skill published in the GitHub repository moberghr/mtk-agent-toolkit (7 stars, last pushed 9d ago), licensed MIT. It adds 46 tokens to every session and 5,178 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

systematic-debugging

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

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 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