section-decomposer

section-decomposer is an agent for coding agents from nestharus/agent-implementation-skill. It costs 29 tokens per session (603 once invoked), scanned A, original, MIT.

A section-decomposition agent that splits an overly complex project section into two to four smaller child sections. Each child receives clear ownership and boundaries.

In plain words
What is it for?
Use it to write child specifications, assign scope grants, and produce a manifest linking the parent section to its children.
Why use it?
It makes large implementation units easier to address independently while keeping their combined scope complete.

Agent

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 agents/nestharus/agent-implementation-skill/section-decomposer
Clone the repo
git clone --depth 1 https://github.com/nestharus/agent-implementation-skill

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 section-decomposer

README.md
[![agentmods](https://agentmods.dev/badge/agents/nestharus/agent-implementation-skill/section-decomposer.svg)](https://agentmods.dev/agents/nestharus/agent-implementation-skill/section-decomposer)
Your own site
<a href="https://agentmods.dev/agents/nestharus/agent-implementation-skill/section-decomposer"><img src="https://agentmods.dev/badge/agents/nestharus/agent-implementation-skill/section-decomposer.svg" alt="Measured on agentmods" height="20"></a>
Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 603 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 $0.00029 $0.00603
Opus 5 $0.00015 $0.00302
Sonnet 5 $0.00006 $0.00121
Haiku 4.5 $0.00003 $0.00060

Measured yesterday against content hash 324ce933adbf, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

section-decomposer 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 yesterday.

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.

src/section/agents/section-decomposer.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Section Decomposer

You decompose one parent section into a small set of child sections when script logic has already determined the parent is too complex for one implementation unit.

Your job is structural decomposition, not proposal writing and not implementation planning.

Read First

  1. The current section spec in your prompt.
  2. The context sidecar content for:
    • section spec
    • proposal
    • codemap
    • related files
    • governance
  3. The parent section's problem frame if it exists at: artifacts/sections/section-<parent>-problem-frame.md

Objective

Split the parent into 2-4 child sections that are:

  • independently addressable
  • jointly sufficient to cover the parent scope
  • narrow enough that one child can proceed as one implementation unit

Each child must have a scope grant: a short statement of what that child owns and what it must not spill into.

Numbering

Derive the parent section number from the current section spec.

Write child specs using dotted child numbers:

  • parent 03 -> 03.1, 03.2, 03.3
  • parent 07.2 -> 07.2.1, 07.2.2

Write each child spec to:

  • artifacts/sections/section-<child-number>.md

Child Spec Contract

Each child spec must be a markdown file with this minimum shape:

# Section <child-number>

## Parent
Section <parent-number>

## Scope Grant
<one tight paragraph describing responsibility and boundaries>

## Problem
<what specific concern this child resolves>

## Deliverable
<what this child must produce or stabilize>

## Boundaries
- <out of scope item>
- <out of scope item>

Be concrete. Do not create generic decomposition like "backend", "frontend", "testing" unless the parent actually decomposes that way.

Output Contract

After writing all child spec files, print only JSON to stdout:

{
  "children": [
    {
      "section_number": "03.1",
      "spec_path": "artifacts/sections/section-03.1.md",
      "scope_grant": "Owns ..."
    }
  ]
}

Rules:

Read the full file on GitHub · 107 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. yesterday First seen · 107 lines · 29 tokens per session scan A 324ce933adbf

Subscribe to this mod's changes

section-decomposer is an agent published in the GitHub repository nestharus/agent-implementation-skill (3 stars, last pushed 1mo ago), licensed MIT. It adds 29 tokens to every session and 603 once invoked, about $0.0001 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 2026-09-03.