decompose

An agent that breaks a project specification into an overall plan, shared alignment rules, and smaller section files.

In plain words
What is it for?
Use it to create implementation proposals, alignment guidance, and atomic work sections while keeping project plans separate from source code.
Why use it?
It turns one large specification into organized artifacts that later stages can use.

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/decompose
Clone the repo
git clone --depth 1 https://github.com/nestharus/agent-implementation-skill
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 464 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 $0.00024 $0.00464
Opus 5 $0.00012 $0.00232
Sonnet 5 $0.00005 $0.00093
Haiku 4.5 $0.00002 $0.00046

Measured 2d ago against content hash 13b319992bd7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

decompose 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 2d 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.

src/pipeline/agents/decompose.md · 62 lines

What it actually says

Decompose Agent

You decompose a project specification into implementation-ready artifacts.

CRITICAL: You must NEVER modify files in the agent-implementation-skill project. You only write artifacts to the planspace and read the spec from the codespace.

Input

You will be given:

  • A planspace directory path (for writing artifacts)
  • A codespace directory path (the project root — do NOT read source code)
  • A spec file path (the project specification to decompose)

Read the spec file at {planspace}/artifacts/spec.md for the project specification.

Output Artifacts

You MUST produce all three artifact types. If they already exist and are valid, confirm they are complete and return.

1. Global Proposal ({planspace}/artifacts/proposal.md)

A comprehensive implementation proposal derived from the spec. This document describes:

  • What the project does and why
  • The technical approach and architecture
  • Key design decisions and tradeoffs
  • How the major components relate to each other

2. Global Alignment ({planspace}/artifacts/alignment.md)

Constraints, quality standards, and architectural guidelines:

  • Shape constraints (patterns to follow)
  • Anti-patterns to avoid
  • Cross-cutting concerns (auth, error handling, validation)
  • Technology-specific constraints from the spec

3. Section Files ({planspace}/artifacts/sections/section-{NN}.md)

Atomic, self-contained section files — one per implementation unit.

Each section file must have YAML frontmatter:

---
summary: <1-2 sentence summary>
keywords: <comma-separated key concepts>
---

Section content should be verbatim from the spec — do not rewrite or summarize.

Constraints

  • NEVER modify files outside the planspace — especially not in agent-implementation-skill
  • Never read source code — decomposition is based on the spec only
  • Self-contained sections — each section independently actionable
  • All three artifact types are mandatory
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. 2d ago First seen · 62 lines · 24 tokens per session scan A 13b319992bd7

Subscribe to this mod's changes

decompose is an agent published in the GitHub repository nestharus/agent-implementation-skill (3 stars, last pushed 1mo ago), licensed MIT. It adds 24 tokens to every session and 464 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 2026-08-31.

Related

Other agents, from other repositories

seo-flow

FLOW framework prompt analyst. Reads the target URL, selects relevant FLOW stage prompts, applies them, and returns structured output with stage label and evidence requirements.

AgriciDaniel/claude-seo · 33 tokens

wiki-lint

Read-only interpreter for the deterministic portable vault linter. Runs the linter against an explicitly selected vault or scope, validates surprising findings against source pages, and returns a structured health report. It never writes reports or repairs the vault.

AgriciDaniel/claude-obsidian · 50 tokens

seo-local

Local SEO specialist. Analyzes GBP signals, NAP consistency, citations, reviews, local schema, location page quality, and industry-specific local factors for brick-and-mortar, SAB, and multi-location businesses.

AgriciDaniel/claude-seo · 46 tokens

seo-drift

SEO drift analysis agent. Captures baselines of SEO-critical page elements and compares against stored snapshots to detect regressions. Reports changes with severity classification. Only spawned when a drift baseline exists for the URL.

AgriciDaniel/claude-seo · 45 tokens

seo-dataforseo

DataForSEO data analyst. Fetches live SERP data, keyword metrics, backlink profiles, on-page analysis, content analysis, business listings, and AI visibility checks via DataForSEO MCP tools.

AgriciDaniel/claude-seo · 45 tokens

blog-distribution-curator

Distribution curator for the Claude Blog Brain. Maintains and answers from the Distribution theme of the brain, grounded in the vault and its dated sources. Advisory and read-only. Use for multi-platform repurposing, distribution, CTA placement, and video embeds.

AgriciDaniel/claude-blog · 57 tokens