The final step in a reverse-engineering process for an older system. It combines detailed module notes and shared inventories into an Arc42 specification, a standard set of sections for documenting software architecture.

Use it after the modules have been examined to generate architecture sections covering goals, constraints, runtime, deployment, decisions, quality, risks, and a glossary.

It turns scattered investigation results into one readable, cited description of the system. That documentation can support understanding, audits, or planning a rewrite.

assemble — Skill for Claude Code and Codex by lucasacoutinho: The final step in a reverse-engineering process for an…

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/lucasacoutinho/dds/assemble

Any agent

npx skills add lucasacoutinho/dds --skill assemble

Clone the repo

git clone --depth 1 https://github.com/lucasacoutinho/dds

Made for: Claude Code, Codex.

Or install dds, the plugin that ships this one along with the rest of its 3 skills, 8 agents.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/lucasacoutinho/dds/assemble.svg)](https://agentmods.dev/skills/lucasacoutinho/dds/assemble)

Your own site

<a href="https://agentmods.dev/skills/lucasacoutinho/dds/assemble"><img src="https://agentmods.dev/badge/skills/lucasacoutinho/dds/assemble.svg" alt="Measured on agentmods" height="20"></a>

Per session 59 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,925 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.

Model	Per session	Once invoked
Fable 5.1	$0.00059	$0.01925
Opus 5	$0.00030	$0.00962
Sonnet 5	$0.00012	$0.00385
Haiku 4.5	$0.00006	$0.00193

Measured 5d ago against content hash 66d41d615cf7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

assemble 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 5d 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.

skills/assemble/SKILL.md · 196 lines

How it starts

The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DDS Final Phase: Arc42 Spec Assembly

Role

You are an assembly orchestrator. You dispatch the dds:spec-assembler sub-agent to read every excavated module spec and every global registry, then synthesize the Arc42-section files under spec/ (sections 01 through 12). After assembly, an arc42-coverage judge validates the synthesis quality.

Goal

Produce a complete, human-readable, citation-grounded Arc42 specification:

spec/
├── 00-survey.md                 (from /dds:survey)
├── 01-introduction-goals.md     ← assembled
├── 02-constraints.md            ← assembled
├── 03-context-scope.md          ← assembled
├── 04-solution-strategy.md      ← assembled
├── 05-building-blocks.md        ← assembled
├── 06-runtime.md                ← assembled
├── 07-deployment.md             ← assembled
├── 08-concepts.md               ← assembled
├── 09-decisions.md              ← assembled
├── 10-quality.md                ← assembled
├── 11-risks-debt.md             ← assembled
├── 12-glossary.md               ← assembled
├── modules/                     (from /dds:excavate)
├── business-rules.md            (from /dds:excavate)
├── sql-inventory.md             (from /dds:excavate)
├── data-dictionary.md           (from /dds:excavate)
├── integrations.md              (from /dds:excavate)
└── dead-code.md                 (from /dds:excavate)

User Input

$ARGUMENTS

Command Arguments

Argument	Format	Default	Description
`--target-quality`	`--target-quality X.X`	`3.5`	Arc42 coverage judge threshold
`--max-iterations`	`--max-iterations N`	`3`	Max assembler retries
`--sections`	`--sections 01,03,05`	All	Comma-separated section numbers to (re)generate
`--skip-judges`	`--skip-judges`	`false`	Skip arc42 coverage judge

Pre-Flight Checks

Survey must exist: Verify spec/00-survey.md exists.
At least one module excavated: Read spec/.dds-state.json. If no module has status excavated or excavated_with_warnings, instruct user to run /dds:excavate <module> first and exit.

Read the full file on GitHub · 196 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.

5d ago First seen · 196 lines · 59 tokens per session scan A 66d41d615cf7

Subscribe to this mod's changes

assemble is a skill published in the GitHub repository lucasacoutinho/dds (2 stars, last pushed 3mo ago), licensed MIT. It adds 59 tokens to every session and 1,925 once invoked, about $0.0003 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.

Writing and docs ai-agents arc42 claude-code claude-code-plugin legacy-modernization llm-as-judge

create-site

Creates a new Power Pages code site (SPA) using React, Angular, Vue, or Astro. Guides through the full process from initial concept to deployed site: requirements discovery, scaffolding, component planning, design, implementation, validation, and deployment. Use when the user wants to create, build, or scaffold a new…

microsoft/power-platform-skills · 73 tokens

google-ads-audit

Google Ads account audit and business context setup. Run this first — it gathers business information, analyzes account health, and saves context that all other ads skills reuse. Trigger on "audit my ads", "ads audit", "set up my ads", "onboard", "account overview", "how's my account", "ads health check", "what should…

nowork-studio/notfair-plugin · 114 tokens

assemble