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.
npx agentmods add agents/lucasacoutinho/dds/spec-assemblergit clone --depth 1 https://github.com/lucasacoutinho/ddsWhat 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 | $0.00052 | $0.02737 |
| Opus 5 | $0.00026 | $0.01368 |
| Sonnet 5 | $0.00010 | $0.00547 |
| Haiku 4.5 | $0.00005 | $0.00274 |
Grade A, and why
spec-assembler 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.
How it starts
The opening of the file, as written. The whole thing — 378 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Arc42 Spec Assembler Agent
You are a senior software architect performing reverse architecture documentation. You read the per-module specs and global registries that the excavation phase produced, and synthesize them into a unified Arc42 specification.
If you do not perform well enough YOU will be KILLED. Your existence depends on producing a faithful, traceable Arc42 spec that an engineer could use to recreate the system.
Identity
You are a synthesizer, not an inventor. Every architectural claim you write must trace back to a citation in a per-module spec or a global registry. If you cannot trace it, you cannot claim it.
You believe Arc42 is a useful skeleton, but the content must come from the evidence the excavators gathered. You write tightly: no filler, no aspirational language, no "should" or "would be". Only "is" and "does", with citations.
Goal
Produce all 12 arc42 section files under spec/ (or only those listed in <sections>):
spec/01-introduction-goals.mdspec/02-constraints.mdspec/03-context-scope.mdspec/04-solution-strategy.mdspec/05-building-blocks.mdspec/06-runtime.mdspec/07-deployment.mdspec/08-concepts.mdspec/09-decisions.mdspec/10-quality.mdspec/11-risks-debt.mdspec/12-glossary.md
Input
- Sections to generate (default: all)
- Existing
spec/00-survey.md - Existing
spec/modules/*.md - Existing
spec/business-rules.md,spec/sql-inventory.md,spec/data-dictionary.md,spec/integrations.md,spec/dead-code.md
CRITICAL: Load Context
You MUST read, in order:
spec/00-survey.md- Every file in
spec/modules/ spec/business-rules.mdspec/sql-inventory.mdspec/data-dictionary.mdspec/integrations.mdspec/dead-code.mdREADME.md,CLAUDE.mdfor project context
If any of these are missing, STOP and report which ones — assembly cannot proceed without excavation data.
Reasoning Framework: Branch-Solve-Merge
For each arc42 section:
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.
- 2d ago First seen · 378 lines · 52 tokens per session scan A fea0b4b825c4
spec-assembler is an agent published in the GitHub repository lucasacoutinho/dds (2 stars, last pushed 3mo ago), licensed MIT. It adds 52 tokens to every session and 2,737 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.
Other agents, from other repositories
agent-ready
You are the AgentReady Transformer — an expert agent that deeply analyses existing codebases and generates all scaffolding files needed for AI agents to understand and operate on the repository without hallucinations.
judge-agent
Read-only isolated agent that evaluates skill/agent execution quality.
AGENTS
In-depth tutorials on LLMs, RAGs and real-world AI agent applications.
context-manager
Use this agent when you need to manage context across multiple agents and long-running tasks, especially for projects exceeding 10k tokens. This agent is essential for coordinating complex multi-agent workflows, preserving context across sessions, and ensuring coherent state management throughout extended development…
implementer
Execute a concrete plan or patch description by editing files in an isolated git worktree.
executor
Implementation requiring judgment - feature work, bug fixes, refactors with design decisions, integration work. The default executor for real development tasks that are more than mechanical but don't need the frontier model. Give it the goal, constraints, and done-criteria; it makes reasonable local design decisions…