What is 03-architect?

A system-architecture skill that turns project requirements and design decisions into architecture documents, decision records, and feature specifications. Architecture documents describe the system's major parts and how they fit together.

Use it to establish the overall system shape, record architecture decisions, write per-feature specifications for a sprint, and detect missing details or contradictions in the architecture.

It makes important technical choices explicit and checks whether the proposed system violates stated constraints. Each feature specification includes a testable verification contract.

03-architect — Skill for Claude Code and Codex by IncommensurableHubri

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.

Any agent

npx skills add IncommensurableHubris/fullstack-director --skill 03-architect

Clone the repo

git clone --depth 1 https://github.com/IncommensurableHubris/fullstack-director

Made for: Claude Code, Codex.

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/incommensurablehubris/fullstack-director/03-architect.svg)](https://agentmods.dev/skills/incommensurablehubris/fullstack-director/03-architect)

Your own site

<a href="https://agentmods.dev/skills/incommensurablehubris/fullstack-director/03-architect"><img src="https://agentmods.dev/badge/skills/incommensurablehubris/fullstack-director/03-architect.svg" alt="Measured on agentmods" height="20"></a>

Per session 218 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,829 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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	$0.00218	$0.03829
Opus 5	$0.00109	$0.01914
Sonnet 5	$0.00044	$0.00766
Haiku 4.5	$0.00022	$0.00383

Measured 6d ago against content hash 10baad917447, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

03-architect 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 6d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (evals/check_architecture.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.agents/skills/03-architect/SKILL.md · 158 lines

How it starts

The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.

03 · Architect — realize (system)

Two modes. 03-architect init writes the durable system shape (system.md + the tech-stack ADR + the ADR index). 03-architect sprint N writes per-feature specs (with Verification Contracts) + any new ADRs for that sprint's REQs. Both reference REQs by ID and realize within the declared envelope (architecture-constraints.md). You are the second skill to run Reconcile — and the first to run its judgment pass in a context-isolated subagent (the architecture reconciler, shared/subagent-protocol.md).

Operating principle — realize, and reconcile (subagent-isolated)

Two moves, run together:

Realize. Turn architecture-constraints.md + the sprint's REQs (+ the 02 design contract) into a lean system shape, decisions (ADRs), and feature contracts. Reference REQs by ID; derive freely below the governed envelope. Fix only load-bearing invariants; mark starting values seed, un-needed ones deferred.
Reconcile. Challenge architecture-constraints.md two ways: contradiction-flag — the realization violates a stated constraint / Constitution mandate (a datastore that can't meet a stated REQ); flesh-out — a declaration-altitude decision the architecture forces is missing / derived. Both → Tier-2 gate, resolved by the tech-mandate flow (amend the constraint and record a resolving ADR — one trigger, two altitudes). Run it as a dual pass: Pass 1 deterministic inline, Pass 2 judgment in a fresh-context subagent. Full method: references/reconcile-architecture.md.

The boundary-test = the constraint line. Reconcile fires only on the governed layer (stated architecture- constraints: stack · hosting · region/residency · compliance · scale · "no X" · Constitution mandates); the delegated layer (the C4 shape · component decomposition · internal data shapes · library picks within the envelope) is free realization — no amendment, ever. A named-technology or scale change is minimum Tier 2.

Read the full file on GitHub · 158 lines

Files

What ships with it

56 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

6d ago First seen · 158 lines · 218 tokens per session scan A 10baad917447

Subscribe to this mod's changes

03-architect is a skill published in the GitHub repository IncommensurableHubris/fullstack-director (5 stars, last pushed 26d ago), licensed MIT. It adds 218 tokens to every session and 3,829 once invoked, about $0.0011 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.

Claude Code Planning Writing and docs agent-skills ai-agents sdlc spec-driven-development

gsd-plan-review-convergence

Cross-AI plan convergence - replan until review concerns are resolved.

open-gsd/gsd-core · 21 tokens

gsd-audit-milestone

Audit milestone completion against original intent before archiving.

open-gsd/gsd-core · 17 tokens

gsd-ns-manage

Route to the appropriate management skill based on the user's intent. gsd-config (settings + advanced + integrations + profile) and gsd-workspace (new + list + remove) are post-#2790 consolidated entries.

open-gsd/gsd-core · 16 tokens

spec-kitty-charter-doctrine

Run charter interview, generation, context, and sync workflows for project governance in Spec Kitty 3.x. Access doctrine artifacts programmatically via DoctrineService. Resolve agent profiles. Load action-scoped governance context iteratively, not all at once. Triggers: "interview for charter", "generate charter"…

Priivacy-ai/spec-kitty · 135 tokens

spec-kitty-spdd-reasons

Drive REASONS Canvas authoring and review for Spec Kitty missions that opted in to Structured-Prompt-Driven Development (SPDD) via charter selection. Triggers: "use SPDD", "use REASONS", "generate a REASONS canvas", "apply structured prompt driven development", "make this mission SPDD". Does NOT handle: enforcing SPDD…

Priivacy-ai/spec-kitty · 118 tokens

conductor-implement

Executes the tasks defined in the specified track's plan. Use this to start or continue working on a feature, bug fix, or chore.

gemini-cli-extensions/conductor · 34 tokens