Agent skill

Architect

Given a PRD, produces an implementation architecture: file tree, component breakdown, data model, and a phased build plan with end conditions that Archon can execute directly.

MITAuto-check passedProduct & Project Management

Install Architect

skills CLI

$ npx skills add SethGammon/Citadel --skill architect -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install SethGammon/Citadel architect --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/SethGammon/Citadel.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/architect .claude/skills/architect && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "architect" agent skill from https://github.com/SethGammon/Citadel/tree/main/skills/architect into .claude/skills/architect/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "architect", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/SethGammon/Citadel/tree/main/skills/architect

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add SethGammon/Citadel --skill architect -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install SethGammon/Citadel architect --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/SethGammon/Citadel.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/architect .agents/skills/architect && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "architect" agent skill from https://github.com/SethGammon/Citadel/tree/main/skills/architect into .agents/skills/architect/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "architect", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add SethGammon/Citadel --skill architect -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install SethGammon/Citadel architect --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/SethGammon/Citadel.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/architect .cursor/skills/architect && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "architect" agent skill from https://github.com/SethGammon/Citadel/tree/main/skills/architect into .cursor/skills/architect/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "architect", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/SethGammon/Citadel.git --path skills/architect

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add SethGammon/Citadel --skill architect -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install SethGammon/Citadel architect --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/SethGammon/Citadel.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/architect .gemini/skills/architect && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "architect" agent skill from https://github.com/SethGammon/Citadel/tree/main/skills/architect into .gemini/skills/architect/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "architect", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install SethGammon/Citadel architect

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add SethGammon/Citadel --skill architect -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/SethGammon/Citadel.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/architect .github/skills/architect && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "architect" agent skill from https://github.com/SethGammon/Citadel/tree/main/skills/architect into .github/skills/architect/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "architect", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add SethGammon/Citadel --skill architect -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install SethGammon/Citadel architect --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/SethGammon/Citadel.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/architect .opencode/skills/architect && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "architect" agent skill from https://github.com/SethGammon/Citadel/tree/main/skills/architect into .opencode/skills/architect/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "architect", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: architect
GitHub stars: 922
Token cost: ~1.6k tokens
SKILL.md length: 619 words
Files: 3
Skills in repo: 48
Repo updated: Oct 1, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Given a PRD, produces an implementation architecture: file tree, component breakdown, data model, and a phased build plan with end conditions that Archon can execute directly.

Works in 5 steps: READ → EVALUATE OPTIONS (for non-trivial… → PRODUCE → …
Tasks that involve PRD writing
SKILL.md covers When to Use, Inputs, Mode Detection and Protocol, plus 4 more sections
Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Architect is an agent skill from SethGammon/Citadel. Given a PRD, produces an implementation architecture: file tree, component breakdown, data model, and a phased build plan with end conditions that Archon can execute directly. Multi-candidate evaluation for key decisions.

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files (for example `__benchmarks__/no-prd.md` and `__benchmarks__/with-direction.md`).

It sits in Product & Project Management, covering PRD writing. The repository describes itself as: The operating layer for Claude Code + OpenAI Codex: persistent project memory, intent routing, safety hooks, cost telemetry, and parallel agent fleets. The licence is MIT.

When your agent uses it

Tasks that involve PRD writing

Example prompts

“/architect”

Workflow steps

5 steps, taken from the step headings in SKILL.md.

READ
EVALUATE OPTIONS (for non-trivial decisions)
PRODUCE
CONNECT TO CAMPAIGN
HANDOFF

What it can do on your machine

Read from SKILL.md and the folder at commit e41ff1d. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Architect loads about 1.6k tokens when it runs. Until then it costs about 58 tokens; SKILL.md has 619 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~58
When it runs · the whole SKILL.md, loaded when a task matches: ~1.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from SethGammon/Citadel at commit e41ff1d, republished under its MIT licence (© SethGammon). 619 words, ~1,641 tokens.

Download SKILL.mdSave it as .claude/skills/architect/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.

name: architect
description: Given a PRD, produces an implementation architecture: file tree, component breakdown, data model, and a phased build plan with end conditions that Archon can execute directly. Multi-candidate evaluation for key decisions.
license: MIT
user-invocable: true
auto-trigger: false
trigger_keywords: architect, architecture, design the system, file structure, plan the build
effort: high

/architect — Implementation Architecture from PRD

When to Use

Don't use when: you already have an architecture and want to implement it (use /marshal or /archon); you need a PRD first (use /prd before /architect).

After /prd produces an approved PRD (greenfield or feature mode)
When the user has a clear direction + existing codebase (no PRD needed)
When /do routes a build request
When the user has a spec and wants a build plan

Inputs

One of:

A PRD file path (from /prd) — preferred, contains structured requirements
A user-provided spec or description + an existing codebase — sufficient
Neither — suggest /prd first, but don't hard-gate. If the user has a clear direction ("add auth to my app"), that + the existing code IS the input.

Mode Detection

Greenfield mode: PRD exists with Mode: greenfield, or no existing source files. Produces a complete architecture from scratch.

Feature mode: PRD exists with Mode: feature, OR the user describes a feature and the project has existing source files. The architecture describes changes to existing code, not a standalone system.

In feature mode:

Read the existing file tree FIRST — understand the current architecture before planning changes
Read key files (package.json, tsconfig, main entry points, existing patterns)
The File Tree section shows ONLY new and modified files, not the entire project
Phases include a Phase 0: "Baseline" that records current typecheck/test state
Every phase's end conditions include "no new typecheck errors" and "existing tests pass"
The Risk Register includes "regression in existing functionality" as a default risk

Protocol

Step 1: READ

If PRD exists, read it. Extract:

Core features (the numbered list)
Technical decisions (stack choices)
End conditions (what "done" looks like)
Out of scope (what NOT to build)
Integration points (feature mode)

If no PRD, read the codebase instead:

Scan the file tree for structure and conventions
Read package.json / equivalent for dependencies and scripts
Read the main entry point(s) to understand the architecture
Use the user's description as the feature spec
Infer end conditions from the description ("add auth" → "protected routes return 401 without token")

Step 2: EVALUATE OPTIONS (for non-trivial decisions)

For decisions with multiple valid approaches — state management, API structure, auth pattern, DB schema, routing — generate 2-3 candidates. Assess each on complexity, risk, maintainability, and LLM-friendliness. Pick the winner and document why. Reject alternatives with reasoning.

Simple decisions (file naming, folder structure, CSS) don't need this — use the PRD's stack choices and move on.

Show full SKILL.md (218 more words)Show less

Step 3: PRODUCE

Write to .planning/architecture-{slug}.md:

markdown

# Architecture: {App Name}
> PRD: .planning/prd-{slug}.md  |  Date: {ISO date}

## File Tree
{Greenfield: complete file tree for v1, every file listed.
Feature mode: ONLY new (+) and modified (~) files.}

## Component Breakdown
### Feature: {name}
- Files: | Dependencies: | Complexity: {low/medium/high}

## Data Model
### {Entity name}
- Fields: {name: type}  |  Relationships: {connections}
{Omit section if no database.}

## Key Decisions
### {Decision}: {chosen approach}
- **Chosen**: {approach} — {reasoning}
- **Rejected**: {alternative} — {why not}

## Build Phases
### Phase N: {name}
- **Goal**: {one sentence}
- **Files**: | **Dependencies**: {or "none"}
- **End Conditions**: [ ] {machine-verifiable}

## Phase Dependency Graph
{Text format: Phase 1 → Phase 2 → Phase 3 / Phase 3 + 4 → Phase 5}

## Risk Register
1. {risk}: {mitigation}
2. {risk}: {mitigation}
3. {risk}: {mitigation}

## Deployment Strategy
{Skip if "deploy later" or static-only.}
- **Platform**: | **Method**: | **Environment variables**: | **Pre-deploy checks**:
{Final phase is "Deploy" when a platform is specified. A failed deploy does NOT fail the campaign.}

Step 4: CONNECT TO CAMPAIGN

Each build phase becomes a campaign phase; end conditions carry over; the dependency graph determines ordering; parallel-safe phases flagged for Fleet.

Present summary to user (file count, phase count, key decisions, estimated complexity) and ask: "Ready to build? This will create an Archon campaign." If approved, write the campaign file.

Step 5: HANDOFF

---HANDOFF---
- Architecture: {app name}
- Document: .planning/architecture-{slug}.md
- Phases: {count}
- Estimated complexity: {low/medium/high}
- Next: Archon campaign ready to execute
- Reversibility: green — delete .planning/architecture-{slug}.md to undo
---

Contextual Gates

Disclosure: "Generating architecture plan for [description]. No files modified until you approve." Reversibility: green — creates .planning/architecture-{slug}.md only; undo with rm .planning/architecture-{slug}.md. Trust gates:

Any: generate architecture document, evaluate options, connect to campaign.

Quality Gates

Every phase has at least one machine-verifiable end condition
Every key decision documents what was rejected and why
File tree is complete (no "etc." or "..." placeholders)
Phase dependencies are explicit (no implicit ordering)
Risk register has at least 2 entries

Fringe Cases

No PRD: Treat user description + existing codebase as the spec; read file tree and package.json; proceed without requiring a PRD.

Project already has code: Use feature mode; read existing architecture first; file tree shows only new/modified files; Phase 0 records baseline typecheck/test state.

Vague description: Ask at most 2 clarifying questions; don't block on perfect clarity.

.planning/ missing: Create it; if not possible, output the architecture inline and instruct the user to save it.

Exit Protocol

---HANDOFF---
- Architecture: {app name}
- Document: .planning/architecture-{slug}.md
- Phases: {count}
- Estimated complexity: {low/medium/high}
- Next: Archon campaign ready to execute
- Reversibility: green — delete .planning/architecture-{slug}.md to undo
---

Files

SKILL.md and 2 other files in skills/architect of SethGammon/Citadel.

SKILL.md
__benchmarks__/no-prd.md
__benchmarks__/with-direction.md

Open the folder on GitHubat commit e41ff1d

Compare with similar skills

Architect next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Architect compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Architect this skillSethGammon/Citadel	922	—	~1.6k	Automated safety check: Pass	MIT	6 days ago
CCPM Project Managementautomazeio/ccpm	8.4k	—	~1.1k	Automated safety check: Pass	MIT	6 mo ago
Ralph Tui Create Beadssubsy/ralph-tui	2.5k	1 repos	~2.6k	Automated safety check: Pass	MIT	1 mo ago
Trellis Brainstormanjiemo/SunnyBeach	178	7 repos	~4k	Automated safety check: Pass	Apache-2.0	26 days ago
Adversarial Speczscole/adversarial-spec	556	1 repos	~8.3k	Automated safety check: Notes	MIT	8 mo ago
Ralph Tui Create Beads Rustsubsy/ralph-tui	2.5k	1 repos	~2.8k	Automated safety check: Pass	MIT	1 mo ago

Similar skills

CCPM Project Management
automazeio/ccpm
Runs a spec-driven workflow from PRD to epic to GitHub issues to parallel agents, with status, standup and blocked-work reports from bundled scripts.
8.4k GitHub stars~1.1k tokensUpdated 6 mo ago
Product & Project ManagementAuto-check passed
Ralph Tui Create Beads
subsy/ralph-tui
Convert PRDs to beads for ralph-tui execution. An agent skill from subsy/ralph-tui.
2.5k GitHub starsUsed in 1 repo~2.6k tokens
Product & Project ManagementAuto-check passed
Trellis Brainstorm
anjiemo/SunnyBeach
Guides collaborative requirements discovery before implementation.
178 GitHub starsUsed in 7 repos~4k tokens
Product & Project ManagementAuto-check passed
Adversarial Spec
zscole/adversarial-spec
Iteratively refine a product spec by debating with multiple LLMs (GPT, Gemini, Grok, etc.) until all models agree.
556 GitHub starsUsed in 1 repo~8.3k tokens
Product & Project ManagementAuto-check: notes
Ralph Tui Create Beads Rust
subsy/ralph-tui
Convert PRDs to beads for ralph-tui execution using beads-rust (br CLI).
2.5k GitHub starsUsed in 1 repo~2.8k tokens
Product & Project ManagementAuto-check passed
To Issues
ywwynm/EverythingDone
Break a plan, spec, or PRD into independently-grabbable issues on the project issue tracker using tracer-bullet vertical slices.
144 GitHub starsUsed in 12 repos~893 tokens
Product & Project ManagementAuto-check passed

Questions about Architect

What does Architect do?

Given a PRD, produces an implementation architecture: file tree, component breakdown, data model, and a phased build plan with end conditions that Archon can execute directly. Architect is an agent skill from SethGammon/Citadel. Given a PRD, produces an implementation architecture: file tree, component breakdown, data model, and a phased build plan with end conditions that Archon can execute directly.

When should I use Architect?

Architect fits situations like: tasks that involve PRD writing.

How do I install Architect in Claude Code?

Run `npx skills add SethGammon/Citadel --skill architect -a claude-code`. Or copy the skill folder (skills/architect in SethGammon/Citadel) into .claude/skills/architect in your project. Claude Code loads it when a task matches its description.

How do I install Architect in Codex?

Run `npx skills add SethGammon/Citadel --skill architect -a codex`. Or copy the skill folder (skills/architect in SethGammon/Citadel) into .agents/skills/architect in your project. Codex loads it when a task matches its description.

Can I use Architect in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add SethGammon/Citadel --skill architect -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/architect, .gemini/skills/architect, .github/skills/architect and .opencode/skills/architect in your project.

What does Architect need to run?

SKILL.md names no scripts, command-line tools or credentials: Architect is instructions for the agent only.

Does Architect access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Architect safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Architect use?

Architect is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Architect use?

About 1.6k tokens (SKILL.md is roughly 6.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Architect?

Skills that share tags, products or a category with Architect: CCPM Project Management (automazeio/ccpm, 8.4k stars), Ralph Tui Create Beads (subsy/ralph-tui, 2.5k stars), Trellis Brainstorm (anjiemo/SunnyBeach, 178 stars) and Adversarial Spec (zscole/adversarial-spec, 556 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Architect?

SethGammon (a GitHub user) maintains it in SethGammon/Citadel, which has 922 GitHub stars. The repository holds 48 skills in this directory. The repository was last updated on October 1, 2026.

Source: SethGammon/Citadel on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Architect

Facts

At a glance

What it does

When your agent uses it

Example prompts

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

/architect — Implementation Architecture from PRD

When to Use

Inputs

Mode Detection

Protocol

Step 1: READ

Step 2: EVALUATE OPTIONS (for non-trivial decisions)

Step 3: PRODUCE

Step 4: CONNECT TO CAMPAIGN

Step 5: HANDOFF

Contextual Gates

Quality Gates

Fringe Cases

Exit Protocol

Files

Compare with similar skills

Similar skills

More from SethGammon/Citadel

Related

Questions about Architect