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 skills/sethgammon/citadel/architectnpx skills add SethGammon/Citadel --skill architectgit clone --depth 1 https://github.com/SethGammon/CitadelWrote 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.
[](https://agentmods.dev/skills/sethgammon/citadel/architect)<a href="https://agentmods.dev/skills/sethgammon/citadel/architect"><img src="https://agentmods.dev/badge/skills/sethgammon/citadel/architect.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00044 | $0.01573 |
| Opus 5 | $0.00022 | $0.00787 |
| Sonnet 5 | $0.00009 | $0.00315 |
| Haiku 4.5 | $0.00004 | $0.00157 |
Grade A, and why
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 4d 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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/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")
What ships with it
2 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.
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.
- 4d ago First seen · 181 lines · 44 tokens per session scan A 009d7f5a9e1a
architect is a skill published in the GitHub repository SethGammon/Citadel (916 stars, last pushed today), licensed MIT. It adds 44 tokens to every session and 1,573 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
compose-org
Run a task as an evolved multi-agent ORG using the installed liquid-org framework — where YOU (the running Claude) embody the org: you ask liquid-org which proven team topology + specialist personas to use (retrieved from its evolved pool, or assembled fresh), then dispatch ONE SUBAGENT PER TALENT to play each role…
liquid-rank
Rank the available skills by RELEVANCE to the current task, on demand, using liquid-org's read-only hermes skill ranker. This is an EXPLICIT, OPT-IN selector you invoke WHEN you want help choosing the most relevant skill for what you're doing — it is NOT default, automatic skill selection, and it does NOT decide for…
present-gate
First-officer gate-presentation rendering — the captain-facing gate-review template and assembly rules, including workflow-owned finding labels. Invoke at the gate point after the FO has decided a stage must be presented.
agent-workflow-playbook
AI Agent Workflow & Skill Architecture Guide — turn expert work into measurable, reusable agent systems. Covers workflow discovery, skill decomposition, harness design, evaluation, human escalation, observability, cost control, and multi-agent orchestration. Includes a measured marketing-delivery case: 15 people × 3–4…
audit-project
Run an iterative multi-agent code audit until critical and high findings are resolved. Use when the user says "audit my code", "find all the bugs", "deep code audit", "iterative review", or "review until clean".
ast-grep
Use when asked to run AST-based structural search, lint, or rewrite of code when regex is too fragile. Pattern is validated, blast radius reviewed, and rewrite landed at the correct scope. Don't use for remote, credential, publish, deploy, or irreversible changes.