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/create-appnpx skills add SethGammon/Citadel --skill create-appgit clone --depth 1 https://github.com/SethGammon/CitadelWhat 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 | $0.01621 |
| Opus 5 | $0.00026 | $0.00811 |
| Sonnet 5 | $0.00010 | $0.00324 |
| Haiku 4.5 | $0.00005 | $0.00162 |
Grade A, and why
create-app 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 3d 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/create-app — From Description to Verified Application
Orientation
Use when: building a new app from scratch -- full scaffold, design system, and feature set from a single description. Don't use when: adding a feature to an existing app (use /marshal or /archon); generating a single component (use /scaffold).
Tier Detection
Use when the user wants to create an app, add a feature, or scaffold a project. Classify the input into one of five tiers:
Tier 1: Blank Project
- Trigger: "create a blank project", "new project", "scaffold"
- Action: Run /scaffold with stack detection. No PRD, no architecture.
Tier 2: Guided
- Trigger: "I want to build...", "help me create...", description with questions
- Action: /prd → user approves → /architect → user approves → /archon
- Human checkpoints: after PRD, after architecture, before each major phase.
Tier 3: Templated
- Trigger: Describes a well-known app type ("a todo app", "a blog", "a dashboard with auth")
- Action: Load template PRD if available → /architect with template defaults → /archon
- Template detection: check
.planning/_templates/app-types/for matching templates. If no template matches, fall through to Tier 2.
Tier 4: Generated (Full Autonomy)
- Trigger: "build me [detailed description]", "create [app] and deploy it"
- Action: /prd (minimal questions) → /architect (auto-approve if confidence high) → /archon with self-correction loop
- Human checkpoints: after PRD only. Architecture and execution are autonomous.
- Safety: all Archon self-correction mechanisms active. Direction alignment every 2 phases. Quality spot-checks every phase. Circuit breakers armed.
Tier 5: Feature Addition (Existing Codebase)
- Trigger: existing project + feature description ("add auth", "add a dashboard", "add dark mode")
- Detection: project has source files (src/, app/, lib/, package.json with deps) AND description is a feature, not a standalone app
- Action: /prd in feature mode → /architect in existing codebase mode → /archon
- Key differences from greenfield tiers:
- PRD reads existing codebase before asking questions
- Architecture describes changes to existing files, not a standalone system
- Phase 0 is always "Baseline" — record current typecheck/test state
- Every phase end condition includes "no new typecheck errors" + "existing tests pass"
- Risk register always includes "regression in existing functionality"
- Human checkpoints: after feature spec (PRD). Architecture can auto-approve if the feature is well-scoped and all conditions are machine-verifiable.
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.
- 3d ago First seen · 153 lines · 52 tokens per session scan A 30de1a93eddf
create-app is a skill published in the GitHub repository SethGammon/Citadel (914 stars, last pushed 6d ago), licensed MIT. It adds 52 tokens to every session and 1,621 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 2026-08-30.
Other skills, from other repositories
debrief
This skill should be used when the user asks to "debrief", "record what happened", "session summary", "write a debrief", or wants to capture session activity (commits, task state changes, decisions, issues) into a structured record for the next session.
refit
This skill should be used when the user asks to "refit a workflow", "upgrade a workflow", "update workflow scaffolding", or wants to bring an existing workflow's scaffolding files up to date with the current Spacedock version.
fo-dispatch-recovery
Claude dispatch failure recovery — Break-Glass Manual Dispatch (the manual Agent() template) and Context Budget Failure/Dead Ensign Handling (the budget-unavailable stderr conditions, the recovery clause, dead-ensign bookkeeping). Read ONLY at its resident triggers inside claude-fo-dispatch.md — a non-zero or…
fo-status-viewer
First-officer status query/mutate/display surface — the status command flag docs, --set field docs, canonical captain-facing invocations, the Captain-Facing State Display rendering, and the GitHub-issue-filing approval gate. Invoke at the first ad-hoc status question, --set mutation, --next-id/--resolve lookup, or…
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…