Agent skill

Setup

by SethGammon in SethGammon/Citadel

First-run experience for the harness. An agent skill from SethGammon/Citadel.

MITAuto-check passedAgent Workflows

Install Setup

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

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

GitHub CLI
$ gh skill install SethGammon/Citadel setup --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/setup .claude/skills/setup && 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/

Facts

Skill name
setup
GitHub stars
922
Token cost
~4.5k tokens
SKILL.md length
1,781 words
Files
3
Skills in repo
48
Repo updated
First seen
Licence
MIT

At a glance

First-run experience for the harness. An agent skill from SethGammon/Citadel.

  • Works in 10 steps: MODE SELECTION → INSTALL HOOKS (all modes, always first) → STACK DETECTION (all modes) → …
  • Agent Workflows work in your project
  • SKILL.md covers Orientation, Protocol, Fringe Cases and Contextual Gates, plus 2 more sections
  • Calls node, codex and npx; needs ANTHROPIC_API_KEY

What it does

Setup is an agent skill from SethGammon/Citadel. First-run experience for the harness. Three modes: Recommended (guided, ~3 min), Full Tour (guided + skill walkthrough, ~8 min), and Express (zero questions, ~30 sec). Installs hooks first, detects stack, configures harness.json, runs a live demo on real code, and prints a reference card.

Its SKILL.md is about 4.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 3 other files (for example `__benchmarks__/already-configured.md` and `__benchmarks__/fresh-project.md`).

It sits in Agent Workflows. 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

  • Agent Workflows work in your project

Example prompts

  • “/setup”

Requirements

  • Python 3
  • Node.js
  • A credential in ANTHROPIC_API_KEY

Workflow steps

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

  1. MODE SELECTION
  2. INSTALL HOOKS (all modes, always first)
  3. STACK DETECTION (all modes)
  4. GENERATE CONFIG (all modes)
  5. CLAUDE.md + AGENTS.md (all modes)
  6. OPTIONAL INTEGRATIONS (Recommended + Full Tour only)
  7. LIVE DEMO (Recommended + Full Tour only)
  8. FULL TOUR WALKTHROUGH (Full Tour only)
  9. REFERENCE CARD (all modes)
  10. CLOSING LINE (all modes)

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

    Shell commands in SKILL.md call:

    • node
    • codex
    • npx
    • mypy
    • go
    • cargo
    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use npx and git, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • ANTHROPIC_API_KEY

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Setup loads about 4.5k tokens when it runs. Until then it costs about 74 tokens; SKILL.md has 1,781 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~74
When it runs · the whole SKILL.md, loaded when a task matches
~4.5k

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). 1,781 words, ~4,500 tokens.

Download SKILL.mdSave it as .claude/skills/setup/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
setup
description
First-run experience for the harness. Three modes: Recommended (guided, ~3 min), Full Tour (guided + skill walkthrough, ~8 min), and Express (zero questions, ~30 sec). Installs hooks first, detects stack, configures harness.json, runs a live demo on real code, and prints a reference card.
license
MIT
user-invocable
true
auto-trigger
false
trigger_keywords
setup, first run, configure harness, install citadel, getting started
last-updated
2026-04-06

/do setup — First-Run Experience

Configures the harness for a specific project: installs hooks, detects stack, writes harness.json, and optionally demos the system on real code. Flag: /do setup --express skips mode selection and runs Express directly. Reference tables and layouts: docs/SETUP_REFERENCE.md.

Orientation

Use when: first-run configuration of Citadel on a new project -- installs hooks, generates harness.json, scaffolds .planning/. Don't use when: harness is already configured and you want to verify it (use /verify); adding a single skill to an existing project (copy SKILL.md manually).

Protocol

Step -1: ARCHIVE DETECTION (all modes, before anything else)

Run ls docs/citadel/ 2>/dev/null. If docs/citadel/ exists and contains .md files with citadel-archive: true in frontmatter, extract the exported-at date and prompt once:

Found a Citadel archive from {exported-at date}.
  Campaigns: {N}  Postmortems: {N}  Backlog items: {N}  Research: {N}

Restore history into .planning/ during setup? [Y/n]

Y or Enter → set restoreArchive = true, restore after Step 1 (below). n → skip silently. No archive found → skip entirely, no output.

ARCHIVE RESTORE (runs after Step 1 if restoreArchive = true). Splitting: each ## Section Title becomes one restored file; strip frontmatter before writing.

FileRestore to
campaigns.mdSplit sections → .planning/campaigns/completed/{name}.md
postmortems.mdSplit sections → .planning/postmortems/{name}.md
research.mdSplit sections → .planning/research/{name}.md
backlog.mdSplit sections → .planning/intake/{name}.md
discoveries.mdSplit sections → .planning/discoveries/{name}.md
project.mdStrip frontmatter → .citadel/project.md
harness.json.mdStrip frontmatter → .claude/harness.json (Citadel's shared config path for all runtimes, including Codex)

After restore: ✓ Archive restored — {N} campaigns, {N} postmortems, {N} backlog items

Step 0: MODE SELECTION
Welcome to Citadel.

How would you like to get started?

  [1] Recommended  — auto-detect your stack, install hooks, live demo  (~3 min)
  [2] Full Tour    — everything in Recommended + guided skill walkthrough (~8 min)
  [3] Express      — zero questions, auto-detect, hooks installed, done  (~30 sec)

Press Enter for Recommended, or type 1, 2, or 3.

If harness.json already exists with full config, add: [4] Update — reconfigure existing setup (current: {language}, {skillCount} skills). Default: Recommended. If --express flag passed: skip mode selection, run Express.

Step 1: INSTALL HOOKS (all modes, always first)

Hooks must be live before anything else. Run node {citadel-root}/scripts/install-hooks.js. Find {citadel-root}: read .citadel/plugin-root.txt; fallback: directory containing this SKILL.md. The installer resolves the current config (or the bootstrap Standard + Core + Persistence default), writes .citadel/effective-config.json, installs only hooks owned by effective bundles, preserves non-Citadel settings, and is idempotent.

On success: ✓ {N} hooks installed (protect-files, external-gate, circuit-breaker, quality-gate + more) On failure: output the error, explain manual install path (node /path/to/Citadel/scripts/install-hooks.js), continue — setup must not abort.

Step 2: STACK DETECTION (all modes)

Auto-detect by scanning the project root. Never ask what can be read. (Readable tables: docs/SETUP_REFERENCE.md#stack-detection-tables.)

  • Language (check in order): tsconfig.json → TypeScript; package.json without tsconfig → JavaScript; requirements.txt or pyproject.toml → Python; go.mod → Go; Cargo.toml → Rust; pom.xml or build.gradle → Java
  • Framework (package.json dependencies): next → Next.js; react (no next) → React; vue → Vue; svelte → Svelte; @angular/core → Angular; express → Express; fastify → Fastify
  • Package manager: pnpm-lock.yaml → pnpm; yarn.lock → yarn; bun.lockb → bun; package-lock.json → npm; requirements.txt → pip; Pipfile → pipenv
  • Test framework: package.json devDependencies for jest, vitest, mocha, jasmine; Python: pytest in requirements.txt or pyproject.toml
  • Typecheck by language: TypeScript npx tsc --noEmit (per-file: no, project-scope incremental); Python mypy {file} or pyright {file} (per-file: yes); Go go vet ./..., Rust cargo check, JavaScript none (per-file: no)

Confirmation (Recommended + Full Tour only): output Detected: {language}{+ framework if any} · {packageManager} · {testFramework if any}, then Correct? [y/n/edit]. y/Enter → proceed; n/edit → ask for corrections inline. Express: skip confirmation, use detected values.

Step 3: GENERATE CONFIG (all modes)

Create .planning/tmp/citadel-stack.json with only the detected compatibility fields below. This input is not authoritative and must not contain profile, bundle, consent, trust, or policy fields:

json
{
  "language": "typescript",
  "framework": "react",
  "packageManager": "npm",
  "typecheck": { "command": "npx tsc --noEmit", "perFile": false, "timeoutMs": 25000 },
  "test": { "command": "npm test", "framework": "vitest" },
  "qualityRules": { "builtIn": ["no-confirm-alert", "no-transition-all"], "custom": [] },
  "protectedFiles": [".claude/harness.json", ".claude/settings.json"],
  "features": { "intakeScanner": true, "telemetry": true },
  "registeredSkills": ["do", "review"],
  "registeredSkillCount": 2,
  "agentTimeouts": { "skill": 600000, "research": 900000, "build": 1800000 }
}

Substitute the detected values and complete skill list; use JSON null when no framework or test framework is detected.

Preview the deterministic version-2 config migration without writing:

bash
node {citadelRoot}/scripts/citadel-config.js initialize \
  --input .planning/tmp/citadel-stack.json --runtime {claude-code|codex|opencode} --json

Show profile, bundles, source/candidate digests, and changed fields. Apply only after the selected setup mode authorizes this exact plan:

bash
node {citadelRoot}/scripts/citadel-config.js initialize \
  --input .planning/tmp/citadel-stack.json --runtime {claude-code|codex|opencode} --apply --json

Recommended and Express use standard@1.0.0 with Core + Persistence. Full Tour may preview Parallel and Operations, but each bundle needs an explicit enable plan. If the runtime is partial, show the named adapter and require --allow-degraded-runtime; never silently describe degraded support as full. Delivery remains off until the user explicitly enables it.

The apply creates a sibling backup when replacing an existing config, validates the observed digest, rolls back a failed write, and reconciles .citadel/effective-config.json. Re-run install-hooks.js after the final bundle choice so disabled hook families are removed from the generated runtime projection.

Note: perFile applies to Python checkers only; TypeScript always runs a project-scope incremental check and ignores perFile with an advisory.

Skill registry rebuild: populate registeredSkills from every directory under {citadelRoot}/skills/ plus .claude/skills/. Set registeredSkillCount to match.

Routing table regeneration: run node {citadelRoot}/scripts/generate-routing.js, then verify with node {citadelRoot}/scripts/generate-routing.js --check — exit 0 means all routing surfaces are in sync (what it regenerates: docs/SETUP_REFERENCE.md#routing-surfaces). If the script is missing (older Citadel install), skip this step silently.

Dependency pattern suggestions (Recommended + Full Tour only): read package.json for @tanstack/react-query, zustand, date-fns, zod. For each match ask: "I see {package} installed. Warn agents when they use {anti-pattern}? [y/n]" and add accepted patterns to dependencyPatterns in harness.json (anti-pattern and message table: docs/SETUP_REFERENCE.md#dependency-pattern-suggestions).

Step 4: CLAUDE.md + AGENTS.md (all modes)

Run node {citadelRoot}/scripts/bootstrap-project-guidance.js --project-root {projectRoot} — creates .citadel/project.md and compatible CLAUDE.md plus AGENTS.md guidance. Safe to run — it preserves user-authored files.

Claude Code v2.1.277 or later can use only AGENTS.md, but the version alone does not prove the built-in support is available in the current environment. When the operator has confirmed the Project instructions setting or an AGENTS.md loaded startup notice, run node {citadelRoot}/scripts/bootstrap-project-guidance.js --project-root {projectRoot} --claude-agents-md-supported. The script detects the installed Claude Code version, migrates only byte-for-byte unchanged Citadel guidance, and retains CLAUDE.md when the version or capability is unknown or project guidance would take precedence.

Project description (Recommended + Full Tour only): ask "What's this project? One line is fine — or press Enter to use the package name." Skip if CLAUDE.md already exists with content.

CLAUDE.md merge rules:

  • Does not exist → generate the starter from docs/SETUP_REFERENCE.md#claudemd-starter-template: project name, description, Stack section (detected values), placeholder Conventions and Architecture sections, and a ## Citadel Harness section noting the harness and .claude/harness.json
  • Exists, no ## Citadel Harness section → append that section at bottom only
  • Exists with ## Citadel Harness → skip, don't duplicate
  • NEVER overwrite or delete existing content

Present as one prompt:

Optional integrations — choose any, or press Enter to skip all:
  [g] GitHub    — scaffold Claude triage workflow for issues + PRs
  [m] MCP       — create .mcp.json with common servers pre-configured
  [b] Both
  [s] Skip

GitHub: create .github/workflows/ if missing; copy .planning/_templates/claude-triage.yml → .github/workflows/claude-triage.yml and .planning/_templates/REVIEW.md → REVIEW.md (skip any that already exist). Output: "Add ANTHROPIC_API_KEY to Settings > Secrets > Actions to activate." MCP: copy .planning/_templates/.mcp.json → .mcp.json (skip if exists). Output: "Edit .mcp.json to uncomment the servers you want."

Run node {citadelRoot}/scripts/repository-memory.js status --project-root {projectRoot} --json.

  • Already enabled: report the stored file/version counts and do not prompt.
  • unavailable: skip the prompt; this optional capability requires Node.js 22.13+.
  • Otherwise ask: "Preserve completed Citadel lessons across disposable clones in a local user-level SQLite database? [y/N]"

On yes, run:

bash
node {citadelRoot}/scripts/repository-memory.js enable --project-root {projectRoot}

State exactly what is stored: completed campaigns, postmortems, research, discoveries, backlog Markdown, and .citadel/project.md. State what is excluded: active work, telemetry, worktrees, consent, runtime config, and credentials. Raw remote URLs and clone paths are excluded as identity metadata, but allowlisted documents are stored verbatim and may mention either. Express mode never opts in automatically, but an already-enabled repository continues to restore and sync through lifecycle hooks.

Show full SKILL.md (661 more words)Show less

Find target file: git diff --name-only HEAD~1 HEAD 2>/dev/null | head -5, filter for source files, use the most recently changed. If no git history, use find for recently modified files.

Pain point question:

What's your biggest frustration with AI coding tools right now?

  [a] Repetitive context — I keep re-explaining my codebase
  [b] Quality — the agent breaks things or misses issues
  [c] Context loss — every new session starts from zero
  [d] Scale — fine for small tasks, falls apart on big ones
  [e] Something else / skip demo

Demo by pain point — execute on real code, show output:

  • (a) run /review on target file — "This review uses the harness.json config you just set up — it already knows your stack, conventions, and quality rules."
  • (b) run /review on target file — "The quality-gate hook just ran on every edit made during setup. Here's what that looks like on your code:"
  • (c) show .planning/ structure, explain campaigns — "Sessions now persist. Start a campaign today, close your laptop, resume tomorrow."
  • (d) run /review on largest source file — "For bigger work: /marshal for multi-step sessions, /archon for multi-day campaigns, /fleet for parallel agents."
  • (e) skip demo, continue to reference card
Step 7: FULL TOUR WALKTHROUGH (Full Tour only)

Present the five skill families in order, using the per-skill one-liners and timings from docs/SETUP_REFERENCE.md#full-tour-walkthrough:

  1. Code Quality (2 min): /review, /test-gen, /systematic-debugging — show by running /review on the Step 6 file if not already done
  2. Building (2 min): /scaffold, /refactor, /create-skill
  3. Research (1 min): /research (add --parallel for multi-scout), /infra-audit
  4. Orchestration (1 min): /marshal, /archon, /fleet
  5. Observability (1 min): /do next, /dashboard, /cost, /learn

After walkthrough: That's the system. Everything routes through /do — you never have to choose the right tool.

Step 8: REFERENCE CARD (all modes)

Print the reference card using the canonical boxed layout at docs/SETUP_REFERENCE.md#reference-card, filled with actual counts from the detected config. It must contain, in order:

  • Header: CITADEL READY — {N} skills · {N} hooks live · {language}{+ framework}
  • THE ONE COMMAND: /do [anything] — describe what you want in plain English, the router handles the rest
  • COMMON STARTING POINTS: /do review [file], /do fix [description], /do why is [thing] broken, /do build [feature], /do test [file], /do next, /do status, /do continue
  • WHEN TASKS GET BIGGER: /marshal (multi-step, one session), /archon (multi-session campaign), /fleet (parallel agents)
  • WHAT'S NOW PROTECTING YOUR SESSION: protect-files, external-gate, circuit-breaker, quality-gate, telemetry
  • NEXT STEPS: add conventions to CLAUDE.md, /do --list, /create-skill, /improve [target]
  • Footer: docs/SKILLS.md · INSTALL.md · /do --list

Express mode: print abbreviated card (THE ONE COMMAND + WHAT'S NOW PROTECTING only).

Step 9: CLOSING LINE (all modes)
Express:      Done. {N} hooks live, {N} skills registered.
              Type /do [anything] to start.

Recommended:  Setup complete. Citadel is configured for {language}{+ framework}.
              {N} hooks are protecting this session. {N} skills are registered.
              Type /do [anything] to get started — or /do --list to browse all skills.

Full Tour:    Tour complete. You've seen the full system.
              {N} hooks live · {N} skills registered · trust level: {level}
              The best next thing: /do "review the most important file in this codebase"

Update:       Configuration updated. {N} hooks reinstalled, {N} skills re-registered.
              Changes: {list what changed vs previous config}

Fringe Cases

Plugin not found (.citadel/plugin-root.txt missing): Prompt for Citadel install path. Write answer to .citadel/plugin-root.txt.

Project has no source files: Skip demo. Output: "Once you have code, try /review [file] to see the harness in action."

harness.json is protected and Write tool is blocked: Do not bypass the hook. Use the plan-first citadel-config.js initialize flow above.

Existing CLAUDE.md with no blank line at end: Append newline before ## Citadel Harness section.

Stack detection fails entirely: Fall back to: "What's your primary language? (typescript / javascript / python / go / rust / other)"

Re-running setup on configured project (Update mode): Show diff of what would change. Don't silently overwrite. Confirm each change.

bootstrap-project-guidance.js not found: Skip silently — fall back to manual CLAUDE.md template.

Contextual Gates

Disclosure: "Configuring Citadel for this project. Will preview a versioned config, reconcile the effective receipt, and install hooks owned by the selected bundles." Reversibility: amber. Writes receipted config/hook state and creates .planning/; undo through node scripts/adopt.js leave plan --target . --out ../citadel-leave.plan.json, then apply that reviewed plan with its exact token Trust gates:

  • Any: first-run configuration; expected to modify settings and install hooks

Quality Gates

  • Hooks must be installed before any other step completes
  • harness.json must validate as schema v2 and contain registeredSkillCount matching actual skill count
  • .citadel/effective-config.json must be current for the harness source digest
  • installed hooks must belong only to effective bundles
  • CLAUDE.md must not lose existing content
  • Demo must run on real user code, not a canned example
  • Reference card must show accurate skill and hook counts
  • Closing line must confirm hooks are live

Exit Protocol

Do not output a HANDOFF block. Setup is the beginning. After the closing line, wait for the user's next command.

© SethGammon, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

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

  • SKILL.md
  • __benchmarks__/already-configured.md
  • __benchmarks__/fresh-project.md

Open the folder on GitHubat commit e41ff1d

Compare with similar skills

Setup 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.

Setup compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Setup this skillSethGammon/Citadel922—~4.5kAutomated safety check: PassMIT
MCP Server Builderanthropics/skills180k62 repos~2.3kAutomated safety check: PassApache-2.0
Hook Development for Claude Code Pluginsanthropics/claude-plugins-official37k11 repos~4.1kAutomated safety check: NotesApache-2.0
Using Superpowersfarm-fe/farm5.6k34 repos~1.4kAutomated safety check: PassMIT
Executing Plans Inlineobra/superpowers296k2 repos~5.1kAutomated safety check: PassMIT
Claude Code Agent Developmentanthropics/claude-plugins-official37k8 repos~2.8kAutomated safety check: PassApache-2.0

Similar skills

  • MCP Server Builder

    anthropics/skills

    Official

    Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.

    180k GitHub starsUsed in 62 repos~2.3k tokens
    Agent WorkflowsAuto-check passed
  • Hook Development for Claude Code Plugins

    anthropics/claude-plugins-official

    Official

    Explains how to write Claude Code plugin hooks, both prompt-based checks and bash commands, for events such as PreToolUse, Stop and SessionStart.

    37k GitHub starsUsed in 11 repos~4.1k tokens
    Agent WorkflowsAuto-check: notes
  • Using Superpowers

    farm-fe/farm

    A skill your agent uses when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions

    5.6k GitHub starsUsed in 34 repos~1.4k tokens
    Agent WorkflowsAuto-check passed
  • Executing Plans Inline

    obra/superpowers

    Has the agent carry out an implementation plan itself, task by task in the current session, keeping a ledger, proving each step with a test and ending with one whole-branch review.

    296k GitHub starsUsed in 2 repos~5.1k tokens
    Agent WorkflowsAuto-check passed
  • Claude Code Agent Development

    anthropics/claude-plugins-official

    Official

    Explains how to write agents for Claude Code plugins: the markdown file with YAML frontmatter, trigger descriptions, model and color settings, and system prompt design.

    37k GitHub starsUsed in 8 repos~2.8k tokens
    Agent WorkflowsAuto-check passed
  • Skill Creator

    Azure/azqr

    Official

    Create new skills, modify and improve existing skills, and measure skill performance.

    794 GitHub starsUsed in 89 repos~8.2k tokens
    Agent WorkflowsAuto-check passed

More from SethGammon/Citadel

All 48 skills in this repo
  • Create Skill

    SethGammon/Citadel

    Creates new skills from the user's repeating patterns. An agent skill from SethGammon/Citadel.

    922 GitHub stars~1.9k tokensUpdated 6 days ago
    Auto-check passed
  • Houseclean

    SethGammon/Citadel

    Cross-drive storage audit and cleanup. An agent skill from SethGammon/Citadel.

    922 GitHub stars~2.2k tokensUpdated 6 days ago
    Auto-check passed
  • Loop

    SethGammon/Citadel

    Bounded foreground repetition for the current session. An agent skill from SethGammon/Citadel.

    922 GitHub stars~1.4k tokensUpdated 6 days ago
    Auto-check passed
  • Triage

    SethGammon/Citadel

    GitHub issue and PR investigator. An agent skill from SethGammon/Citadel.

    922 GitHub stars~2.7k tokensUpdated 6 days ago
    Auto-check passed
  • Watch

    SethGammon/Citadel

    File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills.

    922 GitHub stars~2.9k tokensUpdated 6 days ago
    Auto-check passed
  • Archon

    SethGammon/Citadel

    Autonomous multi-session campaign agent. An agent skill from SethGammon/Citadel.

    922 GitHub stars~5.4k tokensUpdated 6 days ago
    Auto-check passed

Categories

Questions about Setup

What does Setup do?

First-run experience for the harness. An agent skill from SethGammon/Citadel. Setup is an agent skill from SethGammon/Citadel. First-run experience for the harness.

When should I use Setup?

Setup fits situations like: agent Workflows work in your project.

How do I install Setup in Claude Code?

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

How do I install Setup in Codex?

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

Can I use Setup 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 setup -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/setup, .gemini/skills/setup, .github/skills/setup and .opencode/skills/setup in your project.

What does Setup need to run?

Going by SKILL.md and its folder, Setup needs the command-line tools its instructions call (node, codex, npx, mypy, go and cargo) and credentials named ANTHROPIC_API_KEY. Our summary lists: Python 3; Node.js; A credential in ANTHROPIC_API_KEY.

Does Setup access the network?

SKILL.md contains no URLs. Its commands use npx and git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Setup 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 Setup use?

Setup 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 Setup use?

About 4.5k tokens (SKILL.md is roughly 18k 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 Setup?

Skills that share tags, products or a category with Setup: MCP Server Builder (anthropics/skills, 180k stars), Hook Development for Claude Code Plugins (anthropics/claude-plugins-official, 37k stars), Using Superpowers (farm-fe/farm, 5.6k stars) and Executing Plans Inline (obra/superpowers, 296k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Setup?

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.