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 skills add SethGammon/Citadel --skill setupgit 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/setup)<a href="https://agentmods.dev/skills/sethgammon/citadel/setup"><img src="https://agentmods.dev/badge/skills/sethgammon/citadel/setup/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/sethgammon/citadel/setup"><img src="https://agentmods.dev/badge/skills/sethgammon/citadel/setup.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium MCP Rug Pull · line 89 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 104 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium Excessive Agency · line 91 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00069 | $0.04489 |
| Opus 5.5 | $0.00028 | $0.01796 |
| Sonnet 5.5 | $0.00014 | $0.00898 |
| Haiku 4.5 | $0.00007 | $0.00449 |
Grade A, and why
setup 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.
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 — 310 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/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.
| File | Restore to |
|---|---|
campaigns.md |
Split sections → .planning/campaigns/completed/{name}.md |
postmortems.md |
Split sections → .planning/postmortems/{name}.md |
research.md |
Split sections → .planning/research/{name}.md |
backlog.md |
Split sections → .planning/intake/{name}.md |
discoveries.md |
Split sections → .planning/discoveries/{name}.md |
project.md |
Strip frontmatter → .citadel/project.md |
harness.json.md |
Strip 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
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.
- 6d ago Changed 0f27ac18b839
- 27d ago Changed · +2 lines 90e499230b00
- 1mo ago First seen · 308 lines · 69 tokens per session scan A a989aa29490e
setup is a skill published in the GitHub repository SethGammon/Citadel (924 stars, last pushed today), licensed MIT. It adds 69 tokens to every session and 4,489 once invoked, about $0.0003 per session on Opus 5.5. 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.
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".
prototype
Use when asked to prototype one design question through a cheap logic or UI experiment, including button-driven state-model checks. Not for polished artifacts: use polished-web-prototype.
contexts
Use when the user says "get context on X", "how does X work", or wants architectural orientation before coding.