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/loopnpx skills add SethGammon/Citadel --skill loopgit 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 | $0.00058 | $0.01400 |
| Opus 5 | $0.00029 | $0.00700 |
| Sonnet 5 | $0.00012 | $0.00280 |
| Haiku 4.5 | $0.00006 | $0.00140 |
Grade A, and why
loop 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 2d 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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/loop -- Bounded Foreground Loop
Orientation
Use when: the user wants a visible repeat-until-pass cycle inside the current session, such as "loop until lint passes" or "try this up to three times and stop if tests still fail."
Don't use when: the work should run unattended across sessions (/daemon),
on a clock (/schedule), on file changes (/watch), or as a metric-driven
optimization experiment (/experiment).
Commands
| Command | Behavior |
|---|---|
/loop status |
Show all known Citadel loops with active/stopped grouping. |
/loop inspect {id} |
Show one loop's contract, verifier, budget, runs, and stop reason. |
/loop templates |
List built-in loop templates. |
/loop plan --template {name} |
Create a loop contract from a template. |
/loop run "{action}" --verify "{command}" --max {N} |
Run a bounded foreground loop. |
/loop stop {id} |
Mark a loop stopped. |
Protocol
Step 1: Classify the loop
Determine which kind of loop the user requested:
| User intent | Route |
|---|---|
| Repeat within this active session | /loop |
| Continue campaign across sessions | /daemon |
| Run on a schedule | /schedule |
| Watch PR checks/reviews | /pr-watch |
| Watch files or marker comments | /watch |
| Optimize a numeric metric | /experiment |
If another route is clearly better, say so and route there.
Step 2: Require a verifier
A /loop run must have an explicit verifier. Explicit means the user supplied
--verify "<command>" or an equally concrete verifier command in plain language.
Do not infer a verifier from words like "lint", "test", "until it works", or
"fix until passing." If the verifier is missing, ask for it before executing and
do not run loop-runner.js, shell commands, or manual repair steps.
Accept examples like:
--verify "npm run lint"
--verify "npm run test"
--verify "node scripts/operating-proof.js --write"
If missing, respond in this shape:
/loop needs an explicit verifier before it can run. Please provide one, for example:
--verify "npm run lint"
I will not run the loop until the verifier is explicit.
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.
- 2d ago First seen · 189 lines · 58 tokens per session scan A 635f89ede743
loop is a skill published in the GitHub repository SethGammon/Citadel (912 stars, last pushed 5d ago), licensed MIT. It adds 58 tokens to every session and 1,400 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…
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.
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…
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…