Skills for Real Engineers. Straight from my .agents directory.
loop
Agent skill fromSethGammon/Citadel
Bounded foreground repetition for the current session. Creates a loop contract, runs or coordinates an action plus verifier up to a declared attempt limit, and records evidence under .planning/loops/. Use for repeat-until-pass work that is too small for daemon and not time-based scheduling.
How to install loop
npx skills add SethGammon/Citadel# or add only this skill to Claude Code: copy the folder
skills/loop/
# into
~/.claude/skills/loop/ (all projects)
.claude/skills/loop/ (one project)
1# /loop -- Bounded Foreground Loop23## Orientation45**Use when:** the user wants a visible repeat-until-pass cycle inside the6current session, such as "loop until lint passes" or "try this up to three7times and stop if tests still fail."89**Don't use when:** the work should run unattended across sessions (`/daemon`),10on a clock (`/schedule`), on file changes (`/watch`), or as a metric-driven11optimization experiment (`/experiment`).1213In Claude Code, invoke `/citadel:loop` to select this skill explicitly.14The host also has a timer-based `/loop` command with different semantics.1516## Commands1718| Command | Behavior |19|---|---|20| `/loop status` | Show all known Citadel loops with active/stopped grouping. |21| `/loop inspect {id}` | Show one loop's contract, verifier, budget, runs, and stop reason. |22| `/loop templates` | List built-in loop templates. |23| `/loop plan --template {name}` | Create a loop contract from a template. |24| `/loop run "{action}" --verify "{command}" --max {N}` | Run a bounded foreground loop. |25| `/loop stop {id}` | Mark a loop stopped. |2627## Protocol2829### Step 1: Classify the loop3031Determine which kind of loop the user requested:3233| User intent | Route |34|---|---|35| Repeat within this active session | `/loop` |36| Continue campaign across sessions | `/daemon` |37| Run on a schedule | `/schedule` |38| Watch PR checks/reviews | `/pr-watch` |39| Watch files or marker comments | `/watch` |40| Optimize a numeric metric | `/experiment` |41…
Excerpt shown under the repository's MIT license.
More skills in Citadel
Similar skill repositories
An agentic skills framework & software development methodology that works.
Public repository for Agent Skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
Production-grade engineering skills for AI coding agents.
