From loop
Write high-quality session prompts (SESSION_WORKER.md and SESSION_REVIEWER.md) for an agent loop. Reads repo context and follows the loop-author guide to produce targeted, effective prompts. Use when setting up a new loop or rewriting session prompts for an existing one.
How this skill is triggered — by the user, by Claude, or both
Slash command
/loop:loop-author-aThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
> **Action skill** — Write session prompts for agent loops following the loop-author guide.
Action skill — Write session prompts for agent loops following the loop-author guide.
$ARGUMENTS
Write SESSION_WORKER.md and SESSION_REVIEWER.md for an agent loop. These prompts define what the loop accomplishes and how the reviewer evaluates completion.
Before writing, read these sources to understand the repo and task:
# Project instructions
cat CLAUDE.md 2>/dev/null
cat .claude/CLAUDE.md 2>/dev/null
# Recent work
git log --oneline -20
# Repo structure (top-level)
ls -la
From $ARGUMENTS, extract:
Follow the session prompt anatomy from agents/prompts/loop-author.md (or ~/claude-tooling/agents-src/prompts/loop-author.md). The four required sections are:
# Objective
{One paragraph. What is the end goal? What is the output?}
{Read X, Y, Z before starting — point to specific files.}
## Context
{What exists today. Key files and directories. Existing patterns to follow.
What has been tried. Hard constraints.}
## Behavior Targets
When this is done, the following should be true:
1. {Observable behavior — written from a tester's perspective}
2. {Observable behavior}
3. ...
## Acceptance Criteria
- {Verifiable condition — the minimum bar}
- {Verifiable condition}
- ...
## Constraints
- {Hard constraint — language, patterns, dependencies}
- {Hard constraint}
src/auth/middleware.ts" not "understand the auth system."# Review Brief
You are reviewing progress toward: {one-line objective summary}
## What to Verify
- {Verification point — what to check at each iteration}
- {Verification point}
## Quality Bar
- {What good looks like for this specific task}
- {Standards that apply — tests, linting, patterns}
## Watch For
- {Known risk or failure mode}
- {Common mistake for this type of work}
## Done Condition
Write STOP.txt when:
- {Specific, observable condition}
- {Specific, observable condition}
Write the prompts to:
agents/loops/{loop-id}/session/SESSION_WORKER.md
agents/loops/{loop-id}/session/SESSION_REVIEWER.md
Create the directory structure if it doesn't exist:
mkdir -p agents/loops/{loop-id}/session
loop-launch-a or directly:
./agents/run.sh --loop-id {loop-id}
| Mistake | Fix |
|---|---|
| Vague objective | One paragraph, no ambiguity — name the output |
| Steps instead of goals | Describe what, not how |
| No acceptance criteria | List verifiable conditions |
| Reviewer copies worker | Write from reviewer perspective — it's a review brief |
| Too much context | Only include what's needed to start work |
| Implementation approach in prompt | Let the worker decide, reviewer course-correct |
npx claudepluginhub jsai23/claude-tooling --plugin loopCreates or improves production-grade system prompts for autonomous coding agents using evidence-gated workflows, explicit tool contracts, and completion criteria.
Conducts interactive interview to gather task details, generates PRD, and outputs optimized loop commands with phase tracking for Loop plugin.
Orchestrates a build-review-improve loop using sub-agents: a worker produces artifacts, a panel of reviewers critiques in parallel, and the worker iterates until passing. For explicit invocation only.