---
type: Index
title: 'Reusable prompts'
description: 'System prompts, sub-agent recipes, and slash-command bodies that consistently produce gold-standard output.'
---

# Reusable prompts

System prompts, sub-agent recipes, and slash-command bodies that consistently produce gold-standard output.

## Status

✓ v1 — 12 prompt bodies shipped. Adapt the bodies to your toolchain (Claude Code, Cursor, Aider, your CLI).

## Index

| Prompt | Type | Use when |
|---|---|---|
| [`system-architect.md`](/docs/prompts/system-architect) | system | Designing a new package boundary, ADR, or contract |
| [`system-implementer.md`](/docs/prompts/system-implementer) | system | Building a sub-unit against an existing design |
| [`system-reviewer.md`](/docs/prompts/system-reviewer) | system | Code review pass with confidence-scored output |
| [`system-security.md`](/docs/prompts/system-security) | system | Security review of pending changes |
| [`subagent-explore.md`](/docs/prompts/subagent-explore) | sub-agent recipe | Read-only fan-out search across files |
| [`subagent-plan.md`](/docs/prompts/subagent-plan) | sub-agent recipe | Step-by-step implementation plan |
| [`subagent-code-explorer.md`](/docs/prompts/subagent-code-explorer) | sub-agent recipe | Trace execution paths, map dependencies |
| [`subagent-code-reviewer.md`](/docs/prompts/subagent-code-reviewer) | sub-agent recipe | Confidence-filtered review |
| [`slash-goal.md`](/docs/prompts/slash-goal) | slash command | Set a session goal + stop hook |
| [`slash-loop.md`](/docs/prompts/slash-loop) | slash command | Schedule recurring or self-paced runs |
| [`slash-review.md`](/docs/prompts/slash-review) | slash command | Multi-agent PR review |
| [`slash-clear.md`](/docs/prompts/slash-clear) | slash command | Reset session context cleanly |
| [`slash-sanity.md`](/docs/prompts/slash-sanity) | slash command | Run cross-cutting sanity audit |
| [`slash-ship.md`](/docs/prompts/slash-ship) | slash command | Run release-gate checklist |

## Sub-agent strategy

When orchestrating long fan-outs, delegate to scoped specialists:

| Task | Sub-agent type | Model tier |
|---|---|---|
| File / symbol lookup | `explore` | haiku |
| Documentation, unit tests, code review | `plan` / `code-reviewer` | sonnet |
| Complex implementation needing deep reasoning | `implementer` | opus |

Tier by task complexity. Reserve opus for what truly needs it; haiku for trivial fan-outs.

## Slash-command discipline

- One command = one well-scoped workflow.
- The command body is a prompt template, not a script.
- Commands that side-effect (open PR, push, merge) require explicit user confirmation in their body.

## See also

- [`../pillars/ai-collaboration/README.md`](/docs/pillars/ai-collaboration)
- [`../templates/CLAUDE.md.template.md`](/docs/templates/CLAUDE.md.template) — bootstrap doc references these.