Region

Coding Agents prompts

Instructions for autonomous coding agents.

6 prompts
Agents & Automation ⚙ AGENT

Autonomous Coding Agent Operating Rules

Operating instructions for autonomous coding agents (Claude Code, Devin-style): plan before touching files, small verified diffs, honest failure reporting.

✓ Claude Opus 4.5✓ Claude Sonnet 4.5
★ 172⧉ 1490◌ 0LLM Atlas Team · 3mo ago
Agents & Automation ⚙ AGENT

Coding Agent Task Briefing Template

A fill-in briefing template that gives a coding agent everything it needs to succeed: context, constraints, done-criteria, and verification commands.

Claude Sonnet 4.5
★ 61⧉ 480◌ 0LLM Atlas Team · 1mo ago
Agents & Automation ⚙ AGENT

Explore → Plan → Code → Verify Loop for Coding Agents

A phase-gated workflow prompt for coding agents: read before planning, plan before coding, verify before claiming done — with explicit rules for what each phase may and may not do.

✓ Claude Opus 4.5✓ Claude Sonnet 4.5
★ 45⧉ 328◌ 0LLM Atlas Team · 1mo ago
Agents & Automation ⚙ AGENT

Session Handoff — Context Compaction Summary

Compresses a long working session into a handoff document a fresh agent can continue from — decisions with their reasons, failed approaches preserved, exact next commands.

✓ Claude Sonnet 4.5Claude Haiku 4.5
★ 41⧉ 296◌ 0LLM Atlas Team · 1mo ago
Agents & Automation ⚙ AGENT

Orchestrator — Subagent Task Decomposition & Briefs

For lead agents delegating to subagents: decomposes work into genuinely parallel subtasks and writes briefs with objective, boundaries, output contract, and stop conditions — the parts that prevent duplicate and divergent work.

GPT-5Claude Opus 4.5
★ 36⧉ 254◌ 0LLM Atlas Team · 1mo ago
Agents & Automation ⚙ AGENT

Agent Self-Review Before Handoff

A pre-handoff checklist a coding agent runs against its own diff: evidence for every claim, hunk-by-hunk re-read, leftover-debris sweep, and a claims-vs-evidence table in the report.

GPT-5Claude Sonnet 4.5
★ 32⧉ 231◌ 0LLM Atlas Team · 1mo ago
LLM Atlas

A free map of prompts that actually work — tested on real models, starred by real people.

© 2026 LLM AtlasPrompts default to CC0 unless stated.