# Long Horizon Prompting

Should be used when writing, enhancing, or evaluating the launch prompt for a...

- Repository: https://github.com/muratcankoylan/Agent-Skills-for-Context-Engineering (18272 stars)
- Category: Design
- License: MIT
- Last updated: 2026-10-12
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add muratcankoylan/Agent-Skills-for-Context-Engineering --skill long-horizon-prompting -g -a claude-code -y`
Codex: `npx skills add muratcankoylan/Agent-Skills-for-Context-Engineering --skill long-horizon-prompting -g -a codex -y`
Cursor: `npx skills add muratcankoylan/Agent-Skills-for-Context-Engineering --skill long-horizon-prompting -g -a cursor -y`
Gemini CLI: `npx skills add muratcankoylan/Agent-Skills-for-Context-Engineering --skill long-horizon-prompting -g -a gemini-cli -y`
Claude Code plugin marketplace: `/plugin marketplace add muratcankoylan/Agent-Skills-for-Context-Engineering`

## Description

This skill should be used when writing, enhancing, or evaluating the launch prompt for a long-running autonomous agent or a parallel multi-agent orchestration attacking a hard problem: pseudo-formal task briefs that define terms and an exact success predicate linguistically, enumerate non-counting outcomes, set persistence rules with explicit stop and return conditions and effort floors, manage a diverse portfolio of parallel approaches with an approach registry and blocked-route bookkeeping, and gate the return on adversarial audit. Route agent topology and coordination protocols to multi-agent-patterns, runtime control surfaces and loop governance to harness-engineering, evaluator and quality-gate construction to evaluation, judge design to advanced-evaluation, and compaction or memory mechanics to context-compression and memory-systems.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# Long-Horizon Prompting

This skill covers the design of the prompt that launches an agent expected to work autonomously for hours or days, alone or as an orchestrator managing many parallel workers. The central technique is the pseudo-formal task brief: a specification written with the rigor of formal verification but expressed linguistically, because most hard problems have no machine-checkable success condition. The exemplar is the published prompt behind GPT-5.6 Sol Ultra's candidate proof of the Cycle Double Cover Conjecture, produced by a 64-subagent orchestration (claim-long-horizon-cdc-run). The prompt structure generalizes far beyond mathematics: any domain where success can be stated precisely and failure modes can be enumerated can use the same brief anatomy. In orchestrated runs the same discipline applies at every handoff: when a model optimized its own multi-agent workflow text in Sakana AI's MASS work, task information moved out of worker roles and into output contracts and call order (claim-long-horizon-contract-information-shift).

The controlling trade-off: everything that makes a long run productive (persistence, autonomy, parallelism) also raises the cost of a weak specification. A short interactive prompt fails cheaply; a long-horizon brief with a loophole burns hours of compute producing an answer-shaped artifact that does not solve the problem.

## When to Activate

Activate this skill when:

The rest: https://github.com/muratcankoylan/Agent-Skills-for-Context-Engineering/blob/HEAD/skills/long-horizon-prompting/SKILL.md