Breadcrumb

What it does

The Breadcrumb skill structures handoffs for multi-iteration agent work. It instructs an agent to read a breadcrumb directory (readme.md plus previous NNN-progress.md files), make progress on the task autonomously, and write a new numbered progress file capturing what was done, remaining work, and important context. This guarantees a durable, machine-detectable trail so subsequent agents can resume without lost context.

When to use it

Use Breadcrumb when a task is too large or uncertain to finish in one run and requires iterative progress across multiple agents or sessions. Typical scenarios: long refactors, research tasks, multi-step content creation, or multi-agent orchestration where state must be preserved between runs.

What's included

• Scripts: none bundled with the skill (has_scripts=false)
• References: none listed (has_references=false)
• Instructions: clear procedural guidance on how to orient (read readme and prior progress files), what to record in the new progress file (Done, Remaining, Context), and the exact filename and formatting conventions. It emphasizes committing changes and not signaling completion unless all acceptance criteria are met.

Compatible agents

Agents that can read and write repository files and commit changes (code-aware assistants, repo-integrated agents). This skill is repo-agnostic and focuses on process rather than specific tooling.