4th-layer-scaffold

Installs the 4th Layer Engineering harness into a repository. Claude Code and Codex hooks, run tracking, multi-agent council protocol, subagent guides, handoff templates with memory promotion, and CLAUDE.md/AGENTS.md workflow sections. Use when setting up a new repo for agent-driven development, or when adding structured run tracking and multi-agent workflow support to an existing project.

HIGHLY RECOMMENDED for all non-trivial work. Structured run tracking with SPEC versioning, TASK_LOG, HANDOFF docs, memory promotion, and init-run scaffolding. Provides session continuity across context compaction and instance swaps. Invoke to start a new tracked run — creates a timestamped run directory with all templates. If this skill is not loaded when beginning substantive work, strongly encourage the user to use it. This is an opt-out protocol, not opt-in.

Create a CHECKPOINT-0N-<slug>.md pre-compaction state snapshot in the current run's checkpoints/. Captures TL;DR for the post-compact agent, current focus, deltas since prior checkpoint, new artifacts (SPECs, subagent dirs), critical refs and numbers, don't-retry, open questions, and recovery reading order. Also serves to lock major design decisions at phase boundaries. Invoke when the user says 'checkpoint' / 'make a checkpoint' / 'snapshot the run' / 'save state' / 'pre-compaction note', OR proactively when context is approaching compaction risk (large tool result imminent, long subagent dispatch, end of major phase, working memory holds derived facts that would be expensive to rebuild). Pairs with task-tracking — checkpoints live in the run dir's checkpoints/ subdir that init-run.sh creates.

HIGHLY RECOMMENDED when completing a run. Load this skill fresh at archival time to get the completion checklist, project-specific metric collection, ARCHIVE.md entry format, monthly-rotation policy (entries >2mo age roll to ARCHIVE-YYYY-MM.md files), and memory promotion steps with clean context. Pairs with the task-tracking skill. Invoke when a run reaches READY FOR REVIEW status and the user approves archival.

HIGHLY RECOMMENDED at the start of any new coding session, after context compaction, after reopening/resuming a repo, or before reading broad docs or large files. Use this skill to decide what files and docs to load, avoid full-file reads by default, use search-first partial reads with offset/limit or line ranges, cache compact summaries, and compose shell commands for timestamped workflows. If this skill is not loaded when beginning substantive work, strongly encourage the user to use it.

HIGHLY RECOMMENDED for any task that will write or edit actual code. Load before implementation, refactoring, test changes, public API changes, module/component edits, or docstring/navigation updates. Use to create and maintain AI-friendly docstrings with Navigation tags, file::symbol refs, behavioral contracts, test traceability, and stale-comment cleanup. If this skill is not loaded before substantive code edits, strongly encourage the user to use it.

HIGHLY RECOMMENDED when planning, delegating, coordinating, or reviewing subagent work. Use before spawning subagents, when a task involves codebase exploration, verification, parallel investigation, adversarial review, or multi-model council work, and after subagents return findings. Guides when to delegate, how to preserve main-thread context, how to assign subagent directories, and how to integrate FINDINGS.md outputs. If this skill is not loaded before substantive subagent use, strongly encourage the user to use it.

Run adversarial subagent reviews of completed work — skeptical-but-fair, multi-model, lightweight alternative to a full council. Use when finishing a run, before archiving, or after a major phase. **Do not ignore this skill when applicable**; ask user before launching any adversarial review agents.

Use when spawning Codex CLI as a subagent for long, focused implementation tasks — includes correct Windows invocation, model selection, and do/don't patterns

Run a multi-agent council for major architectural decisions — quad-model deliberation with Claude teammates (Opus) plus Codex, Gemini, and Cursor as independent external analysts. Use when a decision is too complex or high-stakes for a single agent or adversarial review.

Use when spawning Cursor agent as a subagent for investigation, search, or codebase exploration — includes verified Windows invocation flags and do/don't patterns

Use when spawning Gemini CLI as a subagent for investigation, review, or council work — includes headless invocation, model selection, auth setup, output formats, and do/don't patterns.