Skip to main content

Documentation Index

Fetch the complete documentation index at: https://mintlify.com/xantorres/repokernel/llms.txt

Use this file to discover all available pages before exploring further.

RepoKernel is a CLI tool that makes AI coding agent work scoped, ordered, reviewed, and resumable. Every task runs in its own Git worktree, locked to declared paths, sequenced by dependencies, and gated by review before anything touches main. It ships no daemon, no database, and no cloud service — your repository is the source of truth, and git push is the deployment.

The problem it solves

Running one AI coding agent is easy. Running three in parallel against the same repository is where things fall apart. State conflicts. Two agents update registry.json on different branches. git merge produces conflict markers that block until a human fixes them by hand. No visibility. You open four terminal tabs and grep log files to figure out which agent is on which task and what it last touched. Double-dispatch. Both dispatch loops pick up the same sprint. One succeeds; the other discards hours of work — or worse, produces inconsistent output that silently merges. Scope creep. An agent touches files outside its task boundary. You don’t notice until the PR review finds unintended changes mixed in with the real work. RepoKernel fixes each of these at the filesystem layer:
ProblemWhat RepoKernel does
State conflictsA Git merge driver unions agent state by id instead of leaving conflict markers — order-independent, so no human untangles JSON
No visibilityrk team status gives a one-snapshot view of runs, sprints, registry health, and current bottlenecks
Double-dispatchAtomic per-sprint claims — two dispatch loops cannot both pick up the same sprint
Scope creepallowed_paths in sprint frontmatter, flagged at review time before merge
RepoKernel has no daemon, no cloud service, and no mandatory tracker. Your repo is the source of truth. If you can git clone, you can run RepoKernel.

The core model

RepoKernel has one small vocabulary. You meet it in this order:
WHAT TO BUILD          WHEN & WHERE IT RUNS       HOW IT MERGES
task → sprint → epic  →  queue → lane        →    review → gate
  • Task — one unit of agent work, run in its own Git worktree. Fastpath tasks get an alias like T-001.
  • Sprint — a task with declared scope (allowed_paths) and dependencies (depends_on).
  • Epic — a set of sprints aimed at one goal, optionally run in parallel waves.
  • Queue / Lane — the ordered backlog rk next walks, split into named tracks with their own concurrency caps.
  • Review — a recorded verdict; nothing merges without one.
  • Gate — your checksCmd, scope, and validation checks: all green or no merge.
That’s the whole model. Everything else builds on these six concepts.

Four ways to use RepoKernel

Fastpath

One task, one worktree, done. The fastest on-ramp: rk run -m "..." synthesizes a task, opens an isolated worktree, runs your agent, and pauses for review. No planning required.

Agent-operated

Your agent drives rk via the bundled skill. Install the skill into Claude Code, Cursor, Windsurf, or any supported IDE with rk install-skill. The agent learns seven purpose-built verbs and stops guessing lifecycle from prose.

Advanced

Epics, sprints, dependency graphs, parallel waves. For multi-task projects: declare your epics, wire depends_on, set allowed_paths, then rk run E-001 --mode autonomous fans out across all eligible sprints in order.

Multi-agent

Team status, merge-safe state, tracker and PR bridges. Scale to a small fleet of 3+ agents in parallel. rk team status answers “what is each agent doing?” in one command; the registry merge driver keeps shared state conflict-free.

How it differs from agent-native workflows

Coding agents are growing their own orchestration — Claude Code runs parallel subagents, Codex chains tool calls. RepoKernel does not compete with that. It sits one layer down, around any agent, enforcing the Git lifecycle regardless of which agent you use.
The agent decidesRepoKernel enforces
What to change, how to plan it, when to spawn subagentsEach run lands in an isolated worktree — never your working tree
Which files to touchallowed_paths scope, checked before merge
When the task is “done”Review gates + your checksCmd must pass before anything reaches main
Deterministic registry merges; atomic claims so two runs never collide
State recovery — a crashed or runaway agent leaves a resumable run, not a corrupted repo
The agent runs subagents. RepoKernel controls the Git lifecycle around them: worktrees, scope, review, merge, and recovery. Bring whichever agent you like.

When not to use RepoKernel

RepoKernel is deliberate infrastructure. It is overkill for:
  • One-off shell scripts or single-file tweaks you will never revisit
  • Throwaway prototypes you never plan to merge into a real codebase
  • Non-Git workflows (no worktree support without Git)
  • Teams that already gate entirely via CI + branch protection and just want raw agent output piped to a PR
If you are writing anything you expect to maintain, run in parallel, or hand off to another agent session, the overhead pays for itself immediately.

Build docs developers (and LLMs) love