Autonomously drive vibix work end-to-end — pick an unblocked issue, plan it, implement, push a PR, resolve CI and review-bot feedback, merge when green, then repeat. Use when the user says "auto-engineer", "auto-pilot", "go run the loop", or invokes /auto-engineer.
Drive a large body of work end-to-end — either from a single scoping issue or a fuzzy topic ("ship GA", "harden the review app") — by discovering scope in the backlog + codebase, filing sub-issues, iterating with the user, planning parallel workstreams, then spawning /auto-engineer subagents to ship the whole epic…
File a new vibix GitHub issue with the correct priority/area/track labels applied up front. Use whenever an agent needs to capture a new unit of work — follow-ups from a merged PR, TODOs discovered while coding, or manually-requested issues. Invoked as /file-issue.
Given an OS topic, deeply research it from canonical sources, draft an RFC, run it through simulated peer review, defend it, merge when approved, then break the work into tracked issues. Use when the user says "research ", "write an RFC for ", or invokes /os-researcher .
Post a daily project report as a GitHub Discussion summarizing wins, issues, risks, and low-hanging fruit from the last 24h of commits and new issues in dburkart/vibix. On first invocation, schedules itself to run every 24h via CronCreate (auto-expires after 7 days). Use when the user invokes /project-report or asks…
The vibix software-delivery workflow — how changes move from idea to merged on main. Use when starting a milestone/task, committing, or opening/updating a PR.
Run vibix tests — host unit tests, in-kernel QEMU integration tests, or the end-to-end serial-marker smoke check. Use when the user asks to test, verify, check, or regression-test the kernel.
Report real Claude Code session-quota state — percent of the 5-hour and 7-day windows used, reset times, and status (ok/warning/rejected). Same numbers Claude Code's own statusline reports. Use when the user asks about usage, quota, rate limits, or when auto-engineer's quota gate calls /usage.
After opening a PR or pushing a fix, wait for all CI checks AND review-bot comments to report, then surface a single unified summary. Use immediately after gh pr create or any push that re-triggers checks on a PR.
Drive one vibix issue-to-PR cycle inside Cursor Cloud — pick an unblocked issue, plan the change, implement it, validate it, push a branch, and open or update a PR. Use when the user says "auto-engineer", "auto-pilot", "go run the loop", or invokes /cursor-cloud-auto-engineer.
Autonomously drive project work end-to-end — pick an unblocked issue, plan it, implement, push a PR, resolve CI and review-bot feedback, merge when green, then repeat. Use when the user says "auto-engineer", "auto-pilot", "go run the loop", or invokes /auto-engineer.
File a new GitHub issue with the correct priority and area labels applied up front. Use whenever an agent needs to capture a new unit of work — follow-ups from a merged PR, TODOs discovered while coding, or manually-requested issues. Invoked as /file-issue.
The project's software-delivery workflow — how changes move from idea to merged on main. Use when starting a new task, committing, or opening/updating a PR.
Seed the auto-engineer SDLC toolkit into a project. Asks for the target project path, detects the tech stack and GitHub configuration, collects any missing values interactively, then writes customized skill files and Docker infrastructure into that project. Use when the user says "seed a project", "set up…
Two-way sync between a seeded project and this auto-engineer repo's templates — covers skills, Dockerfile, and scripts. Detects drift in either direction, presents per-file diffs, and lets you pull from template, push to template, or skip. Harness-internal tool — never seeded into target projects. Invoked as /sync.
Report real Claude Code session-quota state — percent of the 5-hour and 7-day windows used, reset times, and status (ok/warning/rejected). Same numbers Claude Code's own statusline reports. Use when the user asks about usage, quota, rate limits, or when auto-engineer's quota gate calls /usage.
After opening a PR or pushing a fix, wait for all CI checks AND review-bot comments to report, then surface a single unified summary. Use immediately after gh pr create or any push that re-triggers checks on a PR.
Drive a large body of work end-to-end — either from a single scoping issue or a fuzzy topic ("ship GA", "harden the review app") — by discovering scope in the backlog + codebase, filing sub-issues, iterating with the user, planning parallel workstreams, then spawning /auto-engineer subagents to ship the whole epic…
Guidance on shrinking or fully resetting conversation context between auto-engineer iterations — when to use /compact (built-in summarise), /clear (built-in wipe), or a full process restart via scripts/restart-loop.sh.