Reviews a PR, diff, plan or skill with 2–3 models from different providers working blind and independently, and surfaces only the findings they agree on or that survive a contradiction-first proof; a precision mode runs one automated reviewer that posts at most two proven findings and stays silent otherwise. Use when asked to "review this with opus, codex and gemini", "rubber duck this plan", "second opinion", "only show me issues the models agree on", when a plan is about to drive a day or more of work, when work has been stuck for hours, or when setting up review-on-ready automation.
27919d agoReviewMountCreate a free account to mount
Runs many single-hypothesis "arms" as do-not-merge PRs, measures each with paired, interleaved runs against a cost-matched control, keeps only the arms that clear a keep bar set in advance, records every negative, and composes the winners into a stack that is re-measured on real traffic after merge. It opens PRs and burns CI, so it runs only on `/lever arms` or an explicit ask to measure ideas ("which of these ideas actually helps?", "is this change worth it?", "try that tip I saw", "run arms on this") for a CI, perf, eval, benchmark or cost hill-climb where the system can be run on demand.
27919d agoReviewMountCreate a free account to mount
Before iterating on a speedup or quality problem, build the feedback loop first and write it down as a Loop Card that names the outcome, the instrument the agent runs itself, the noise floor, the keep bar and the stop rule. Use on `/lever loop`, when asked to speed up, optimize, hill-climb or "make X better" against something measurable, and when a loop smell shows up mid-task: the user has pasted two or more screenshots or numbers, "still broken" has come up twice, the agent said "please try it" without running it, someone claims a win from one run, or the human is acting as the instrument. Not for one-shot fixes that existing tests already prove.
27919d agoReviewMountCreate a free account to mount
Backlog steward that keeps a pool of ready, independently mergeable issues above a target by mining real sources (failing tests, TODOs, gaps, audits, user reports), deduplicating, sizing and labeling them ready. It files issues, so it runs only on `/lever backlog`, inside a delivery run whose idle policy is refill, on a schedule the user set up, or on an explicit ask ("file more issues", "keep them busy", "fill the backlog", "we have nothing to do").
27919d agoReviewMountCreate a free account to mount
Turns a set of open PRs into a merge plan. It maps their dependencies, puts the PRs into merge-queue batches with strict order only where they overlap, and writes a hand-off with evidence for each PR. At L2 it gives the plan to the human who will merge; at L4 it enqueues the PRs itself. It can enqueue, so it runs only on `/lever land`, a hand-off from a lever coordinator, or an explicit ask ("what order should these merge in", "land the stack", "why is landing taking all day").
27919d agoReviewMountCreate a free account to mount
The one lever command. `/lever <verb> [args]` runs a lever skill directly (loop, arms, review, brief, deliver, refactor, backlog, shepherd, land, status, automate, health, mirror, steer, autonomy, spend, setup, help). `/lever <plain words>` picks the verb for you, says which in one line, then runs it. Also reads and writes the user's personal dials in `~/.copilot/lever.yml`. Use when the user types /lever, asks "which lever skill should I use?", or wants to see or change their autonomy or spend dial.
27919d agoReviewMountCreate a free account to mount
Pushes progress on long-running or delegated work so the human never has to poll. It publishes milestones with ETAs and the evidence each needs, sends reports only when something meaningful changed, labels every claim with an evidence level, logs ETA accuracy, watches time since last merge, and audits "done" against evidence before declaring it. Use for any delegated, multi-hour or overnight run, when a brief sets a report contract, or when the user asks "status?", "ETA?", "where are we?", "what happened overnight?", "hour by hour" or "are you done?".
27919d agoReviewMountCreate a free account to mount
Drives an open pull request to landed through an event-driven loop. On each wake it does one batched read, fixes root causes of red required checks, dispositions every review thread, and lands at the level set by the autonomy dial. It pushes and can merge, so it runs only on `/lever shepherd`, a hand-off from a lever coordinator, a PR labeled for shepherding, or an explicit ask ("monitor CI until green", "push fixes until green", "resolve the review threads", "merge when green", "babysit this PR", "shepherd #123").
27919d agoReviewMountCreate a free account to mount
Runs a huge, mechanical refactor (crate or package splits, module extraction, API migrations, dead-code removal) as three independent lanes, producer, packager and shepherd, that coordinate only through git and a PR stack. It pushes branches and opens PRs, so it runs only on `/lever refactor` or an explicit ask ("split this crate", "break up this monolith", "this module is huge, cut it down", "migrate every caller").
27919d agoReviewMountCreate a free account to mount
Stall watchdog and automation health review. Pulls recent runs, merges, no-op rate, failures, rate-limit hits and stuck PRs; classifies each stall; proposes exactly one change or "no change"; and takes over orphaned work. Use when unattended delivery stalled ("why did it stall overnight", "no merges in N hours", "it was fast the first few days, now slow"), when an automation fails or its output drops, when rate limits or quotas are hit, or on a schedule while agents run unattended.
27919d agoReviewMountCreate a free account to mount
Turn a correction you keep repeating into a durable fix: mine your corrections, classify them, choose the cheapest layer that would have prevented them (instruction, skill, lint/CI check, test, automation, or product bug report), open a PR with an evidence block, then re-measure after K days and keep, escalate or revert. Opens PRs, so it runs only on `/lever steer` or an explicit ask ("mine my corrections", "why do I keep telling you X", "didn't I give you a skill for this"), or when prompt-mirror reports the same correction class in 3+ sessions and you say go.
27919d agoReviewMountCreate a free account to mount
Replica contains the self-hosted Hub, selectable prototype starters, and the shared prototype build action. Read Contributing and the shared documentation index, then read the affected project's instructions and guides before editing. Keep shared rules in root guides and project-specific rules in the affected project. Do not apply Hub's Rails, Primer, or devcontainer requirements to the starter, build action, or shared packages. The starter's copied instructions must remain usable without this monorepo. Follow the commit and PR conventions and the repository's…
23023d agoReviewMountCreate a free account to mount
Implements a captured Pick & polish batch from the Replica prototype canvas. Use for Fix all requests with verified checkout, branch, batchId and noteCount, including pending follow-ups.
23023d agoReviewMountCreate a free account to mount
Publishes a Replica prototype through its existing workflow and Hub Build. Use for prototype canvas publishing requests that include verified target JSON and a publishing mode.
23023d agoReviewMountCreate a free account to mount
Review Replica pull requests using the same shared conventions and project guides as implementation agents. Use when reviewing changes to code, tests, workflows, or documentation in this repository.
Replica Hub is a self-hosted Rails application where teams review prototype branches. GitHub owns source code and repository access. Hub stores Builds and review data. Prototype code runs on isolated preview origins. Read the root instructions and shared guides, then the Hub documentation index and guides for the work:
23023d agoReviewMountCreate a free account to mount
Read the shared Replica instructions before prototype work. They own task scope, component preflight, canvas setup, publishing and browser validation. This file and the CoreAI skills own app-specific conventions. The CoreAI Prototype is a React Router single-page app for exploring agent and design-system experiences with local mock data. Run commands from this app's directory: The app runs at <http://127.0.0.1:5174>. Vitest runs hook tests in jsdom with React Testing Library. Keep the chat hook real and use simulated timers to test…
23023d agoReviewMountCreate a free account to mount
Plain text files in a repository that tell a coding agent how the project works: commands to run, conventions to follow and things to avoid. CLAUDE.md, AGENTS.md, cursor rules and skills are the common kinds.
CLAUDE.md or AGENTS.md?
CLAUDE.md is read by Claude Code. AGENTS.md is an open format that Codex, Cursor and other agents read. Many projects keep one and point the other at it.
What is a skill?
A folder with a SKILL.md that describes one capability, such as filling PDFs or reviewing code. The agent loads it only when the task calls for it.
Can I search my own team's files too?
Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.
GitHubSkill