lever

Plugin lever from marketplace nicholls in nicholls-inc/claude-code-marketplace. Commands read from the repo's manifest — yesterday.

Skills (16)

• automate-it

  Turns a task you keep doing by hand into a paused automation, as a plain GitHub Actions workflow for deterministic jobs, or for LLM-driven jobs a GitHub Actions workflow running anthropics/claude-code-action or a Claude Code cloud routine (/schedule), with an event trigger, least-privilege permissio

• autonomous-delivery

  Runs long-lived delivery as a coordinator with parallel lanes. Sets authority and pacing dials up front, keeps lanes alive and fed, lands work through a single-writer release train, and reports status only when something changed. Runs only on `/lever deliver`, "/autonomous-delivery" or an explicit r

• autonomy-dial

  Resolves how far an agent may take a change, from L0 propose to L5 release. It reads the repo's real GitHub rules (rulesets, branch protection, CODEOWNERS, merge queue) and `.github/lever.yml`, applies per-path and per-class limits, records every grant verbatim with its source and expiry, and expose

• brief

  Turns a short intent, often around 20 words, into a brief that can run unattended. The brief has the user's words verbatim, an outcome owner, an observable done-when, a feedback loop, constraints and neighbors, a budget, an autonomy level, an absence window, stop conditions and a report contract. Ru

• cross-model-review

  Reviews a PR, diff, plan or skill with 2–3 models (different Claude tiers, plus another provider's CLI when installed) 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

• experiment-arms

  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.

• find-the-loop

  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

• keep-the-pool-full

  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 p

• landing-plan

  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 enque

• lever

  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 i

• pr-shepherd

  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 han

• progress-contract

  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 audi

• prompt-mirror

  Mine your own local Claude Code session history and return a scorecard of how you direct agents, plus three suggestions illustrated with your own before/after messages. It reads your private history, so it runs only on `/lever mirror` or an explicit ask ("how am I prompting?", "coach me", "mine my s

• refactor-pipeline

  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

• run-health-review

  Stall watchdog and automation health review (lever-* GitHub Actions workflows plus Claude Code sessions and loops). 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 whe

• steer-once

  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 kee

Subagents (1)

• blind-reviewer

  One blind seat on a cross-model review panel. Receives a review packet (a diff with context, or a plan with its Loop Card) and returns defects as JSON lines, or objections for a plan. Never sees other reviewers' output. Read-only. Used by the cross-model-review skill; the caller sets a different mod

Similar plugins