codex-lane
Operate Claude Lane Stack schema-v2 runs from Codex. Use for lane status, start, resume, review, verification, evidence, or…
Bounded Codex Lane writer protocol for one assigned task. Use only when the lane runtime assigns this worker.
$ npx -y skills add VKirill/claude-lane-stack --skill codex-lane-worker --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/codex-lane-workerContext preview
The summary Claude sees to decide when to auto-load this skill.
Bounded Codex Lane writer protocol for one assigned task. Use only when the lane runtime assigns this worker.
name: codex-lane-worker description: Bounded Codex Lane writer protocol for one assigned task. Use only when the lane runtime assigns this worker.
You are the writer for exactly one runtime task. The task YAML and runtime boundary are authoritative. Work only in `PROJECT_CWD` and only in `owns_paths`; honor `never_touch`. Read assigned skills and packet paths only.
Trace the assigned flow before editing. Reuse existing code, then stdlib/native features before adding code. Make the smallest root-cause change that meets all acceptance criteria; preserve validation, security, and accessibility. Resolve reversible details from project patterns; report consequential uncertainty as Gaps. Distinguish observed evidence from assumptions and unrun checks.
controller owns independent L1 verification.
The runtime supplies the task and prompt binding. When work is complete or blocked, report exactly one of these statuses: `complete`, `partial`, `timeout`, or `unavailable`. Include the changed paths, concrete evidence, worker checks (`none` / skipped), and any specific gap. Never invent a prompt digest or acceptance receipt.
Claude Lane Stack is a self-hosted toolkit for coordinating coding agents through CLI processes, task contracts, Git workspaces, and verification receipts (bin/run-controller:117-159, schemas/task-v2.schema.json:1-60).
Operate Claude Lane Stack schema-v2 runs from Codex. Use for lane status, start, resume, review, verification, evidence, or…
Детекция и коррекция AI-сгенерированного текста по методике DrMax LinguaForensic v3.9.4 (284 лингвистических признака + 16…
Owner-facing architect for a new app or service. Plain-language chat; living plan artifacts on disk. Use when user says…
Live browser QA + Playwright-compatible replay. Disk .agents/qa/. Use when (terminal Lane Stack): проверь в браузере, кликни…
Delegate fat file reads to the project's pm_read worker. Use when a Read/cat/head/tail/sed of a file over pm_read.min_lines was…
DrMax COCOON CHAINSMITH v3 — fills 9 YAML vars and emits a verified CP-Navigator command sequence for Cocoon Engine X4. Does not…