aram-devdocs

Pick the fastest build/verify command for the change at hand, from cargo check to the full verify gate

Run and troubleshoot the SDK code generation pipeline (./codegen.sh) and the generated-artifact drift gate

How versioning and releases work via release-please, version.txt, and the version pins across the workspace

Build and debug the WASM browser target and the TypeScript web SDK, including the wasm-pack path and the debugger WebSocket relay

Dependency flow audit and layer validation for GoudEngine's 5-layer hierarchy

Discover and list available skills in the repository

12-area audit checklist adapted for Rust game engine projects

Integration test patterns for Rust game engine with GL context and FFI boundaries

Drive one GitHub issue through the full self-driving lifecycle in an isolated worktree: investigate, plan, implement, verify, review, PR, wait for CI, and clean up. Every phase is gated and every state transition goes through the gh_issue_run.py state machine, never a hand edit. Dispatches the implementer and the four review subagents; does not merge its own PR.

The top-level self-driving loop. Orients against repo and run state, resumes an active run or selects the highest-priority unblocked GitHub issue, routes large issues through /gh-runbook and the rest straight to /gh-issue, drives the issue to a green PR against dev through gated subagent phases, mirrors the review locally with /gh-review, records lessons, and squash-merges only after rechecking the completed run and current GitHub state. One issue per invocation.

A local pull-request review that mirrors the CI review criteria so self-review and CI cannot drift: build, lint, tests, architecture, and the leak scan, run through the same scripts CI runs. Works on a PR number or on the local diff dev...HEAD. Sorts the diff into file buckets and ends with exactly one verdict.

Turn an audit, a scope, or a large issue into a parent runbook plus a set of grouped child issues. Produces a plan and a child-issue manifest (title, body, labels, milestone, blocked-by), then creates them with a script that dry-runs by default and only writes to GitHub when --apply is passed. Feeds /work.

Save and restore run state across a context compaction. Maintains a MEMORY.md whiteboard (current state, in progress, next, decisions, blockers) capped at 200 lines under the active run directory. Documents the protocol the save-session (PreCompact) and context-loader (SessionStart) hooks already run.

The in-session delegation engine /work uses to implement. One fresh subagent per task, parallel batches for independent tasks with disjoint file ownership dispatched in one message, and the fixed review order spec then quality then architecture then security. The orchestrator delegates and never implements.

List the skills available in this repository. Reads every .agents/skills/*/SKILL.md, extracts its name and description, and prints a compact index so an agent can pick the right skill before acting.

Strip AI-tell patterns from prose before it lands in docs or PR text. A catalog of the words, punctuation, and sentence shapes that mark machine writing, each paired with the fix. Run it over any markdown you wrote.

Strict issue-to-PR lifecycle for GitHub issues in the Plumb Rust workspace. Investigates, plans, implements (TDD), verifies, reviews, creates PR, waits for CI, and cleans up. Supports worktree isolation and durable run state for session resumption.

Convert a Plumb runbook spec (YAML) into a parent tracking issue plus grouped child workstream issues organized into sequential batches with phase gates. Generates markdown drafts and an idempotent `gh issue create` script; never creates GitHub issues without explicit approval.

Local PR review workflow for the Plumb Rust workspace. Mirrors .github/workflows/claude-code-review.yml, reviews a PR number or local diff, classifies changed files by crate, applies Plumb's Rust blocker and warning taxonomy, and drafts a structured markdown review body before optionally posting it.

Execute implementation plans in Plumb via fresh subagents per task, parallel batches for independent work, and a 4-gate review chain (spec → code-quality → architecture → test). Use when a plan has multiple independent tasks and you want to stay in this session.