Command Claude CodeOpenCode
Analyze tasks landed since the last release and create one documentation task covering website docs gaps.
not rated 8 today A 17 tokens
Command Claude CodeOpenCode
Explain files in the project: functionality, usage examples, and code evolution history traced through aitasks.
not rated 8 today A 20 tokens
Command Claude CodeOpenCode
Explore the codebase interactively, then create a task for implementation.
not rated 8 today A 14 tokens
aitask-fold
52Command Claude CodeOpenCode
Identify and merge related tasks into a single task, then optionally execute it.
not rated 8 today A 15 tokens
Command Claude CodeOpenCode
Procedure-backed verifier for the docsupdated gate — inspects a task's change, updates the project's documentation per the configured doc-update spec (confirming with the user), and records the gate result. Run by the attended agent (task-workflow / aitask-resume), not the headless engine.
not rated 8 today A 62 tokens
Command Claude CodeOpenCode
Scaffold for authoring a new gate verifier. Documents the orchestrator's verifier contract (positional args, exit codes, sidecar log, ledger append) and provides a copy-me script template.
not rated 8 today A 40 tokens
Command Claude CodeOpenCode
Learn a new skill from sources — a local file, a URL, a repo file/dir, or a tmux pane (capturing the workflow an agent just ran) — and generate a complete static SKILL.md.
not rated 8 today A 45 tokens
aitask-pick
56Command Claude CodeOpenCode
Select the next AI task for implementation from the aitasks/ directory.
not rated 8 today A 14 tokens
Command Claude CodeOpenCode
Pick and implement a task in remote/non-interactive mode. All decisions from execution profile - no AskUserQuestion calls.
not rated 8 today A 24 tokens
Command Claude CodeOpenCode
Pick and implement a task on Claude Code Web. Zero interactive prompts. No cross-branch operations — stores task data locally in .aitask-data-updated/.
not rated 8 today A 32 tokens
Command Claude CodeOpenCode
Create an aitask from a pull request by analyzing PR data and generating a structured task with implementation plan.
not rated 8 today A 21 tokens
aitask-qa
60Command Claude CodeOpenCode
Run QA analysis on any task — analyze changes, discover test gaps, run tests, and create follow-up test tasks.
not rated 8 today A 23 tokens
Command Claude CodeOpenCode
Research latest AI code agent models via web and update models.json configuration files.
not rated 8 today A 17 tokens
Command Claude CodeOpenCode
Resume an in-flight task from its gate-ledger checkpoint (programmatic re-entry surface for testing / TUI / board ops).
not rated 8 today A 26 tokens
Command Claude CodeOpenCode
Revert changes associated with completed tasks — fully or partially.
not rated 8 today A 11 tokens
Command Claude CodeOpenCode
Review code using configurable review guides, then create tasks from findings.
not rated 8 today A 13 tokens
Command Claude CodeOpenCode
Classify a review guide file by assigning metadata and finding similar existing guides.
not rated 8 today A 15 tokens
Command Claude CodeOpenCode
Import external content (file, URL, or repository directory) as a reviewguide with proper metadata.
not rated 8 today A 20 tokens
Command Claude CodeOpenCode
Compare two similar review guide files and merge, split, or keep separate.
not rated 8 today A 15 tokens
Command Claude CodeOpenCode
Run a task's declared gates — the conversational front of the headless gate orchestrator engine. Dispatches unlocked machine-gate verifiers within their retry budgets, observes human gates without self-signalling, and reports.
not rated 8 today A 43 tokens
Command Claude CodeOpenCode
Shadow companion for a followed coding agent — reads its captured terminal output and, in one instruction-driven flow, explains it, helps answer an AskUserQuestion, or critically interrogates a plan. Advisory-only. Spawned by minimonitor; not a task-implementation command.
not rated 8 today A 55 tokens
aitask-stats
70Command Claude CodeOpenCode
Calculate and display statistics of AI task completions (daily, global, per-label).
not rated 8 today A 17 tokens
aitask-trail
71Command Claude CodeOpenCode
Create, refresh, or show an implementation trail — a durable, wave-structured, evidence-backed task-sequencing artifact stored via ait artifact.
not rated 8 today A 29 tokens
Command Claude CodeOpenCode
Merge completed Claude Web branches to main and archive task data.
not rated 8 today A 12 tokens
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: