aitasks

Create, refresh, or show an implementation trail — a durable, wave-structured, evidence-backed task-sequencing artifact stored via ait artifact.

Create, refresh, or show an implementation trail — a durable, wave-structured, evidence-backed task-sequencing artifact stored via ait artifact.

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.

Draft a manager-facing work report from selected board columns.

Pick and implement a task in remote/non-interactive mode. All decisions from execution profile - no AskUserQuestion calls.

Pick and implement a task on Claude Code Web. Zero interactive prompts. No cross-branch operations — stores task data locally in .aitask-data-updated/.

Pick and implement a task in remote/non-interactive mode. All decisions from execution profile - no AskUserQuestion calls.

Pick and implement a task in remote/non-interactive mode. All decisions from execution profile - no AskUserQuestion calls.

Pick and implement a task on Claude Code Web. Zero interactive prompts. No cross-branch operations — stores task data locally in .aitask-data-updated/.

Pick and implement a task on Claude Code Web. Zero interactive prompts. No cross-branch operations — stores task data locally in .aitask-data-updated/.

Merge completed Claude Web branches to main and archive task data.

Pick and implement a task in remote/non-interactive mode. All decisions from execution profile - no AskUserQuestion calls.

Pick and implement a task on Claude Code Web. Zero interactive prompts. No cross-branch operations — stores task data locally in .aitask-data-updated/.

Draft a manager-facing work report from selected board columns.

Draft a manager-facing work report from selected board columns.

Procedure-backed verifier for the `docs_updated` 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.

Shared implementation workflow for task-based skills, with profile-check sites wrapped in Jinja conditionals.

Shared implementation workflow for task-based skills, with profile-check sites wrapped in Jinja conditionals.

Explore the codebase interactively, then create a task for implementation.

Chat-native explore flow for a bug report — machine-spawned by the chatlink gateway, every decision routed through the file-spool Q&A relay instead of AskUserQuestion, ending in a task-creation payload.json. Not a user task command.

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.

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.

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.

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.

Run QA analysis on any task — analyze changes, discover test gaps, run tests, and create follow-up test tasks

Review code using configurable review guides, then create tasks from findings.

Create a new AI task file with automatic numbering and proper metadata. Supports interactive agent prompts, terminal fzf, and batch mode.

Resume an in-flight task from its gate-ledger checkpoint (programmatic re-entry surface for testing / TUI / board ops).

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.

Select the next AI task for implementation from the `aitasks/` directory.

Resume an in-flight task from its gate-ledger checkpoint (programmatic re-entry surface for testing / TUI / board ops).

Resume an in-flight task from its gate-ledger checkpoint (programmatic re-entry surface for testing / TUI / board ops).

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.

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.

Register a known code-agent model in models_<agent>.json, optionally promote it to default across config/seed/DEFAULT_AGENT_STRING.

Audit and port aitask skill wrappers across code-agent trees, plus helper-script whitelist coverage.

Research latest AI code agent models via web and update models_*.json configuration files.

Register a known code-agent model in models_<agent>.json, optionally promote it to default across config/seed/DEFAULT_AGENT_STRING.

Audit and port aitask skill wrappers across code-agent trees, plus helper-script whitelist coverage.

Generate a changelog entry by analyzing commits and archived plans since the last release.