dispatch-cli-agent
Dispatch prompts to external CLI agents and collect results.
Supported CLIs
| CLI | Command | Output | Reference |
|---|---|---|---|
| Claude Code | claude -p "prompt" --output-format json |
JSON (result, session_id, usage) |
claude-code.md |
| Codex CLI | codex exec "prompt" --json |
JSONL events | codex-cli.md |
| Gemini CLI | gemini -p "prompt" |
Plain text (recommended; --output-format json may not print to stdout) |
gemini-cli.md |
| Copilot CLI | copilot -p "prompt" -s |
Plain text (silent mode) | copilot-cli.md |
Dispatch Workflow
1. Write the prompt file
Write the prompt to .dispatch/<cli>-<timestamp>.md so it's inspectable and replayable.
More from wiseiodev/skills
code-principles
Software engineering principles for code review, planning validation, and learning. Covers SOLID, DRY, YAGNI, design heuristics, testing, API design, architecture patterns, and React best practices. Use when reviewing code, validating plans/specs, injecting review criteria into council sessions, or when user asks about a specific principle. Triggers on "principles", "code review checklist", "SOLID", "DRY", "design heuristics", "review criteria", "best practices", or any named principle like "Law of Demeter", "Liskov", "YAGNI", etc.
11gt
Create Graphite stacked PRs from staged git changes. Use when user says "/gt", "create a PR", "submit PR", or wants to commit and create a pull request using Graphite. Optionally accepts a Linear issue ID (e.g., "/gt A-35") to auto-close issues on merge.
4graphite
Comprehensive Graphite CLI for stacked PRs. Triggers on stack management, gt commands, rebasing/syncing, branch navigation (up/down/top/bottom), merge conflicts, reorganizing branches, recovery (undo/abort), teammate stacks. For simple PR creation, use gt skill instead.
3review-council
Send a document (plan, spec, PRD, ADR, code) to a review council of 2+ AI agents (Claude Code + Codex CLI by default, optionally Gemini CLI and Copilot CLI) for independent parallel review. Synthesizes feedback, auto-revises the document, and re-reviews if council members had high variance. Use when wanting multi-agent review, "review council", peer review from multiple AIs, or validating plans/specs/code before finalizing.
3work-log
Log accomplishments, solved problems, learnings, and milestones to Obsidian daily notes via the Obsidian CLI. Also answers questions about the Obsidian CLI. Triggers on "/log", "log accomplishment", "log what I did", "work log", "obsidian cli", "daily note", or when user wants to record something noteworthy they did.
1adversarial-review
Run a multi-round adversarial code review with two independent AI reviewers that cross-examine each other's findings. Iterates until only nitpicks remain (max 3 rounds). Use when you want deep, debate-style review that catches issues a single pass misses. Triggers on "adversarial review", "debate review", "cross-review", "deep review".
1