Prompt executor
Execute prompts from ./prompts/ directory with various AI models. Use when user asks to run a prompt, execute a task, delegate work to an AI model, run prompts in worktrees/tmux, or run prompts with verification loops.From its SKILL.md
npx -y skills add cruzanstx/daplug --skill prompt-executorAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 6 stars6 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
21.1 KB, as published. Nobody here has run it
Prompt Executor
Auto-Approval Setup
If the user has to manually confirm the executor bash command, suggest they add this rule to ~/.claude/settings.json under permissions.allow:
"Bash(PLUGIN_ROOT=$(jq -r '.plugins.\"daplug@cruzanstx\"[0].installPath' ~/.claude/plugins/installed_plugins.json):*)"
Quick command to add it:
# Add auto-approval rule for prompt executor
jq '.permissions.allow += ["Bash(PLUGIN_ROOT=$(jq -r '"'"'.plugins.\"daplug@cruzanstx\"[0].installPath'"'"' ~/.claude/plugins/installed_plugins.json):*)"]' ~/.claude/settings.json > /tmp/settings.json && mv /tmp/settings.json ~/.claude/settings.json
Execute prompts from ./prompts/ (including subfolders) using various AI models (Claude, Codex, Antigravity/Gemini, ZAI, etc).
When to Use This Skill
- User says "run prompt 123" or "execute prompt 123"
- User says "run that prompt with codex/agy/gemini/zai"
- User wants to "run a prompt in a worktree"
- User wants to "run prompts in parallel"
- User asks to "delegate this to codex/agy/gemini"
- User wants to "run with verification loop" or "keep retrying until complete"
- User asks to "check loop status" for a running prompt
Executor Script
IMPORTANT: Get the executor path from Claude's installed plugins manifest:
PLUGIN_ROOT=$(jq -r '.plugins."daplug@cruzanstx"[0].installPath' ~/.claude/plugins/installed_plugins.json)
EXECUTOR="$PLUGIN_ROOT/skills/prompt-executor/scripts/executor.py"
python3 "$EXECUTOR" [prompts...] [options]
Options:
<!-- BEGIN GENERATED: skill-model-options -->--model, -m: claude, cc-sonnet, cc-opus, fable, codex, codex-spark, codex-high, codex-xhigh, sol, terra, luna, gpt54, gpt54-high, gpt54-xhigh, gpt55, gpt55-high, gpt55-xhigh, gpt52, gpt52-high, gpt52-xhigh, gemini, gemini-high, gemini-xhigh, gemini25pro, gemini25flash, gemini25lite, gemini3flash, gemini3pro, gemini31pro, gemini37, gemini37-high, gemini37-medium, gemini37-low, agy, zai, glm5, glm52, glm53, kimi, synthetic, syn-flash, syn-kimi, syn-kimi3, syn-qwen, syn-minimax, syn-nemotron, opencode, local, qwen, devstral, glm-local, qwen-small, qwen36, qwen36-27bglm53: GLM-5.3 via Z.AI / OpenCode (1M context)synthetic: GLM-5.2 via Synthetic / OpenCode (syn:large:text, requiresSYNTHETIC_API_KEY)
--moa: Mixture-of-agents — comma-separated list of 2+ models (e.g.codex,synthetic,qwen36). Entries may carry a per-model CLI override asmodel:cli(e.g.codex:opencode). Each run gets its own worktree (implies--worktree); a manifest for the judge/consolidation phase is written to~/.claude/loop-state/moa/. Mutually exclusive with--modeland the global--cli; the bareclaudeTask-subagent shorthand is not allowed (usecc-sonnet,cc-opus, orclaude:claude).--cli: Override CLI wrapper (codex, opencode, claude, agy, or gemini; aliases: claudecode, cc, antigravity). Unsupported explicit combinations fail with a clear error (no silent fallback). Not allowed with--moa.--variant: Reasoning variant override (none|low|medium|high|xhigh). Explicit--variantoverrides alias defaults (codex-high,gpt55-high,gpt54-high,gpt52-high, etc.).--cwd, -c: Working directory for execution--run, -r: Actually run the CLI (default: just return info)--info-only, -i: Only return prompt info, no CLI details--worktree, -w: Create isolated git worktree for execution--sandbox: Enable sandboxing (Linux default backend: bubblewrap)--sandbox-type: Sandbox backend override (bubblewrap)--no-sandbox: Explicitly disable sandboxing--sandbox-profile: Isolation profile (strict|balanced|dev, defaultbalanced)--sandbox-workspace: Override sandbox workspace path (default: execution cwd)--sandbox-net: Network override (on|off; default comes from profile)
Sandbox Authentication & CLI-Scoped Binds
Bubblewrap sandboxes bind only the minimum host files each CLI needs to authenticate:
- Claude Code (
claude): read-only bind of~/.claude/.credentials.jsonand~/.claude.json; the rest of~/.claudestays outside the sandbox. Aclaude auth statuspreflight verifies the binds before real runs. - Antigravity (
agy/antigravity): read-only bind of~/.gemini/antigravity-cli/antigravity-oauth-tokenon top of a tmpfs for the parent directory, so only the token file is visible — conversations, databases, cache, and logs stay outside the sandbox. Anagy modelspreflight verifies the token works before real runs. - Other CLIs (
codex,gemini,opencode): authenticate via environment variables or API keys passed through--setenv; no host credential files are bound.
Writable tool-state binds are CLI-scoped (least privilege): opencode_state/opencode_cache/opencode_config are only bound for opencode children. workspace and tool_caches remain shared across all CLIs.
--base-branch, -b: Base branch for worktree (default: main)--on-conflict: How to handle existing worktree (error|remove|reuse|increment)--loop, -l: Enable iterative verification loop until completion--max-iterations: Max loop iterations before giving up (default: 3)--completion-marker: Text pattern signaling completion (default: VERIFICATION_COMPLETE)--require-diff: Reject completion marker when no file changes detected (created, modified, or committed) in the execution directory. Excludes TASK.md and .sisyphus/.--loop-status: Check status of an existing verification loop
Output: JSON with prompt content, CLI command, log path, worktree info, and loop state if enabled
Execution Flows
Direct Execution (default)
# Get executor path from installed plugins manifest
PLUGIN_ROOT=$(jq -r '.plugins."daplug@cruzanstx"[0].installPath' ~/.claude/plugins/installed_plugins.json)
EXECUTOR="$PLUGIN_ROOT/skills/prompt-executor/scripts/executor.py"
# Get prompt info
python3 "$EXECUTOR" 123 --model codex
# Force OpenCode path with reasoning variant
python3 "$EXECUTOR" 123 --model codex --cli opencode --variant high
# Folder-qualified prompt (resolves prompts/providers/011-*.md)
python3 "$EXECUTOR" providers/011 --model codex
# Run in current directory
python3 "$EXECUTOR" 123 --model codex --run
# Run in bubblewrap sandbox (Linux)
python3 "$EXECUTOR" 123 --model codex --run --sandbox
# Strict profile (no network by default)
python3 "$EXECUTOR" 123 --model codex --run --sandbox --sandbox-profile strict
# Explicit opt-out
python3 "$EXECUTOR" 123 --model codex --run --no-sandbox
With Worktree (built-in)
Single command creates worktree, copies TASK.md, and optionally runs:
# Create worktree and get info
python3 "$EXECUTOR" 123 --worktree --model codex
# Create worktree and run immediately
python3 "$EXECUTOR" 123 --worktree --model codex --run
# Use different base branch
python3 "$EXECUTOR" 123 --worktree --base-branch develop --model codex
The worktree directory is read from worktree_dir in <daplug_config> within CLAUDE.md (via config-reader), or defaults to ../worktrees/.
Mixture of Agents (--moa)
Run the same prompt with multiple models in parallel, one worktree per model, then judge and consolidate the results in the main session:
# 3 models, 3 worktrees, launched in parallel
python3 "$EXECUTOR" 123 --moa codex,synthetic,qwen36 --run
# With per-runner verification loops (state keyed as 123-moa-<label>)
python3 "$EXECUTOR" 123 --moa codex,glm5 --run --loop
# Per-entry CLI override: run the codex model through OpenCode
python3 "$EXECUTOR" 123 --moa codex:opencode,qwen36 --run
# Same model on two CLIs (distinct labels: codex, codex-opencode)
python3 "$EXECUTOR" 123 --moa codex,codex:opencode --run
Per-run info lands in prompts[].moa.runs[] (worktree, branch, log, state file, launch status); the same data is persisted as a manifest at ~/.claude/loop-state/moa/{N}-{timestamp}.json. One model failing to launch does not abort the other runs. --variant applies per model where supported and is dropped (with variant_dropped: true) where not. After all runs finish, compare diffs and test results across the worktrees, pick or synthesize a winner, and merge — see the run-prompt command's "Judge & Consolidation Phase".
With tmux (use tmux-manager skill)
- Get CLI command from executor:
python3 "$EXECUTOR" 123 --model codex
# Returns: {"cli_command": ["codex", "exec", "--full-auto"], "content": "...", "log": "..."}
- Create tmux session using tmux-manager patterns:
SESSION_NAME="prompt-123-$(date +%Y%m%d-%H%M%S)"
tmux new-session -d -s "$SESSION_NAME" -c "$WORKTREE_PATH"
- Send command to session:
tmux send-keys -t "$SESSION_NAME" "codex exec --full-auto '...' 2>&1 | tee $LOG_FILE" C-m
With Verification Loop
Run prompts with automatic retries until the task is verified complete:
# Run with verification loop (background, default 3 iterations)
python3 "$EXECUTOR" 123 --model codex --run --loop
# With custom max iterations
python3 "$EXECUTOR" 123 --model codex --run --loop --max-iterations 5
# With custom completion marker
python3 "$EXECUTOR" 123 --model codex --run --loop --completion-marker "TASK_DONE"
# Worktree + loop combo
python3 "$EXECUTOR" 123 --model codex --worktree --run --loop
# Require file changes before accepting completion (--require-diff)
python3 "$EXECUTOR" 123 --model codex --run --loop --require-diff
Output includes:
{
"execution": {
"status": "loop_running",
"pid": 12345,
"loop_log": "~/.claude/cli-logs/codex-123-loop-20251229-120000.log",
"state_file": "~/.claude/loop-state/123.json",
"max_iterations": 3,
"completion_marker": "VERIFICATION_COMPLETE"
}
}
Log paths follow cli_logs_dir from <daplug_config> if configured (default ~/.claude/cli-logs/).
Completion markers (required):
- To end the loop, the model must output a final-line verification tag:
<verification>VERIFICATION_COMPLETE</verification>. - To request another iteration, output:
<verification>NEEDS_RETRY: [reason]</verification>. - The executor ignores any markers that appear inside echoed prompt instructions (some CLIs print the full prompt into logs).
--require-diff (optional):
- When enabled, the completion marker is rejected if the execution directory has no file changes (created, modified, or committed since the loop started).
- Executor-injected artifacts (
TASK.md,.sisyphus/) are excluded from the diff. - A rejected completion injects a synthetic retry reason so the model sees why it was rejected and gets another chance.
- Terminal status on the final iteration with no diff:
completed_unverified(notcompleted).
Dead-loop detection (always on):
- Stalled: Two consecutive iterations with the same retry reason (case/whitespace-insensitive) → loop aborts with status
stalled. - Blocked: A retry reason matching impossible-gate patterns (references to paths outside the worktree, isolation-boundary refusals) → loop aborts immediately with status
blockedand a suggested next step.
Check Loop Status
# Check specific prompt's loop
python3 "$EXECUTOR" 123 --loop-status
# List all active loops
python3 "$EXECUTOR" --loop-status
Model Reference
<!-- BEGIN GENERATED: skill-model-reference -->| Model | CLI | Description |
|---|---|---|
| claude | (Task subagent) | Complex reasoning in current Claude Code context |
| cc-sonnet | claude --print --no-session-persistence --output-format text --input-format text --permission-mode dontAsk --model sonnet | Claude Code CLI Sonnet runs |
| cc-opus | claude --print --no-session-persistence --output-format text --input-format text --permission-mode dontAsk --model opus | Claude Code CLI Opus runs |
| fable | claude --print --no-session-persistence --output-format text --input-format text --permission-mode dontAsk --model fable | Claude Code CLI Fable 5 runs |
| codex | codex exec --full-auto -m gpt-5.6-terra | Fast coding execution (default Codex shorthand) |
| codex-spark | codex exec --full-auto -m gpt-5.3-codex-spark | Lowest-latency quick edits |
| codex-high | codex exec --full-auto -m gpt-5.6-terra -c model_reasoning_effort="high" | Complex coding |
| codex-xhigh | codex exec --full-auto -m gpt-5.6-terra -c model_reasoning_effort="xhigh" | Large refactors |
| sol | codex exec --full-auto -m gpt-5.6-sol | Hardest agentic coding tasks |
| terra | codex exec --full-auto -m gpt-5.6-terra | Balanced everyday coding (codex default) |
| luna | codex exec --full-auto -m gpt-5.6-luna | Fast, cost-efficient coding |
| gpt54 | codex exec --full-auto -m gpt-5.4 | Explicit GPT-5.4 shorthand |
| gpt54-high | codex exec --full-auto -m gpt-5.4 -c model_reasoning_effort="high" | Deep reasoning with GPT-5.4 |
| gpt54-xhigh | codex exec --full-auto -m gpt-5.4 -c model_reasoning_effort="xhigh" | Maximum reasoning with GPT-5.4 |
| gpt55 | codex exec --full-auto | Explicit GPT-5.5 shorthand |
| gpt55-high | codex exec --full-auto -c model_reasoning_effort="high" | Deep reasoning with GPT-5.5 |
| gpt55-xhigh | codex exec --full-auto -c model_reasoning_effort="xhigh" | Maximum reasoning with GPT-5.5 |
| gpt52 | codex exec --full-auto -m gpt-5.2 | Planning, research, analysis |
| gpt52-high | codex exec --full-auto -m gpt-5.2 -c model_reasoning_effort="high" | Deep reasoning |
| gpt52-xhigh | codex exec --full-auto -m gpt-5.2 -c model_reasoning_effort="xhigh" | Maximum reasoning (30+ min) |
| gemini | agy --model "Gemini 3.7 Flash (High)" --dangerously-skip-permissions --print-timeout 60m --output-format stream-json --print | Fast daily driver, high reasoning (default) |
| gemini-high | gemini -y -m gemini-2.5-pro | Stable, more capable |
| gemini-xhigh | gemini -y -m gemini-3-pro-preview | Most capable Gemini fallback |
| gemini25pro | gemini -y -m gemini-2.5-pro | Explicit stable Pro selection |
| gemini25flash | gemini -y -m gemini-2.5-flash | Fast, cost-effective |
| gemini25lite | gemini -y -m gemini-2.5-flash-lite | Fastest Gemini option |
| gemini3flash | gemini -y -m gemini-3-flash-preview | Explicit 3 Flash selection |
| gemini3pro | gemini -y -m gemini-3-pro-preview | Explicit 3 Pro selection |
| gemini31pro | gemini -y -m gemini-3.1-pro-preview | Latest Pro model (if available) |
| gemini37 | agy --model "Gemini 3.7 Flash (High)" --dangerously-skip-permissions --print-timeout 60m --output-format stream-json --print | Latest Flash tier, high reasoning (default 3.7 Flash alias) |
| gemini37-high | agy --model "Gemini 3.7 Flash (High)" --dangerously-skip-permissions --print-timeout 60m --output-format stream-json --print | Latest Flash tier, high reasoning |
| gemini37-medium | agy --model "Gemini 3.7 Flash (Medium)" --dangerously-skip-permissions --print-timeout 60m --output-format stream-json --print | Latest Flash tier, balanced reasoning |
| gemini37-low | agy --model "Gemini 3.7 Flash (Low)" --dangerously-skip-permissions --print-timeout 60m --output-format stream-json --print | Latest Flash tier, fast low-reasoning |
| agy | agy --model "Gemini 3.7 Flash (High)" --dangerously-skip-permissions --print-timeout 60m --output-format stream-json --print | Antigravity default (same as gemini/gemini37) |
| zai | codex exec --full-auto --profile zai | General coding fallback |
| glm5 | opencode run --format json -m zai/glm-5.3 --pure --agent build | Latest GLM 5.x tasks via OpenCode |
| glm52 | opencode run --format json -m zai/glm-5.2 --pure --agent build | Explicit GLM-5.2 pin via OpenCode |
| glm53 | opencode run --format json -m zai/glm-5.3 --pure --agent build | Explicit GLM-5.3 pin via OpenCode |
| kimi | opencode run --format json -m opencode/kimi-k2.5 --pure --agent build | Kimi K2.5 via OpenCode |
| synthetic | opencode run --format json -m synthetic/syn:large:text --pure --agent build | GLM-5.2 default, 512k context |
| syn-flash | opencode run --format json -m synthetic/syn:small:text --pure --agent build | Fast GLM-4.7-Flash fallback |
| syn-kimi | opencode run --format json -m synthetic/syn:large:vision --pure --agent build | Kimi-K2.7-Code vision tasks |
| syn-kimi3 | opencode run --format json -m synthetic/hf:moonshotai/Kimi-K3 --pure --agent build | Kimi-K3 flagship, vision, 512k context |
| syn-qwen | opencode run --format json -m synthetic/syn:small:vision --pure --agent build | Qwen3.6-27B vision tasks |
| syn-minimax | opencode run --format json -m synthetic/hf:MiniMaxAI/MiniMax-M3 --pure --agent build | MiniMax-M3 vision, cheap all-rounder |
| syn-nemotron | opencode run --format json -m synthetic/hf:nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4 --pure --agent build | Nemotron-3-Super-120B, cheapest large text |
| opencode | opencode run --format json -m zai/glm-4.7 --pure --agent build | Recommended OpenCode JSON runner |
| local | opencode run --format json -m lmstudio/qwen3.6-35b-a3b --pure --agent build | Local qwen-coder model with no quota |
| qwen | opencode run --format json -m lmstudio/qwen3.6-35b-a3b --pure --agent build | Local qwen-coder model with no quota |
| devstral | opencode run --format json -m lmstudio/devstral-small-2-2512 --pure --agent build | Local Devstral model with no quota |
| glm-local | opencode run --format json -m lmstudio/glm-4.7-flash --pure --agent build | Local GLM-4.7 Flash model with no quota |
| qwen-small | opencode run --format json -m lmstudio/qwen3-4b-2507 --pure --agent build | Small/fast local Qwen model |
| qwen36 | opencode run --format json -m lmstudio/qwen3.6-35b-a3b --pure --agent build | Best local coding model, MoE 35B, no quota |
| qwen36-27b | opencode run --format json -m lmstudio/qwen3.6-27b --pure --agent build | Local Qwen 3.6 dense 27B, no quota |
OpenCode runs include --variant <value> when a variant is set.
GLM-5.2 uses the Z.AI Coding Plan endpoint (https://api.z.ai/api/coding/paas/v4) with raw model ID glm-5.2. OpenCode receives zai/glm-5.2; Claude Code env examples use glm-5.2[1m] with ANTHROPIC_DEFAULT_SONNET_MODEL, ANTHROPIC_DEFAULT_OPUS_MODEL, and CLAUDE_CODE_AUTO_COMPACT_WINDOW=1000000. daplug passes only the model ID; the 1M context window is provided by the Coding Plan endpoint.
Synthetic shorthands use OpenCode provider refs such as synthetic/syn:large:text; set SYNTHETIC_API_KEY and configure OpenCode's synthetic provider with https://api.synthetic.new/openai/v1. Raw hf: IDs are intentionally not daplug shorthands; add them to OpenCode as synthetic/hf:owner/model pass-through refs when needed.
OpenCode permissions (headless runs): configure ~/.config/opencode/opencode.json to avoid interactive permission prompts, e.g.:
{
"permission": {
"*": "allow",
"external_directory": "allow",
"doom_loop": "allow"
}
}
Output Display
After executing the prompt, display a clear summary that includes the prompt title from the JSON output:
## Execution Started
**Prompt 295**: Add transcript success monitoring with retry logic
| Field | Value |
|-------|-------|
| Model | codex (gpt-5.5) |
| Status | 🟢 Running (PID 12345) |
| Loop | Max 3 iterations |
Worktree: `.worktrees/repo-prompt-295-20251229-181852/`
Branch: `prompt/295-transcript-success-monitoring`
Important: Always include the title field from the executor JSON output. This tells the user what the prompt actually does, not just its number.
Monitoring Pattern
After launching, spawn a haiku monitor subagent:
Task(
subagent_type: "general-purpose",
model: "haiku",
run_in_background: true,
prompt: """
Monitor prompt execution:
- Log file: {log_path}
- PID: {pid}
- {If tmux: Session: {session}}
- {If worktree: Worktree: {worktree_path}}
IMPORTANT: Use Bash tool for all file operations (not Read tool):
Every 30 seconds, check status using Bash:
```bash
# Check if process is running
ps -p {pid} > /dev/null 2>&1 && echo "RUNNING" || echo "STOPPED"
# Tail last 20 lines of log
tail -20 "{log_path}"
```
On completion (process ended):
```bash
# Get summary from log
tail -50 "{log_path}"
# If worktree, show git status
cd "{worktree_path}" && git log --oneline -5 && git diff --stat
```
- Summarize what was done
- Report final status
"""
)
Cleanup
For worktree executions, after completion:
# Remove TASK.md before merge
rm "$WORKTREE_PATH/TASK.md"
# Merge if requested
git checkout main
git merge --no-ff "$BRANCH_NAME" -m "Merge prompt: $BRANCH_NAME"
# Cleanup
git worktree remove "$WORKTREE_PATH"
git branch -D "$BRANCH_NAME"
git worktree prune