Add draw agent for let-fate-decide

[tob-joe]

Summary

• Adds agents/draw.md to the let-fate-decide plugin
• Named agent runs on Haiku (model: haiku in frontmatter) for cheap tarot draws
• Callers use Agent(subagent_type="let-fate-decide:draw", prompt="question") instead of wrapping Skill(let-fate-decide) in a generic Agent
• Card file content stays in agent context (not caller's)

Changes (v2)

• draw_cards.py --content: new flag that reads card .md files and includes their text inline in the JSON output. The draw agent now completes in 1 Bash call instead of 1 Bash + 4 sequential Reads.
• agents/draw.md: updated to use --content, removed Read from tools list. Agent goes from 5-6 turns to 1 turn per draw.

Problem solved: Haiku ignores <use_parallel_tool_calls> hints and reads the 4 card files sequentially (4 extra turns per draw, ~8-12 wasted turns per vivisect pipeline run with 2-3 draws). By having the Python script read the files directly, no Read calls are needed at all.

Motivation

Skills that draw tarot portents in parallel with other work currently require a 4-line Agent prompt telling the sub-agent to call Skill(let-fate-decide). This named agent replaces that with a 1-line dispatch. Running on Haiku saves cost since card interpretation is simple work.

Test plan

• uv run scripts/draw_cards.py --content outputs JSON with "content" field containing card markdown
• uv run scripts/draw_cards.py (no flag) still outputs JSON without content (backward compatible)
• Agent(subagent_type="let-fate-decide:draw", prompt="What portent awaits?") returns a 1-2 sentence reading
• Draw agent completes in exactly 1 tool call (Bash), not 5-6
• Card content does NOT appear in the caller's context (only the verdict text)

🤖 Generated with Claude Code

[claude]

Claude Code Review

This repository is configured for manual code reviews. Comment @claude review to trigger a review.

_{Tip: disable this comment in your organization's Code Review settings.}

[dguido]

Automated Review — PR #134

Conflicts

None — clean merge with main.

Review Findings

1. Agent script discovery used fragile find command — draw.md used find ~/.claude/plugins -name draw_cards.py to locate the script at runtime. Replaced with ${CLAUDE_PLUGIN_ROOT}/skills/let-fate-decide/scripts/draw_cards.py, which is the standard plugin path variable.

2. Unclosed file handle in draw_cards.py — open(path).read() on line 125 leaked a file descriptor. Wrapped in a with statement.

3. Version not bumped — Adding a new agent is a substantive change. Bumped from 1.0.0 to 1.1.0 in both plugin.json and marketplace.json.

No issues found with:

• Agent frontmatter (valid name, description, model, tools)
• Python script quality (PEP 723 metadata, proper error handling, uv run pattern, cryptographic randomness via os.urandom)
• No hardcoded paths in Python script
• No security concerns

Validation

• validate_codex_skills.py — PASS (61 skills, 62 Codex entries)
• validate_plugin_metadata.py — PASS (36 plugins in sync)
• Hardcoded path check — PASS (no /Users/ or /home/ references)

Changes Made

• 8aa54cf — Fix draw agent script discovery and bump version to 1.1.0

---

🤖 Reviewed by Claude Code