Agent skill
spool
Search your local Claude Code and Codex CLI session history
Install this agent skill to your Project
npx add-skill https://github.com/spool-lab/spool/tree/main/skills/spool
SKILL.md
Search your thinking with spool — a local search engine over your Claude Code and Codex CLI sessions.
Steps
- Check if spool is installed
which spool
If the command is not found, tell the user:
spoolCLI is not installed. Run:npm install -g @spool/clithenspool syncto index your sessions. Stop here.
- Run the search
spool search "$ARGS" --json --limit 5
where $ARGS is everything the user passed to /spool.
- Present the results
For each result in the JSON array, show:
- Session title and date (
startedAt) - Source (claude or codex) and project path
- The snippet with highlighted terms (strip
<mark>/</mark>tags for plain display) - A note of the session UUID
Example format:
1. [claude] /code/myproject — 2026-03-20
"…evaluated the database sharding tradeoffs and reached a decision…"
UUID: abc123
2. [codex] /code/api — 2026-03-18
"…the race condition was caused by a shared map write without a mutex…"
UUID: def456
- Offer to load a full session
Ask: "Want to see the full conversation for any of these? I can load it with spool show <uuid>."
If the user says yes (or specifies a number/UUID), run:
spool show <uuid>
Include the output as context in your next reply.
Tips
- Add
--source claudeor--source codexto filter by source - Add
--since 7dto limit to the last 7 days - Use quotes for exact phrases:
/spool "read replicas" - Run
spool syncfirst if results seem stale
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
clarify
Improve unclear UX copy, error messages, microcopy, labels, and instructions to make interfaces easier to understand. Use when the user mentions confusing text, unclear labels, bad error messages, hard-to-follow instructions, or wanting better UX writing.
adapt
Adapt designs to work across different screen sizes, devices, contexts, or platforms. Implements breakpoints, fluid layouts, and touch targets. Use when the user mentions responsive design, mobile layouts, breakpoints, viewport adaptation, or cross-device compatibility.
arrange
Improve layout, spacing, and visual rhythm. Fixes monotonous grids, inconsistent spacing, and weak visual hierarchy. Use when the user mentions layout feeling off, spacing issues, visual hierarchy, crowded UI, alignment problems, or wanting better composition.
frontend-design
Create distinctive, production-grade frontend interfaces with high design quality. Generates creative, polished code that avoids generic AI aesthetics. Use when the user asks to build web components, pages, artifacts, posters, or applications, or when any design skill requires project context.
verl-rl-training
Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.
openrlhf-training
High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing.
Didn't find tool you were looking for?