Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/dropbox/witchcraft/pickbrain-codexnpx skills add dropbox/witchcraft --skill pickbrain-codexgit clone --depth 1 https://github.com/dropbox/witchcraftWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00065 | $0.00510 |
| Opus 5 | $0.00032 | $0.00255 |
| Sonnet 5 | $0.00013 | $0.00102 |
| Haiku 4.5 | $0.00006 | $0.00051 |
Grade A, and why
pickbrain scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Pickbrain — Semantic Search for AI Coding History
Search past Pi, Claude Code, and Codex conversations, memory files, and authored files using semantic search.
Usage
Run pickbrain with the user's query:
pickbrain "$ARGUMENTS"
Pickbrain automatically ingests new Pi/Claude/Codex sessions, memories, and project config files (CLAUDE.md, AGENTS.md, and their @ references) before each search.
Interpreting Results
Each result includes:
- Timestamp and project directory
- Session ID and turn number — identifies the exact conversation turn
- Matching text — the relevant chunk from the conversation
Present results as a concise summary. Quote the most relevant excerpts. To dig deeper into a specific session:
pickbrain --dump <session-id> --turns <start>-<end>
Filtering
Search within the current (calling) session:
pickbrain --current "<query>"
Search within a specific session by ID:
pickbrain --session <session-id> "<query>"
Exclude the current (calling) session from results:
pickbrain --exclude-current "<query>"
Exclude specific sessions by ID (comma-separated or repeated):
pickbrain --exclude <uuid1>,<uuid2> "<query>"
pickbrain --exclude <uuid1> --exclude <uuid2> "<query>"
Search only recent history:
pickbrain --since 24h "<query>"
pickbrain --since 7d "<query>"
pickbrain --since 2w "<query>"
Notes
- First run requires a full ingest+embed pass (~7s). Subsequent searches are incremental.
- The database lives at
~/.pickbrain/pickbrain.db. - Results are ranked by semantic similarity — they may not contain the exact query words.
- The active session's JSONL is skipped during ingest if it was indexed less than 10 minutes ago. If the active session can't be detected, everything is ingested eagerly.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 74 lines · 65 tokens per session scan A ae3a7731889a
pickbrain is a skill published in the GitHub repository dropbox/witchcraft (507 stars, last pushed 14d ago), licensed Apache-2.0. It adds 65 tokens to every session and 510 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…