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-pinpx skills add dropbox/witchcraft --skill pickbrain-pigit 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 | $0.00056 | $0.00679 |
| Opus 5 | $0.00028 | $0.00340 |
| Sonnet 5 | $0.00011 | $0.00136 |
| Haiku 4.5 | $0.00006 | $0.00068 |
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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pickbrain — Recall for Pi
Search previous Pi sessions semantically and use the results to answer the user with citations/excerpts. Pickbrain can also search Claude Code, Codex, and Slack when explicitly requested, but in Pi it should default to Pi history.
Preferred Pi Usage
If the pickbrain_search tool is available, use it first. It automatically:
- defaults to
type: "pi" - passes the current Pi session to pickbrain
- suppresses ingest progress noise
- limits results to a small useful set unless asked otherwise
Examples:
- Search Pi history:
{ "query": "auth middleware fix" } - Search current Pi session:
{ "query": "install target", "current": true } - Exclude current Pi session:
{ "query": "dropbox witchcraft", "excludeCurrent": true } - Search all coding agents:
{ "query": "extension api", "type": "pi,claude,codex" } - Search everything, including Slack:
{ "query": "launch plan", "allSources": true } - Dump a session:
{ "dump": "<session-id>", "turns": "2-4" }
Slash Command
The Pi extension also registers:
/pickbrain <query>
This searches Pi sessions by default. Pass flags to override:
/pickbrain --type pi,claude,codex auth middleware
/pickbrain --dump <session-id> --turns 2-4
Bash Fallback
If the tool is unavailable, run pickbrain via Bash:
pickbrain -q --type pi "$ARGUMENTS"
Pickbrain automatically ingests new sessions before each search. First run can take longer while building the local database.
Interpreting Results
Each result includes:
- timestamp and project directory
- source: usually
pi, orclaude,codex,slackif requested - session ID and turn number
- relevant matching text
Present results as a concise summary and quote the most relevant excerpts. To dig deeper:
pickbrain -q --dump <session-id> --turns <start>-<end>
Useful CLI Filters
pickbrain -q --type pi "<query>" # only Pi sessions
pickbrain -q --current "<query>" # current calling session when detectable
pickbrain -q --exclude-current "<query>"
pickbrain -q --session <session-id> "<query>"
pickbrain -q --since 7d "<query>"
pickbrain -q -n 20 "<query>"
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.
- 3d ago First seen · 84 lines · 56 tokens per session scan A c17a8eed83c1
pickbrain is a skill published in the GitHub repository dropbox/witchcraft (507 stars, last pushed 14d ago), licensed Apache-2.0. It adds 56 tokens to every session and 679 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…