Witchcraft is a standalone semantic search engine written in Rust that stores its search index in a single SQLite database and runs on a device. It is intended for client-side document search without external services or API keys, and the catalogue skills support using the project.
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 skills add dropbox/witchcraft --skill pickbraingit clone --depth 1 https://github.com/dropbox/witchcraftWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/dropbox/witchcraft/pickbrain)<a href="https://agentmods.dev/skills/dropbox/witchcraft/pickbrain"><img src="https://agentmods.dev/badge/skills/dropbox/witchcraft/pickbrain/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/dropbox/witchcraft/pickbrain"><img src="https://agentmods.dev/badge/skills/dropbox/witchcraft/pickbrain.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What 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 5.1 | $0.00085 | $0.01083 |
| Opus 5.5 | $0.00034 | $0.00433 |
| Sonnet 5.5 | $0.00017 | $0.00217 |
| Haiku 4.5 | $0.00009 | $0.00108 |
Grade A, and why
pickbrain scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pickbrain — Semantic Search for Claude History and Slack
Search past Pi sessions, Claude Code conversations, Codex sessions, Slack messages, memory files, and authored files using semantic search.
Installation
Build and install from the repo root:
make pickbrain
# then copy or symlink the binary to somewhere on your PATH:
ln -sf "$(pwd)/pickbrain" ~/bin/pickbrain
The binary embeds its own model weights (embed-assets feature), so no separate assets directory is needed.
Usage
Run pickbrain via Bash with the user's query:
pickbrain "$ARGUMENTS"
Pickbrain automatically ingests new Pi/Claude/Codex sessions, Slack conversations (from the desktop app's local IndexedDB), memories, and project config files before each search.
Interpreting Results
Each result includes:
- Timestamp and project directory (or channel name for Slack results)
- Source —
pi,claude,codex, orslack - Session ID and turn number (Claude/Codex) or channel + thread ID (Slack)
- Matching text — the relevant chunk from the conversation
Slack results show thr:TIMESTAMP for threaded conversations. This thread ID can be passed to --session or --dump to filter/view that thread.
Present results as a concise summary. Quote the most relevant excerpts. If the user wants to dig deeper into a specific session, use --dump:
pickbrain --dump <session-id> [--turns <start>-<end>]
pickbrain --dump <channel-name> [--turns <start>-<end>] [--since 7d]
pickbrain --dump thr:<thread-ts>
Slack results include (you: Name (@handle)) to identify the logged-in user.
Filtering
To search within the current (calling) session:
pickbrain --current "<query>"
To search within a specific session, channel, or thread:
pickbrain --session <session-id> "<query>"
pickbrain --channel <channel-name> "<query>"
pickbrain --session thr:<thread-ts> "<query>"
--channel is an alias for --session.
To exclude the current (calling) session from results:
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.
- 1mo ago First seen · 140 lines · 85 tokens per session scan A f3c6f183a26a
pickbrain is a skill published in the GitHub repository dropbox/witchcraft (524 stars, last pushed 10d ago), licensed Apache-2.0. It adds 85 tokens to every session and 1,083 once invoked, about $0.0003 per session on Opus 5.5. 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
mem0-oss-to-platform
Plan, then execute, a migration of a project from the mem0 open-source / self-hosted SDK (local Memory class) to the mem0 Platform / hosted SDK (MemoryClient). TRIGGER when: the developer wants to move, switch, or migrate mem0 off OSS/self-hosted to the hosted API, e.g. "migrate my mem0 setup to the platform", "switch…
forget
Remove a personal fact, preference, relationship detail, topic, or prior event from Muse's active memory and stop existing copies or automations from bringing it back. Use for explicit requests such as 'forget that', 'don't remember this about me', or 'remove that from your memory'. Do not use when 'forget it' merely…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
shellm
Reference for the shellm system — recursive LLM shell, identity management, memory, skills, trajectory, and all CLI tools. Use when working on shellm itself, debugging agent behavior, or understanding how the pieces fit together.