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 GeoffreyCoulaud/bgcpm --skill pick-my-braingit clone --depth 1 https://github.com/GeoffreyCoulaud/bgcpmWrote 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/geoffreycoulaud/bgcpm/pick-my-brain)<a href="https://agentmods.dev/skills/geoffreycoulaud/bgcpm/pick-my-brain"><img src="https://agentmods.dev/badge/skills/geoffreycoulaud/bgcpm/pick-my-brain/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/geoffreycoulaud/bgcpm/pick-my-brain"><img src="https://agentmods.dev/badge/skills/geoffreycoulaud/bgcpm/pick-my-brain.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00044 | $0.01578 |
| Opus 5 | $0.00022 | $0.00789 |
| Sonnet 5 | $0.00009 | $0.00316 |
| Haiku 4.5 | $0.00004 | $0.00158 |
Grade A, and why
pick-my-brain 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 11d 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 — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pick My Brain
Overview
A structured questioning technique that builds shared understanding between agent and user before any work begins. The core principle: never guess what you can ask.
Without this skill, agents ask good initial questions but collapse under social pressure ("you have enough context"), miss entire knowledge domains, and can't track what they don't know.
When to Use
- Before a planning session (use this THEN plan)
- Starting any non-trivial task where the user knows more than you
- When you catch yourself about to make an assumption
- When requirements feel vague or incomplete
Do NOT use for:
- Simple, well-defined tasks ("fix this typo", "rename this variable")
- Tasks where the user already provided a detailed spec
- Follow-up work where context was already established
The Iron Rules
- One question at a time. Never bundle. Not even "just two quick ones."
- Dig into vague answers. "Yeah something like that" is not an answer. Probe why.
- Track your coverage. Know what domains you've explored and which remain.
- Resist pressure to stop. When the user says "you have enough context," respond with what you've covered and what's still missing. Let them make an informed choice.
- Produce a brief. Always end with a written knowledge brief before any work begins.
Questioning Flow
digraph pick_my_brain {
rankdir=TB;
node [shape=box];
start [label="User describes topic" shape=doublecircle];
identify [label="Identify knowledge domains\n(silently, from first description)"];
ask [label="Ask ONE question\nabout least-understood domain"];
listen [label="Listen to answer"];
vague [label="Answer vague\nor uncertain?" shape=diamond];
dig [label="Dig deeper:\nOffer options or sub-questions"];
update [label="Update mental model\nMark domain progress"];
gaps [label="Uncovered domains\nremain?" shape=diamond];
pressure [label="User pressuring\nto stop?" shape=diamond];
articulate [label="Articulate: covered X,\nmissing Y — let user decide"];
brief [label="Produce knowledge brief\nwith facts + open questions"];
done [label="Proceed to work/planning" shape=doublecircle];
start -> identify;
identify -> ask;
ask -> listen;
listen -> vague;
vague -> dig [label="yes"];
vague -> update [label="no, clear answer"];
dig -> listen;
update -> gaps;
gaps -> ask [label="yes"];
gaps -> brief [label="no, sufficient"];
pressure -> articulate [label="yes"];
articulate -> brief [label="user agrees to stop"];
articulate -> ask [label="user agrees to continue"];
gaps -> pressure [label="yes, but user impatient"];
brief -> done;
}
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.
- 11d ago First seen · 170 lines · 44 tokens per session scan A cb63782ca3da
pick-my-brain is a skill published in the GitHub repository GeoffreyCoulaud/bgcpm (4 stars, last pushed 5mo ago), licensed Unlicense. It adds 44 tokens to every session and 1,578 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
postgres-database-migration
Use this skill for planning, testing, and safely executing PostgreSQL schema migrations — especially when working with production data or shared databases. Trigger when user asks to: Test a schema migration before applying it to production Add, remove, or rename columns safely on a live table Change a column's data…
setup-timescaledb-hypertables
Use this skill when creating database schemas or tables for Timescale, TimescaleDB, TigerData, or Tiger Cloud, especially for time-series, IoT, metrics, events, or log data. Use this to improve the performance of any insert-heavy table. Trigger when user asks to: Create or design SQL schemas/tables AND…
design-postgis-tables
Comprehensive PostGIS spatial table design reference covering geometry types, coordinate systems, spatial indexing, and performance patterns for location-based applications.
migrate-postgres-tables-to-hypertables
Use this skill to migrate identified PostgreSQL tables to Timescale/TimescaleDB hypertables with optimal configuration and validation. Trigger when user asks to: Migrate or convert PostgreSQL tables to hypertables Execute hypertable migration with minimal downtime Plan blue-green migration for large tables Validate…
pgvector-semantic-search
Use this skill for setting up vector similarity search with pgvector for AI/ML embeddings, RAG applications, or semantic search. Trigger when user asks to: Store or search vector embeddings in PostgreSQL Set up semantic search, similarity search, or nearest neighbor search Create HNSW or IVFFlat indexes for vectors…
find-hypertable-candidates
Use this skill to analyze an existing PostgreSQL database and identify which tables should be converted to Timescale/TimescaleDB hypertables. Trigger when user asks to: Analyze database tables for hypertable conversion potential Identify time-series or event tables in an existing schema Evaluate if a table would…