agentmods.dev

brain-ask

brain-ask is a command for Claude Code from hamza-ali-shahjahan/hamzaish. It costs 0 tokens per session (489 once invoked), scanned A, original, MIT.

A command for searching the Hamzaish brain, a collection of team learnings, decisions, playbooks, and product documents. It returns matching passages with references.

In plain words
What is it for?
Use it to recall decisions about a topic, check whether a problem has been seen before, or find supporting notes before designing a solution.
Why use it?
It helps you find what the team already decided or learned instead of searching manually or repeating previous work.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

not rated 10repo +1 1mo ago A scan 0 tokens original MIT

Good fit Use it to recall decisions about a topic, check whether a problem has been seen before, or find supporting notes before designing a solution.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/hamza-ali-shahjahan/hamzaish/brain-ask
View source ↗ hamza-ali-shahjahan/hamzaish hamzaish.com
Install

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.

Clone the repo
git clone --depth 1 https://github.com/hamza-ali-shahjahan/hamzaish

Made for: Claude Code.

Wrote 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.

agentmods badge for brain-ask

README.md
[![agentmods](https://agentmods.dev/badge/commands/hamza-ali-shahjahan/hamzaish/brain-ask/github.svg)](https://agentmods.dev/commands/hamza-ali-shahjahan/hamzaish/brain-ask)
Your own site
<a href="https://agentmods.dev/commands/hamza-ali-shahjahan/hamzaish/brain-ask"><img src="https://agentmods.dev/badge/commands/hamza-ali-shahjahan/hamzaish/brain-ask/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.

agentmods 80×15 button for brain-ask

Your own site · 80×15
<a href="https://agentmods.dev/commands/hamza-ali-shahjahan/hamzaish/brain-ask"><img src="https://agentmods.dev/badge/commands/hamza-ali-shahjahan/hamzaish/brain-ask.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 489 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.00489
Opus 5.5 $0.00000 $0.00196
Sonnet 5.5 $0.00000 $0.00098
Haiku 4.5 $0.00000 $0.00049

Measured 2mo ago against content hash d1a7acece360, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

brain-ask 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 2mo 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.

factory/commands/brain-ask.md · 25 lines

What it actually says

The user invoked: /brain-ask $ARGUMENTS — or you reached for recall yourself (a cross-cutting question, a past decision, the start of a fresh session on an unfamiliar product).

  1. If the query is empty, ask the user what they want to find.
  2. Query (via Bash) — it refreshes the index itself before answering, so there is no reindex step to remember: 
    bun ${HAMZAISH_ROOT:-$HOME/Claude/Hamzaish}/brain/ask.ts $ARGUMENTS
    A ⟳ index was behind the files — refreshed note on stderr is normal and means it caught up before answering. Scoping when results are noisy: --product <slug>, --source brain/learnings, --limit 4 --json. Phrase-quote for exact wording ("Sean Ellis target"); multi-word terms are OR'd and BM25-ranked.
  3. Show the markdown output as-is — it's already formatted with citations (path + source tag + score + snippet).
  4. Read the top 2–3 hits before answering, and cite the source file paths so the user can verify.
  5. If results are empty, they are empty against a just-refreshed index — treat it as genuinely uncharted and retry with broader terms, not as a missed reindex.

What you don't do

  • Don't run brain/ingest.ts first "to be safe" — ask refreshes itself, and the extra run is pure latency. Run it directly only to rebuild on demand.
  • Don't paraphrase from snippets alone — snippets are 18 tokens of context, not the full picture. Read the hits.
  • Don't substitute brain-ask for reading a file the user named directly. brain-ask is for discovery, not retrieval-by-path.

Sources: brain/README.md (what's indexed, how it works), brain/schema.sql (the database shape).

Changes

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.

  1. 2mo ago First seen · 25 lines · 0 tokens per session scan A d1a7acece360

Subscribe to this mod's changes

brain-ask is a command published in the GitHub repository hamza-ali-shahjahan/hamzaish (10 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 489 tokens. 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.

Claude CodeMemory and contextagent-skillsai-agentsbuildinpublicclaudeindie-hacker
Related

brain-ask compared with commands from other repositories

brain-ask next to 6 commands from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
brain-askhamza-ali-shahjahan/hamzaishCommand101mo agoMITA0Claude Code
minutes-ideassilverstein/minutesCommand1.6kyesterdayMITA48Claude Code, OpenCode
learnReflexioAI/claude-smartCommand7913d agoApache-2.0A14Claude Code
memory-storeverygoodplugins/mcp-automemCommand66yesterdayMITA10Claude Code
cc-memoryTheLobbi/claudeCommand217d agoMITA0Claude Code
lians-recallLians-ai/LiansCommand175d agoApache-2.0A19Claude Code
recallnaimkatiman/continuous-improvementCommand95d agoMITA44Claude Code