ask

A command that answers a question in everyday language by searching stored memories and producing a combined answer with source citations.

In plain words
What is it for?
Use it to ask about past decisions or project knowledge, choose keyword, meaning-based, or combined search, include context from multiple scopes, and return human-readable or JSON output.
Why use it?
It reduces the need to search memories manually and shows where the answer came from.

Command

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.

agentmods
npx agentmods add commands/proticom/gnosys/ask
Clone the repo
git clone --depth 1 https://github.com/proticom/gnosys
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 673 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.00673
Opus 5 $0.00000 $0.00336
Sonnet 5 $0.00000 $0.00135
Haiku 4.5 $0.00000 $0.00067

Measured 2d ago against content hash 33bdd34cd017, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 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.

docs/commands/ask.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

gnosys ask

Ask a natural-language question and get a synthesized answer with citations.

Usage

gnosys ask "What did we decide about auth?"
gnosys ask "What did we decide about auth?" --mode hybrid --limit 10
gnosys ask "What did we decide about auth?" --federated --scope project,user
gnosys ask "What did we decide about auth?" --no-stream --json

Options

Option Description
-l, --limit <n> Max memories to retrieve (default 15)
-m, --mode <mode> Search mode: keyword, semantic, or hybrid (default hybrid)
--no-stream Disable streaming output
--federated Pre-retrieve cross-scope context from central DB
--scope <scope> Filter federated scopes: project, user, global (comma-separated)
-d, --directory <dir> Project directory for federated context detection
--json Output answer and sources as JSON (disables streaming)

Behavior

  1. Resolves stores; exits if none (No stores found. Run gnosys init first.).
  2. Loads config from store (falls back to DEFAULT_CONFIG).
  3. Builds search index, embeddings, hybrid search, and GnosysAsk synthesizer.
  4. Checks LLM availability before querying; exits with provider-aware error if unavailable.
  5. Optionally pre-retrieves federated context from central DB when --federated or --scope is set.
  6. Calls ask.ask() with mode, limit, streaming callbacks, and optional federated context.
  7. Prints answer (streamed or buffered), sources, and deep-query note when applicable.
  8. Best-effort reinforces cited source paths via GnosysMaintenanceEngine.reinforceBatch.
  9. Closes search and embeddings handles.

Streaming

By default, tokens stream to stdout via onToken. Search completion and deep-query expansion print status lines to stderr/stdout. --no-stream or --json disables token streaming.

Federated context

When federated/scope is enabled, matching central DB memories are injected as additionalContext before synthesis. If central DB is unavailable, ask falls through to normal local retrieval.

Read the full file on GitHub · 74 lines

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. 2d ago First seen · 74 lines · 0 tokens per session scan A 33bdd34cd017

Subscribe to this mod's changes

ask is a command published in the GitHub repository proticom/gnosys (4 stars, last pushed 15d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 673 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.