query-memory

A memory lookup step that searches previous reasoning, shared findings, verified mathematical facts, and known dead ends before new work begins.

In plain words
What is it for?
Finding earlier conclusions, counterexamples, verification results, reusable proofs, and project definitions relevant to a new question.
Why use it?
It reduces repeated effort and helps avoid approaches that have already failed or claims that have not been verified.

Skill for Claude CodeCodex

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 skills/frenzymath/danus/query-memory
Any agent
npx skills add frenzymath/Danus --skill query-memory
Clone the repo
git clone --depth 1 https://github.com/frenzymath/Danus

Made for: Claude Code, Codex.

Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 761 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 $0.00068 $0.00761
Opus 5 $0.00034 $0.00380
Sonnet 5 $0.00014 $0.00152
Haiku 4.5 $0.00007 $0.00076

Measured 3d ago against content hash 17a6355fdf1f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

query-memory 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.

agents/skills/worker/query-memory/SKILL.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Query Memory

Before spending effort, check what already exists. There are three places to look, in the three-memory model:

  1. Your own local memory (private): read/grep local_memory/notes.jsonl and events.jsonl for your prior reasoning and what you already tried.
  2. Global memory (shared findings): gm_search(query, kinds=...) over the swarm's findings. Especially useful kinds:
    • dead_end / obstacle — paths that already died (skip them);
    • verification — outcomes of others' fact_submit (learn from rejections);
    • conclusion / example / counterexample / plan — others' results to build on. You can also read the global_memory/<kind>.jsonl files directly.
  3. Fact graph (verified truth): fact_search(query) (BM25 over the verified facts) to find results you can cite or that show your subgoal is already proved — it returns {fact_id, statement}; read the full proof from fact_graph/facts/<fact_id>.md on a relevant hit, and fact_graph/glossary.json to reuse the project's symbol definitions. A proof may build only on facts (cite a fact_id).

Procedure

  1. Obey the current prompt's restrictions first. If it forbids a direction, file, or search, that overrides default recall. If it recommends specific results or directions, raise their priority.
  2. Start with the cheapest relevant source: your own local memory for your context; gm_search for the swarm's findings; the fact graph for verified building blocks.
  3. Prefer a narrow, targeted query (specific kinds, a sharp query string) over reading everything.
  4. Workspace boundary: stay inside your own working directory and the shared project stores. Do not scan parent directories, other workers' private local_memory/, or other projects.

Retrieval priority

  • A relevant verified fact (fact graph) is the strongest hit — you can build on it directly by citing its fact_id.
  • A sibling's dead_end/obstacle saves you from re-walking a dead path.
  • A sibling's verification rejection tells you why a similar claim failed.
  • A conclusion/example/counterexample is awareness — useful, but never a brick (only facts are). Re-verify anything you intend to build on.

Read the full file on GitHub · 60 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 3d ago First seen · 60 lines · 68 tokens per session scan A 17a6355fdf1f

Subscribe to this mod's changes

query-memory is a skill published in the GitHub repository frenzymath/Danus (387 stars, last pushed 7d ago), licensed Apache-2.0. It adds 68 tokens to every session and 761 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.

Related

Other skills, from other repositories

project-graveyard

Scans the developer's machine for dead side projects, autopsies each one from its git history (died at the payments wall, killed by a newer project, finished but never shipped), surfaces their personal death patterns, and picks the corpse most worth resurrecting — then helps ship it. Use when the user mentions…

Shubhamsaboo/awesome-llm-apps · 127 tokens

web-app-penetration-testing

Pentest a web app or website end to end — black-box testing of a live URL, staging environment, or local dev server that finds and exploits real vulnerabilities (auth bypass, broken access control, IDOR, injection, XSS, SSRF, business logic) and proves each one with a working proof-of-concept instead of a signature…

usestrix/strix · 129 tokens

haiku

When writing a haiku for this bot, follow these conventions.

agno-agi/agno · 0 tokens

deploy-docker-compose

Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…

omnigent-ai/omnigent · 84 tokens

azure-mgmt-botservice-dotnet

Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".

microsoft/skills · 78 tokens

babysit

Same-session monitoring loop for PRs, CI runs, tickets, and deployments using the monitorstart / monitorupdate / autonudgestop MCP tools. The loop re-injects your check instructions into THIS session on an idle interval — same context, same tools — and works from dashboard chat, Slack threads, and Discord DMs. Use…

kirodotdev/KiroCrew · 137 tokens