New: 97,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Query Memory

by frenzymath in frenzymath/Danus

Recall what is already known — your own prior reasoning, the swarm's shared findings (including dead ends and verifier feedback), and the verified facts — before doing new work.

Apache-2.0Auto-check passed

Install Query Memory

skills CLI
$ npx skills add frenzymath/Danus --skill query-memory -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install frenzymath/Danus query-memory --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/frenzymath/Danus.git skills-src && mkdir -p .claude/skills && cp -r skills-src/agents/skills/worker/query-memory .claude/skills/query-memory && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
query-memory
GitHub stars
471
Token cost
~784 tokens
SKILL.md length
367 words
Files
2
Skills in repo
16
Repo updated
First seen
Licence
Apache-2.0

At a glance

Recall what is already known — your own prior reasoning, the swarm's shared findings (including dead ends and verifier feedback), and the verified facts — before doing new work.

  • Works in 3 steps: Your own local memory (private):… → Global memory (shared findings):… → Fact graph (verified truth):…
  • Prior conclusions
  • SKILL.md covers Procedure, Retrieval priority, Output and Tools
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Query Memory is an agent skill from frenzymath/Danus. Recall what is already known — your own prior reasoning, the swarm's shared findings (including dead ends and verifier feedback), and the verified facts — before doing new work. Use when prior conclusions, examples, dead branches, verification outcomes, or verified results may inform the current question, claim, subgoal, or branch decision.

Its SKILL.md is about 780 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

The repository describes itself as: Orchestrating Mathematical Reasoning Agents with Fact-Graph Memory. The licence is Apache-2.0.

When your agent uses it

  • Prior conclusions
  • Verification outcomes
  • Verified results may inform the current question
  • Branch decision

Example prompts

  • “/query-memory”

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. Your own local memory (private): read/grep local_memory/notes.jsonl and
  2. Global memory (shared findings): gm_search(query, kinds=...) over the
  3. Fact graph (verified truth): fact_search(query) (BM25 over the verified

What it can do on your machine

Read from SKILL.md and the folder at commit 6d92e8d. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Query Memory loads about 784 tokens when it runs. Until then it costs about 89 tokens; SKILL.md has 367 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~89
When it runs · the whole SKILL.md, loaded when a task matches
~784

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from frenzymath/Danus at commit 6d92e8d, republished under its Apache-2.0 licence (© frenzymath). 367 words, ~784 tokens.

Download SKILL.mdSave it as .claude/skills/query-memory/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
query-memory
description
Recall what is already known — your own prior reasoning, the swarm's shared findings (including dead ends and verifier feedback), and the verified facts — before doing new work. Use when prior conclusions, examples, dead branches, verification outcomes, or verified results may inform the current question, claim, subgoal, or branch decision.

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.
Show full SKILL.md (128 more words)Show less

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.

Output

Note what you recalled and how you used it in your local memory (events). Do not re-publish others' findings; just use them.

Tools

  • gm_search (recall shared findings; BM25 over global memory)
  • fact_search (recall verified facts; BM25 over the fact graph — novelty + citation lookup)
  • local memory is read directly (no tool — read/grep the files); read a fact's full proof from its fact_graph/facts/<fact_id>.md once fact_search surfaces it

© frenzymath, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in agents/skills/worker/query-memory of frenzymath/Danus.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit 6d92e8d

Compare with similar skills

Query Memory next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Query Memory compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Query Memory this skillfrenzymath/Danus471—~784Automated safety check: PassApache-2.0
Recallcursor/plugins10k7 repos~1.3kAutomated safety check: PassNone
Agentmemory Recallrohitg00/agentmemory29k—~557Automated safety check: PassApache-2.0
Cognee Memory Recalltopoteretes/cognee32k—~2.6kAutomated safety check: PassApache-2.0
Recallparcadei/Continuous-Claude-v33.9k1 repos~314Automated safety check: PassMIT
Recalldavepoon/buildwithclaude3.6k—~981Automated safety check: PassMIT

Similar skills

  • Recall

    cursor/plugins

    Official

    Reconstruct your recent working context from your own chat history, live state, and the shared record (user reports, prior fixes, incidents), then hand back a tight current-state brief.

    10k GitHub starsUsed in 7 repos~1.3k tokens
    Auto-check passed

  • Agentmemory Recall

    rohitg00/agentmemory

    Searches agentmemory for past observations, sessions and learnings with hybrid keyword, vector and graph search, and reports only what comes back.

    29k GitHub stars~557 tokensUpdated yesterday
    Agent WorkflowsAuto-check passed

  • Cognee Memory Recall

    topoteretes/cognee

    Explains how to query cognee agent memory with recall(): how the search type is chosen, how to narrow a query to datasets, and what the returned results contain.

    32k GitHub stars~2.6k tokensUpdated yesterday
    AI & LLM EngineeringAuto-check passed

  • Recall

    parcadei/Continuous-Claude-v3

    Query the memory system for relevant learnings from past sessions

    3.9k GitHub starsUsed in 1 repo~314 tokens
    Auto-check passed

  • Recall

    davepoon/buildwithclaude

    Search Origin's local memory by query. An agent skill from davepoon/buildwithclaude.

    3.6k GitHub stars~981 tokensUpdated yesterday
    Auto-check passed

  • Hindsight Recall

    vectorize-io/hindsight

    Search long-term memory for relevant context from past coding sessions using Hindsight MCP tools

    46k GitHub stars~312 tokensUpdated today
    Agent WorkflowsAuto-check passed

More from frenzymath/Danus

All 16 skills in this repo

  • Check Referenced Statements

    frenzymath/Danus

    Validate externally referenced theorems by querying arXiv theorem search first and Codex's built-in web search second.

    471 GitHub stars~852 tokensUpdated 1 mo ago
    Auto-check passed

  • Construct Counterexamples

    frenzymath/Danus

    Construct candidate counterexamples to test a proposed conjecture, lemma, or intermediate claim by keeping the assumptions true while making the claimed conclusion fail.

    471 GitHub stars~790 tokensUpdated 1 mo ago
    Auto-check passed

  • Construct Toy Examples

    frenzymath/Danus

    Generate and analyze simpler examples that satisfy both the assumptions and the conclusion of a theorem statement or subgoal.

    471 GitHub stars~541 tokensUpdated 1 mo ago
    Auto-check passed

  • Direct Proving

    frenzymath/Danus

    Screen a decomposition plan by first trying to prove all of its subgoals directly, then identifying the key stuck points if the plan does not fully go through.

    471 GitHub stars~1.3k tokensUpdated 1 mo ago
    Auto-check passed

  • Identify Key Failures

    frenzymath/Danus

    Synthesize the common stuck points across failed decomposition plans.

    471 GitHub stars~586 tokensUpdated 1 mo ago
    Auto-check passed

  • Obtain Immediate Conclusions

    frenzymath/Danus

    Derive immediate mathematical consequences from a theorem statement or subgoal.

    471 GitHub stars~587 tokensUpdated 1 mo ago
    Auto-check passed

Questions about Query Memory

What does Query Memory do?

Recall what is already known — your own prior reasoning, the swarm's shared findings (including dead ends and verifier feedback), and the verified facts — before doing new work. Query Memory is an agent skill from frenzymath/Danus. Recall what is already known — your own prior reasoning, the swarm's shared findings (including dead ends and verifier feedback), and the verified facts — before doing new work.

When should I use Query Memory?

Query Memory fits situations like: prior conclusions; verification outcomes; verified results may inform the current question; branch decision.

How do I install Query Memory in Claude Code?

Run `npx skills add frenzymath/Danus --skill query-memory -a claude-code`. Or copy the skill folder (agents/skills/worker/query-memory in frenzymath/Danus) into .claude/skills/query-memory in your project. Claude Code loads it when a task matches its description.

How do I install Query Memory in Codex?

Run `npx skills add frenzymath/Danus --skill query-memory -a codex`. Or copy the skill folder (agents/skills/worker/query-memory in frenzymath/Danus) into .agents/skills/query-memory in your project. Codex loads it when a task matches its description.

Can I use Query Memory in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add frenzymath/Danus --skill query-memory -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/query-memory, .gemini/skills/query-memory, .github/skills/query-memory and .opencode/skills/query-memory in your project.

What does Query Memory need to run?

SKILL.md names no scripts, command-line tools or credentials: Query Memory is instructions for the agent only.

Does Query Memory access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Query Memory safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Query Memory use?

Query Memory is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Query Memory use?

About 784 tokens (SKILL.md is roughly 3.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Query Memory?

Skills that share tags, products or a category with Query Memory: Recall (cursor/plugins, 10k stars), Agentmemory Recall (rohitg00/agentmemory, 29k stars), Cognee Memory Recall (topoteretes/cognee, 32k stars) and Recall (parcadei/Continuous-Claude-v3, 3.9k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Query Memory?

frenzymath (a GitHub organization) maintains it in frenzymath/Danus, which has 471 GitHub stars. The repository holds 16 skills in this directory. The repository was last updated on August 27, 2026.

Source: frenzymath/Danus on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.