frenzymath/danus/query-memory
Claude Code and agent skill by frenzymath/danus
- community
Checking that the SKILL.md file is still in the repository.
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.
Install
npx vskill@latest install frenzymath/danus/query-memorySKILL.md
Query Memory
Before spending effort, check what already exists. There are three places to look, in the three-memory model:
- Your own local memory (private): read/grep
local_memory/notes.jsonland
events.jsonl for your prior reasoning and what you already tried.
- 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.
- 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
- 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.
- 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.
- Prefer a narrow, targeted query (specific
kinds, a sharp query string) over
reading everything.
- 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/counterexampleis 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
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewNot runA model review is scheduled for the next rescan.
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingagents/skills/worker/query-memory/SKILL.md
Popularity
- 7-day trend score
- 0
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/frenzymath/danus/query-memory)