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.
npx agentmods add skills/nickcirv/engram/querynpx skills add NickCirv/engram --skill querygit clone --depth 1 https://github.com/NickCirv/engramWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00060 | $0.00627 |
| Opus 5 | $0.00030 | $0.00313 |
| Sonnet 5 | $0.00012 | $0.00125 |
| Haiku 4.5 | $0.00006 | $0.00063 |
Grade A, and why
query scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
1 near-identical copy found in the catalogue:
- query — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
engram query
Query engram's knowledge graph instead of reading files directly. Saves tokens when a structural answer suffices.
The argument is a natural-language question. Run:
engram query "$ARGUMENTS" -p $CLAUDE_PROJECT_DIR
The graph returns a token-budgeted answer with:
- Relevant nodes (functions, files, concepts)
- Edges (calls, imports, decided-for relationships)
- Mistake hits if any (these surface with ⚠️ at the top — read carefully, they represent past failure modes)
If the answer doesn't fully address the question, fall back to reading specific files mentioned in the result.
For a connection between two specific concepts use engram path <source> <target>.
For most-connected entities use engram gods.
Example invocations
User: "How does authentication work in this project?"
You: Run engram query "how does authentication work" -p $CLAUDE_PROJECT_DIR. Read the structured response. Cite the relevant nodes (function names, file paths). If the answer mentions specific files, those are good candidates for a follow-up Read — but only if the structural view leaves a question.
User: "What calls validateToken?"
You: Run engram query "what calls validateToken" -p $CLAUDE_PROJECT_DIR. The graph returns the inbound call sites without you ever Reading those files.
User: "Where is the rate limiter implemented?"
You: Run engram query "rate limiter implementation" -p $CLAUDE_PROJECT_DIR. If the answer points at one file, you can Read that file confidently. If it points at three files, ask the user which path matters.
User: "Trace from userController.create to the database write"
You: This is a path query, not a free-text query. Use engram path userController.create database.write -p $CLAUDE_PROJECT_DIR. Returns the shortest call chain.
User: "Show me the most-connected files in this codebase"
You: Use engram gods -p $CLAUDE_PROJECT_DIR --top 10. Returns the entities with the most graph degree. Useful for "where do I start reading."
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.
- 2d ago First seen · 51 lines · 60 tokens per session scan A 088201faf9b5
query is a skill published in the GitHub repository NickCirv/engram (141 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 60 tokens to every session and 627 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.
Other skills, from other repositories
chatcrystal-task-writeback
Write reusable ChatCrystal task memories after substantive work completes. Use when implementation or debugging produced a durable fix, pitfall, pattern, or decision worth preserving, and when the environment can either persist it through writetaskmemory or emit a structured memory candidate for later save.
chatcrystal-debug-recall
Recall ChatCrystal memories for debugging tasks involving failing tests, compiler errors, runtime exceptions, dependency issues, environment breakage, or performance regressions. Use when historical root causes, fixes, or pitfalls may accelerate diagnosis before proposing a fix.
chatcrystal-task-recall
Recall project-first and global-supplement ChatCrystal memories before substantive implementation, refactoring, migration, configuration, investigation, or optimization work. Use when the task is non-trivial, has repository or project context, and prior fixes, decisions, pitfalls, or reusable patterns may change the…
slm-graph
Index and query a codebase as a structural graph — build the code graph, trace blast radius of a change, find callers/callees/inheritors, semantic code search by meaning, assemble PR review context, and detect what changed since last index. Use when the user asks how code connects, what breaks if X changes, what calls…
slm-recall
Search and retrieve facts, decisions, and past context from SuperLocalMemory. Use when the user asks to recall, find, search, or "what did we decide/say about X". Triggers multi-channel semantic retrieval with reranking; always call before storing anything new.
slm-governance
Enterprise compliance and governed workspace behavior for SuperLocalMemory. Covers role-based access (admin/member/viewer), retention policies, audit trail, GDPR data export/erase, and how agents must behave when operating under workspace governance. Requires power MCP profile for audit/retention tools. Agents must…