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 skills add Republicofhaitigoodstory6175/engram --skill querygit clone --depth 1 https://github.com/Republicofhaitigoodstory6175/engramWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/republicofhaitigoodstory6175/engram/query)<a href="https://agentmods.dev/skills/republicofhaitigoodstory6175/engram/query"><img src="https://agentmods.dev/badge/skills/republicofhaitigoodstory6175/engram/query/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/republicofhaitigoodstory6175/engram/query"><img src="https://agentmods.dev/badge/skills/republicofhaitigoodstory6175/engram/query.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00060 | $0.00627 |
| Opus 5 | $0.00030 | $0.00313 |
| Sonnet 5 | $0.00012 | $0.00125 |
| Haiku 4.5 | $0.00006 | $0.00063 |
Grade A, and why
query scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
100% identical to query — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
engram query
Query engram's knowledge graph instead of reading files directly. Saves tokens when a structural answer suffices.
The argument is a natural-language question. Run:
engram query "$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.
- 10d ago First seen · 51 lines · 60 tokens per session scan A 088201faf9b5
query is a skill published in the GitHub repository Republicofhaitigoodstory6175/engram (1 stars, last pushed yesterday), 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. It is 100% identical to query, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
handoff
Create, validate, list, and load local Portable Handoff capsules for context transfer, continuing work in a new chat, compacting current work, or loading prior work. Use whenever the user asks for a handoff, context transfer, continuation briefing, or portable work-state summary.
institutional-memory-distill
Distill decisions, reasoning, and rejected alternatives from PRs, design docs, and postmortems into the project's decisionledger, so ult-context-generate's trip-wire can surface institutional memory before new work quietly repeats settled ground. Do NOT use to query the ledger against new work or decide…
continuity-ledger
Create or update continuity ledger for state preservation across clears.
recall-reasoning
Search past reasoning for relevant decisions and approaches.
system-overview
Show users how Continuous Claude works - the opinionated setup with hooks, memory, and coordination.
remember
Store a learning, pattern, or decision in the memory system for future recall.