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/scops/engrama/onboardnpx skills add scops/engrama --skill onboardgit clone --depth 1 https://github.com/scops/engramaWrote 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/scops/engrama/onboard)<a href="https://agentmods.dev/skills/scops/engrama/onboard"><img src="https://agentmods.dev/badge/skills/scops/engrama/onboard.svg" alt="Measured on agentmods" 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 | $0.00104 | $0.02437 |
| Opus 5 | $0.00052 | $0.01218 |
| Sonnet 5 | $0.00021 | $0.00487 |
| Haiku 4.5 | $0.00010 | $0.00244 |
Grade A, and why
engrama-onboard 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 250 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Engrama Onboard
Build a personalized memory graph schema for any user through conversation.
Engrama's power comes from its graph structure, but that structure must match how the user actually thinks and works. A developer tracks Projects, Decisions, and Technologies. A nurse tracks Patients, Protocols, and Medications. A teacher tracks Students, Curricula, and Assessments. The onboard skill conducts a short interview to understand who the user is, then generates a complete profile that drives the entire system.
Prerequisites
The only hard dependencies are:
- Python ≥ 3.11 with PyYAML (installed automatically by
uv sync) - An installed Engrama checkout (
git clone+uv sync) - Obsidian vault (optional — only needed for note sync features)
A database is not a prerequisite. Since 0.9 Engrama defaults to a
zero-dependency SQLite backend that lives in ~/.engrama/engrama.db
and is created automatically on first connection. Neo4j is opt-in
(uv sync --extra neo4j + Docker) for multi-process production
setups, very large vector indexes, or teams already using Cypher —
see BACKENDS.md for the decision guide.
No dependency on any specific AI framework, agent SDK, or MCP runtime.
What gets generated
From a profile YAML (standalone or composed from base + modules), the codegen script produces:
engrama/core/schema.py— NodeType enum, RelationType enum, dataclasses,TITLE_KEYED_LABELSset (used by engine and MCP server for merge-key logic)scripts/init-schema.cypher— Neo4j-only constraints, fulltext index, and range indexes. Applied automatically when the Neo4j backend is selected. The SQLite backend ignores this file entirely; its schema lives inengrama/backends/sqlite/schema.sqland is applied on first connection, souv run engrama initis backend-agnostic.
The profile YAML is the single source of truth. Change it, rerun the script, and the entire schema propagates. No manual editing needed.
What ships with it
2 files 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.
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.
- 4d ago First seen · 250 lines · 104 tokens per session scan A 504daaa47a91
engrama-onboard is a skill published in the GitHub repository scops/engrama (9 stars, last pushed 15d ago), licensed Apache-2.0. It adds 104 tokens to every session and 2,437 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
handoff
Save a session handoff to Engram for future sessions. Captures decisions, todos, blockers, mental model, and next steps as a structured memory. Use when the user wants to preserve session context before ending work.
memory-review
Memory hygiene audit -- finds stale facts, contradictions, low-confidence entries, and consolidation candidates in Pensyve memory. Use periodically to maintain memory quality.
session-memory
End-of-session memory capture -- classifies session signals using a tiered taxonomy and stores confirmed items via Pensyve. Use when ending a work session or when the user wants to capture what was learned.
memory-informed-refactor
Pre-refactor context briefing -- loads relevant prior decisions, failures, and pitfalls from Pensyve memory before refactoring a module. Use before any refactor to avoid repeating past mistakes.
memory-informed-debug
Debug with working memory -- before diagnosing, recall prior root causes and known-good diagnostic procedures; when a root cause is confirmed, capture it immediately. Use whenever debugging a non-trivial failure.
memory-informed-longitudinal-work
Long-running multi-session work (research, eval loops, iterative benchmarks) with continuity -- resume prior lessons, capture per-run outcomes, build up stable truths over time. Use for eval/research/benchmark work that spans sessions.