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/stevepridemore/graph-memory/graphnpx skills add stevepridemore/graph-memory --skill graphgit clone --depth 1 https://github.com/stevepridemore/graph-memoryWhat 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 | $0.00039 | $0.00322 |
| Opus 5 | $0.00019 | $0.00161 |
| Sonnet 5 | $0.00008 | $0.00064 |
| Haiku 4.5 | $0.00004 | $0.00032 |
Grade A, and why
graph 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 yesterday.
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.
What it actually says
The user wants to query the memory graph.
Arguments: $ARGUMENTS
Parse the arguments:
- First positional argument(s) are entity names to query (required)
--hops Noptional: max traversal depth (default 2)--typeoptional: filter results by node type (Person, Project, Preference, Concept, Decision, Fact, Event, Object)--relatedoptional: show all entities related to the query entity
Steps:
- Call the
graph_queryMCP tool with:- entities: the entity name(s) from the arguments
- max_hops: from --hops flag or default 2
- entity_types: from --type flag if provided
- project_context: the current working directory
- Present the results in a readable format:
- Group by entity type
- Show relationship types and weights
- Highlight the strongest connections
- Note any effective_weight vs raw weight differences (project affinity)
- List associated source files the user can read for full context
If the query returns no results, suggest checking entity names or trying broader terms. If no entity name is provided, ask the user what they want to look up.
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.
- yesterday First seen · 32 lines · 0 tokens per session scan A 4d222044ec57
graph is a skill published in the GitHub repository stevepridemore/graph-memory (2 stars, last pushed 3mo ago), licensed MIT. It adds 39 tokens to every session and 322 once invoked, about $0.0002 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
ori-memory
Persistent agent memory with learning retrieval. Knowledge graph on markdown files — capture insights, decisions, research, and learnings during work, then retrieve them weeks or months later. Use when knowledge is too valuable to lose but too much to inject into every prompt.
svoboda-profiler
Use when asked to profile someone, unpack a person, build a psychological portrait, run a Svoboda session, or map life state. Triggers on распаковка, профилирование, психопортрет, точка А, колесо баланса, profile someone, unpack, svoboda session.
vault-scaffolder
Use when a completed svoboda profile.yaml exists and a new Personal OS needs to be personalized in the current workspace.
lint
Use weekly or after major ingest sessions to check wiki health.
pos-audit
Use when checking overall Personal OS health or diagnosing system gaps.
start
One-word self-unfolding onboarding. Sets up a fresh, unpersonalized vault end-to-end — installs the memory engine, runs the profile interview, scaffolds the vault, and teaches the user as it goes. The single front door.