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/graph-dreamnpx skills add stevepridemore/graph-memory --skill graph-dreamgit 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 | $0.00041 | $0.00369 |
| Opus 5 | $0.00020 | $0.00185 |
| Sonnet 5 | $0.00008 | $0.00074 |
| Haiku 4.5 | $0.00004 | $0.00037 |
Grade A, and why
graph-dream 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.
What it actually says
The user wants to manually trigger the graph memory dream process. This runs inline in the current session — you ARE the dream process. No separate script needed.
Arguments: $ARGUMENTS
Parse the arguments:
--dry-runoptional: describe what you would do without actually calling graph tools--ingest-onlyoptional: only process the ingest drop folder, skip conversation transcripts
For the full dream process instructions, read the file: ~/graph-memory/prompts/dream-nightly.md (seeded into the data dir by the docker container's entrypoint on first start)
Follow those instructions exactly. The key steps are:
- Read manifest at ~/graph-memory/processed/manifest.json
- Find unprocessed transcripts in ~/.claude/projects/
- Check ~/graph-memory/ingest/pending/ for documents
- If nothing pending, report "No pending work" and exit
- For each unprocessed transcript: extract entities, call graph_relate/graph_boost/graph_weaken
- For each ingest document: same extraction process
- Call graph_decay for maintenance
- Write changelog to ~/graph-memory/logs/YYYY-MM-DD.md
- Update manifest.json
- Move ingest files from pending/ to completed/
If --dry-run, describe what you would extract but do NOT call any graph write tools. If --ingest-only, skip transcript processing entirely.
IMPORTANT: Never merge entities unless highly confident. Flag suspected duplicates instead.
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 · 36 lines · 0 tokens per session scan A 9c04795be4a7
graph-dream is a skill published in the GitHub repository stevepridemore/graph-memory (2 stars, last pushed 3mo ago), licensed MIT. It adds 41 tokens to every session and 369 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.
install-waggle
Install the official Waggle plugin locally for Codex from the latest stable Abhigyan-Shekhar/Waggle-mcp GitHub Release. Use for explicit requests such as "Install Waggle", "Set up Waggle", "Install Waggle for Codex", or "Enable Waggle". Do not use for Waggle operation, repair, updates, configuration, or memory…
lint
Use weekly or after major ingest sessions to check wiki health.
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.