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/dgraziosi/foundation/graph-hygienenpx skills add dgraziosi/foundation --skill graph-hygienegit clone --depth 1 https://github.com/dgraziosi/foundationWrote 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/dgraziosi/foundation/graph-hygiene)<a href="https://agentmods.dev/skills/dgraziosi/foundation/graph-hygiene"><img src="https://agentmods.dev/badge/skills/dgraziosi/foundation/graph-hygiene.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 5.1 | $0.00039 | $0.00426 |
| Opus 5 | $0.00019 | $0.00213 |
| Sonnet 5 | $0.00008 | $0.00085 |
| Haiku 4.5 | $0.00004 | $0.00043 |
Grade A, and why
graph-hygiene 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
Graph hygiene
You are running graph hygiene. The user can run this, or attach it to Vault Keeper.
Read docs/GRAPH_HYGIENE.md and follow it. Call bootstrap if you need the current tools.
The user is the human who runs this vault on this machine. The graph is the knowledge in this vault. Do not call the graph “the Vault.”
Schedule and voice
Weekly, local time. If there is nothing to report, stay quiet. Ping the user only when you found duplicates, isolates, or type soup.
A first-day vault (seed types, zero user nodes) is healthy — skip duplicate and orphan reports.
User config (fill in)
- MCP / health base: http://127.0.0.1:8787
- FOUNDATION_DATA: (from .env; default ./data)
Checks (report only)
- Duplicate titles among live nodes. Report id, type, title. Do not merge.
- Live nodes with zero edges. Report them; do not delete. Skip if the graph has no user nodes.
- Type soup: inspect_ontology / bootstrap types. Flag authored types that fight the spine (duplicate area/project/goal/habit/task, empty parent_types on something that should hang on the spine, near-synonym pile). System seeds are not soup. Do not manage_type on this run.
Prefer MCP (bootstrap, inspect_ontology, get, search, list_activity). There is no list_nodes tool. Page search by type until next is omitted. Do not list the graph around MCP.
This pass is the weekly graph report. Dream rewrites the record from today's activity, closes what's done, and cleans obvious duplicates. Vault health and product updates have their own schedules.
This routine reports. It changes the graph only when the user asked for a repair in this conversation.
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 Changed 3ee19b1c21bd
- 4d ago First seen · 36 lines · 39 tokens per session scan A f832291fdea0
graph-hygiene is a skill published in the GitHub repository dgraziosi/foundation (1 stars, last pushed today), licensed MIT. It adds 39 tokens to every session and 426 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
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
agent-memory
../../../engineering/agent-memory/skills/agent-memory/SKILL.md.
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…