Borrowing it
Nothing to install: this file belongs to donbr/lifesciences-research. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/donbr/lifesciences-research/main/.claude/commands/graphiti-verify.mdgit clone --depth 1 https://github.com/donbr/lifesciences-researchWrote 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/commands/donbr/lifesciences-research/graphiti-verify)<a href="https://agentmods.dev/commands/donbr/lifesciences-research/graphiti-verify"><img src="https://agentmods.dev/badge/commands/donbr/lifesciences-research/graphiti-verify/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/commands/donbr/lifesciences-research/graphiti-verify"><img src="https://agentmods.dev/badge/commands/donbr/lifesciences-research/graphiti-verify.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 | $0.00011 | $0.01073 |
| Opus 5 | $0.00005 | $0.00536 |
| Sonnet 5 | $0.00002 | $0.00215 |
| Haiku 4.5 | $0.00001 | $0.00107 |
Grade A, and why
graphiti-verify 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.
How it starts
The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run the Day 1 verification sequence to confirm the environment is working.
Instructions
Execute these checks in order. Report results but do NOT attempt fixes without user approval.
Environments checked:
- Production: Neo4j Aura via
graphiti-auraMCP (Checks 1-4) - Development: Docker Neo4j via
graphiti-dockerMCP (Check 5)
Check 1: Server Health
mcp__graphiti-aura__get_status()
Expected: Status OK with database connection confirmed.
Check 2: Query Available Groups
mcp__neo4j-aura-cypher__read_neo4j_cypher(
query="MATCH (e:Episodic) RETURN DISTINCT e.group_id AS group_id, count(*) AS episodes ORDER BY episodes DESC"
)
Expected: List of group_ids with episode counts. Primary groups are graphiti_meta_knowledge and graphiti_reference_docs.
Note: This check requires the neo4j-aura-cypher MCP server running. If unavailable, start it with:
docker compose -f docker/docker-compose-neo4j-mcp.yml --env-file .env up -d
Check 3: Test Semantic Search
mcp__graphiti-aura__search_nodes(
query="graphiti best practices",
group_ids=["graphiti_meta_knowledge"],
max_nodes=5
)
Expected: Returns relevant entity nodes.
Check 4: Neo4j Aura Health (Optional)
# First, get available instances
mcp__neo4j-aura-management__list_instances()
# Then check health of your instance (replace with your instance ID)
mcp__neo4j-aura-management__get_instance_details(instance_ids=["your-instance-id"])
Expected:
- Instance status: "running"
- Memory allocation appropriate for workload
- Graph size metrics (nodes/relationships) reported
- Connection URL accessible
Health Indicators:
- ✅ Status "running" with graph nodes/relationships counts
- ⚠️ Warn if memory is 1GB and graph has >5000 nodes (may need scaling)
- ❌ Status not "running" or connection errors
Note: This check requires the neo4j-aura-management MCP server running. If unavailable, start it with:
docker compose -f docker/docker-compose-neo4j-mcp.yml --env-file .env up -d
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 · 119 lines · 11 tokens per session scan A 1ef30451282b
graphiti-verify is a command published in the GitHub repository donbr/lifesciences-research (7 stars, last pushed 7d ago), licensed MIT. It adds 11 tokens to every session and 1,073 once invoked, about $0.0001 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 commands, from other repositories
by:plan-campaign
Pre-campaign discussion -- capture design preferences before launching.
by:resume
Resume an interrupted campaign from the last checkpoint.
by:campaign-auto
Full autonomous campaign — research, design, screen, rank with minimal interruption.
by:load
Load a protein target and analyze it for design.
by:approve-lab
Approve lab submission to Adaptyv Bio (triple-gated).
by:set-profile
Switch model profile (quality/balanced/budget).