graph-lock

A guide for checking and changing a graph's lock state, where a lock freezes the graph's structure against AI changes while people can still edit and run it.

In plain words
What is it for?
Use it to see whether a graph is locked and to direct a person to lock or unlock it using the web interface.
Why use it?
It prevents the AI from unlocking the graph, leaving the final lock decision with a human.

Command

Install

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.

agentmods
npx agentmods add commands/sciencemj/graph-engineering/graph-lock
Clone the repo
git clone --depth 1 https://github.com/sciencemj/graph-engineering
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 211 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00017 $0.00211
Opus 5 $0.00009 $0.00105
Sonnet 5 $0.00003 $0.00042
Haiku 4.5 $0.00002 $0.00021

Measured yesterday against content hash 4e352e09d92c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

graph-lock 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.

commands/graph-lock.md · 20 lines

What it actually says

Request: $ARGUMENTS

You cannot do this. graph_lock and graph_unlock do not exist as MCP tools, and over HTTP they require the human-only ui_token. That is the design, not a bug — a lock means nothing if the AI has a path to release it.

Do this:

  1. Read the current state with graph_get_lock_state and report it.
  2. Tell the user to use the padlock button in the web UI header (see /graph-engineering:graph-open).
  3. If you think locking is the right call, explain why — but leave the decision to the user.

What the lock means: a freeze against the AI. The human keeps editing freely in the UI while locked, and a locked graph still runs. The lock freezes structure, it does not forbid execution.

Changes

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.

  1. yesterday First seen · 20 lines · 17 tokens per session scan A 4e352e09d92c

Subscribe to this mod's changes

graph-lock is a command published in the GitHub repository sciencemj/graph-engineering (0 stars, last pushed 1mo ago), licensed MIT. It adds 17 tokens to every session and 211 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.