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 commands/sciencemj/graph-engineering/graph-lockgit clone --depth 1 https://github.com/sciencemj/graph-engineeringWhat 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 | $0.00017 | $0.00211 |
| Opus 5 | $0.00009 | $0.00105 |
| Sonnet 5 | $0.00003 | $0.00042 |
| Haiku 4.5 | $0.00002 | $0.00021 |
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.
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:
- Read the current state with
graph_get_lock_stateand report it. - Tell the user to use the padlock button in the web UI header (see
/graph-engineering:graph-open). - 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.
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 · 20 lines · 17 tokens per session scan A 4e352e09d92c
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.
Other commands, from other repositories
fix-issues
Diagnose, reproduce, then fix reproducible open GitHub issues in parallel: one clean worktree/issue; symlink build artifacts to avoid rebuilds.
review-prs
Parallel PR triage: decide merge-worthiness, prepare rebased worktrees, fix blockers, return them for human merge.
triage
Classify/label newly opened GitHub issues missing labels.
release
Release all packages at specified version.
cleanup
Autonomous cleanup-loop iteration: discover ONE target → complete execution → verify → report. Runs stateless: derive from current tree; assume prior runs left it consistent.
hello
Say hello.