graph-run

A command that starts a graph-engineering run and advances it until it finishes or needs an answer from a person. A run is a sequence of connected work steps.

In plain words
What is it for?
It is for running graph workflows, carrying out any agent-assigned steps, reporting progress, and stopping when human input is required.
Why use it?
It handles the repeated progress checks required to move a registered execution graph forward.

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-run
Clone the repo
git clone --depth 1 https://github.com/sciencemj/graph-engineering
Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 241 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 $0.00010 $0.00241
Opus 5 $0.00005 $0.00120
Sonnet 5 $0.00002 $0.00048
Haiku 4.5 $0.00001 $0.00024

Measured yesterday against content hash 95ed761430fc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

graph-run 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-run.md · 21 lines

What it actually says

Follow the pump loop and Never sections of the graph-engineering skill exactly.

Target: $ARGUMENTS

  1. Create the run with run_start. Nothing executes at this point.
  2. Call run_advance repeatedly. Handle each response kind as the skill's pump loop says:
    • executed → report steps briefly and continue. If a step has status:"running", that command is still going — call run_advance again right away to collect it.
    • ai_task → read context, carry out instruction and only that, then run_submit.
    • waiting_user → tell the user and stop. Do not poll.
    • finished → final summary.

Remember: you are a pump, not a scheduler. The server decides which node runs. When an ai_task fails, report the failure as-is — retries are declared in the graph and enforced by the server.

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 · 21 lines · 10 tokens per session scan A 95ed761430fc

Subscribe to this mod's changes

graph-run is a command published in the GitHub repository sciencemj/graph-engineering (0 stars, last pushed 1mo ago), licensed MIT. It adds 10 tokens to every session and 241 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.