graph-status

A command for summarizing the current state of workflow graphs and their runs. A graph is a set of connected steps, while a run is one execution of those steps.

In plain words
What is it for?
Use it to inspect graph locks, node statuses, attempts, the current cursor, waiting conditions, timestamps, and failure logs.
Why use it?
It shows where each step stands, where execution is paused, and whether the system is waiting for a person or for the automated runner. It also reports the cause of failed steps.

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-status
Clone the repo
git clone --depth 1 https://github.com/sciencemj/graph-engineering
Per session 7 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 228 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 $0.00007 $0.00228
Opus 5 $0.00003 $0.00114
Sonnet 5 $0.00001 $0.00046
Haiku 4.5 $0.00001 $0.00023

Measured yesterday against content hash 87296a08af29, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

graph-status 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-status.md · 19 lines

What it actually says

Target: $ARGUMENTS (everything, if empty)

  1. graph_list for the graphs and their lock state.
  2. run_list for the runs. If a specific run was named, get the detail with run_get_context.
  3. Summarize in a table:
    • each node's status (pending / ready / running / awaiting_* / succeeded / failed / skipped) with its visit and attempt
    • where the cursor is and what it is waiting on (waiting_for)
    • last_advance_at — when the cursor was last pushed
  4. If waiting_for is "user", say what the user has to do. If it is "ai_pump", say that /graph-engineering:graph-run can keep pushing it.

If a node failed, read the cause with run_get_node_log and report it too.

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 · 19 lines · 7 tokens per session scan A 87296a08af29

Subscribe to this mod's changes

graph-status is a command published in the GitHub repository sciencemj/graph-engineering (0 stars, last pushed 1mo ago), licensed MIT. It adds 7 tokens to every session and 228 once invoked, about $0.0000 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.