graph-undo

graph-undo is a command for Claude Code from sodam-ai/SoDam-Graph-Eng. It costs 24 tokens per session (402 once invoked), scanned A, original, Apache-2.0.

A command for reversing a milestone that has already been marked done back to verified status.

In plain words
What is it for?
Undoing a specific completed milestone when its ID is known; it does not handle milestones still awaiting approval.
Why use it?
It provides a way to correct an automatic completion without changing unrelated projects or adding a duplicate rejection record.

Command for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the sodam-graph plugin — 9 commands, 1 hook shipped together

Good fit Undoing a specific completed milestone when its ID is known; it does not handle milestones still awaiting approval.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add sodam-ai/SoDam-Graph-Eng
Claude Code
/plugin install sodam-graph

Made for: Claude Code.

Or install sodam-graph, the plugin that ships this one along with the rest of its 9 commands, 1 hook.

Wrote 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.

agentmods badge for graph-undo

README.md
[![agentmods](https://agentmods.dev/badge/commands/sodam-ai/sodam-graph-eng/graph-undo/github.svg)](https://agentmods.dev/commands/sodam-ai/sodam-graph-eng/graph-undo)
Your own site
<a href="https://agentmods.dev/commands/sodam-ai/sodam-graph-eng/graph-undo"><img src="https://agentmods.dev/badge/commands/sodam-ai/sodam-graph-eng/graph-undo/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.

agentmods 80×15 button for graph-undo

Your own site · 80×15
<a href="https://agentmods.dev/commands/sodam-ai/sodam-graph-eng/graph-undo"><img src="https://agentmods.dev/badge/commands/sodam-ai/sodam-graph-eng/graph-undo.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 402 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00024 $0.00402
Opus 5 $0.00012 $0.00201
Sonnet 5 $0.00005 $0.00080
Haiku 4.5 $0.00002 $0.00040

Measured 8d ago against content hash ce7ca3ccbd14, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

graph-undo 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 8d 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.

commands/graph-undo.md · 32 lines

What it actually says

이미 done 으로 확정된 마일스톤을 verified 상태로 되돌리세요.

하는 일

node "${CLAUDE_PLUGIN_ROOT}/lib/judge.mjs" --undo <마일스톤ID>
  • 마일스톤 ID를 모르면 먼저 /graph-where/graph-next 로 확인하세요. ID를 추측해서 지어내지 마세요.
  • 이 명령은 done 상태에서만 동작합니다. 아직 승격 대기(done_candidate)라면 실패 메시지가 뜨고 /graph-reject 로 안내합니다 — 그 안내를 그대로 전하세요.

/graph-reject 와의 차이

시점 명령
승격 (아직 사람이 확인할 시간이 있음) done_candidate /graph-reject
승격 (이미 done 으로 넘어감) done /graph-undo

결과를 이렇게 전해 주세요

  • 성공: "verified 로 되돌렸습니다"라고 알려주세요. (/graph-reject 와 달리 재제안 방지 기록은 남기지 않습니다 — 되돌린 뒤 조건을 다시 충족하면 또 승격 제안될 수 있다고 안내하세요)
  • 실패("done 상태가 아님"): 아직 승격 대기 중일 수 있습니다 — /graph-reject 를 안내하세요.

규칙 (이 명령의 안전 범위)

  • 정본(graph.json)의 해당 마일스톤 하나만 verified 로 되돌립니다.
  • 형제 저장소는 여전히 읽기만 합니다.
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. 8d ago First seen · 32 lines · 24 tokens per session scan A ce7ca3ccbd14

Subscribe to this mod's changes

graph-undo is a command published in the GitHub repository sodam-ai/SoDam-Graph-Eng (4 stars, last pushed 7d ago), licensed Apache-2.0. It adds 24 tokens to every session and 402 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.