plan-undo

plan-undo is a command for coding agents from nguyenthienthanh/aura-frog. It costs 0 tokens per session (411 once invoked), scanned A, original, MIT.

A command for restoring the most recent saved checkpoint in a planning tree. It uses last-in, first-out order, so repeated uses undo progressively older changes.

In plain words
What is it for?
Use it to undo recent plan changes, inspect available checkpoints, or restore a specific planning node.
Why use it?
It provides a way to recover earlier planning state without manually rebuilding it. It also supports previewing or listing available checkpoints.

Command

Part of the aura-frog plugin — 17 skills, 24 commands, 15 agents, 10 hooks, 6 MCP servers shipped together

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/nguyenthienthanh/aura-frog/plan-undo
Clone the repo
git clone --depth 1 https://github.com/nguyenthienthanh/aura-frog

Or install aura-frog, the plugin that ships this one along with the rest of its 17 skills, 24 commands, 15 agents, 10 hooks, 6 MCP servers.

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 plan-undo

README.md
[![agentmods](https://agentmods.dev/badge/commands/nguyenthienthanh/aura-frog/plan-undo.svg)](https://agentmods.dev/commands/nguyenthienthanh/aura-frog/plan-undo)
Your own site
<a href="https://agentmods.dev/commands/nguyenthienthanh/aura-frog/plan-undo"><img src="https://agentmods.dev/badge/commands/nguyenthienthanh/aura-frog/plan-undo.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 411 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 $0.00000 $0.00411
Opus 5 $0.00000 $0.00205
Sonnet 5 $0.00000 $0.00082
Haiku 4.5 $0.00000 $0.00041

Measured 4d ago against content hash b2d1e0c9b3e6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

plan-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 4d 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.

aura-frog/commands/plan-undo.md · 38 lines

What it actually says

/aura-frog:plan-undo

Restore the latest checkpoint (LIFO). Alias for /aura-frog:plan undo [<id>] (v3.7.2+).


Usage

/aura-frog:plan-undo                 # active node (deepest non-null in active path)
/aura-frog:plan-undo <NODE_ID>
/aura-frog:plan-undo --dry-run       # preview
/aura-frog:plan-undo --list          # list available checkpoints for the node

Delegation

bash aura-frog/scripts/plans/undo-decision.sh [<NODE_ID>] [--dry-run] [--list] [--force]

The script:

  1. Resolves target: explicit arg, else walks active.{task,story,feature,initiative} for deepest non-null.
  2. Picks the latest .claude/plans/checkpoints/<id>.<ISO8601>.json (LIFO).
  3. Restores the node body (base64-decoded from node_state_before_b64).
  4. Moves the consumed checkpoint to .consumed so LIFO advances.
  5. Appends history.jsonl event=undo.

Multi-step undo works — call again to undo further. Retention cap is 5 checkpoints per node (per rules/workflow/checkpoint-discipline.md).

Not undoable: trace/history appends (append-only by design), archived nodes (terminal), mutations older than the retention window.

Git-state rollback (the git_sha in each checkpoint) is recorded but NOT auto-restored — git resets are deferred to a follow-up that asks for explicit user confirmation; v3.7.2 ships the plan-only undo.

Full protocol in commands/plan.md.

Deprecation timeline: soft-deprecated v3.7.2, warning v4.0, removed v5.0.

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. 4d ago First seen · 38 lines · 0 tokens per session scan A b2d1e0c9b3e6

Subscribe to this mod's changes

plan-undo is a command published in the GitHub repository nguyenthienthanh/aura-frog (24 stars, last pushed 10d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 411 tokens. 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 2026-08-30.