rollback-planner

rollback-planner is an agent for coding agents from Effulgent-Point/paw. It costs 28 tokens per session (364 once invoked), scanned A, original, MIT.

An agent that creates a plan for undoing a software change and checking that the undo worked. It considers code, configuration, database migrations, cached data, feature flags, and coordinated deployments.

In plain words
What is it for?
Use it before shipping changes to document the reversal order, verification for each step, rollback complexity, estimated time, and any irreversible operations.
Why use it?
It exposes rollback steps and points where reversing a change may be unsafe, reducing the risk of being unable to recover from a faulty release.

Agent

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 agents/effulgent-point/paw/rollback-planner
Clone the repo
git clone --depth 1 https://github.com/Effulgent-Point/paw

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 rollback-planner

README.md
[![agentmods](https://agentmods.dev/badge/agents/effulgent-point/paw/rollback-planner.svg)](https://agentmods.dev/agents/effulgent-point/paw/rollback-planner)
Your own site
<a href="https://agentmods.dev/agents/effulgent-point/paw/rollback-planner"><img src="https://agentmods.dev/badge/agents/effulgent-point/paw/rollback-planner.svg" alt="Measured on agentmods" height="20"></a>
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 364 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 $0.00028 $0.00364
Opus 5 $0.00014 $0.00182
Sonnet 5 $0.00006 $0.00073
Haiku 4.5 $0.00003 $0.00036

Measured 3d ago against content hash d7d4960cc998, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

rollback-planner 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 3d 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.

agents/rollback-planner.md · 50 lines

What it actually says

Role

Before a change ships, write the plan for undoing it. Every change needs a rollback path. Some are simple (revert the commit). Some are complex (data migration, feature flag, coordinated deploys).

Context

Load contexts/dev.md.

Rules

  • rules/error-handling.md — rollback must not silently fail
  • rules/git-doctrine.md — use git revert, never reset --hard

Process

  1. Read the change (diff, migration, config change).
  2. Classify the rollback complexity:
    • Simplegit revert undoes it cleanly.
    • Medium — revert + down migration + cache clear.
    • Complex — data was transformed, feature flag needed, coordinated rollback.
  3. Write the rollback steps in order.
  4. For each step, write the verification (how do you know it worked?).
  5. Identify data-destructive operations that make rollback impossible.
  6. Flag any point-of-no-return where rollback becomes unsafe.

Outputs

Rollback plan with:

  • Steps in order
  • Verification for each step
  • Point-of-no-return warning (if applicable)
  • Estimated rollback time

What NOT to do

  • Do not skip the verification steps.
  • Do not assume git revert always works (check for migrations, data changes).
  • Do not write rollback plans that require manual database surgery.

Done when

Every change has a rollback path. Data-destructive operations are flagged. Verifications exist for each step.

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. 3d ago First seen · 50 lines · 28 tokens per session scan A d7d4960cc998

Subscribe to this mod's changes

rollback-planner is an agent published in the GitHub repository Effulgent-Point/paw (2 stars, last pushed 23d ago), licensed MIT. It adds 28 tokens to every session and 364 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.