recovery-plan

recovery-plan is a command for Claude Code from maxschottke-spec/seo-survival-kit. It costs 15 tokens per session (4,992 once invoked), scanned A, original, MIT.

A command that turns diagnosis results and website crawl problems into a prioritized recovery plan for human review.

In plain words
What is it for?
Use it to plan SEO and online-shop recovery work, record risk points, respect change limits, and check whether a required approval gate is active.
Why use it?
It helps teams decide which fixes to make first while limiting risky or unauthorized changes. It does not apply SEO changes automatically.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the seo-rescue plugin — 18 skills, 6 commands shipped together

Good fit Use it to plan SEO and online-shop recovery work, record risk points, respect change limits, and check whether a required approval gate is active.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/maxschottke-spec/seo-survival-kit/recovery-plan
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.

Clone the repo
git clone --depth 1 https://github.com/maxschottke-spec/seo-survival-kit

Made for: Claude Code.

Or install seo-rescue, the plugin that ships this one along with the rest of its 18 skills, 6 commands.

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 recovery-plan

README.md
[![agentmods](https://agentmods.dev/badge/commands/maxschottke-spec/seo-survival-kit/recovery-plan/github.svg)](https://agentmods.dev/commands/maxschottke-spec/seo-survival-kit/recovery-plan)
Your own site
<a href="https://agentmods.dev/commands/maxschottke-spec/seo-survival-kit/recovery-plan"><img src="https://agentmods.dev/badge/commands/maxschottke-spec/seo-survival-kit/recovery-plan/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 recovery-plan

Your own site · 80×15
<a href="https://agentmods.dev/commands/maxschottke-spec/seo-survival-kit/recovery-plan"><img src="https://agentmods.dev/badge/commands/maxschottke-spec/seo-survival-kit/recovery-plan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,992 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 $0.00015 $0.04992
Opus 5 $0.00008 $0.02496
Sonnet 5 $0.00003 $0.00998
Haiku 4.5 $0.00002 $0.00499

Measured 12d ago against content hash c899b053b5c8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

recovery-plan 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 12d 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.

plugins/seo-rescue/commands/recovery-plan.md · 368 lines

How it starts

The opening of the file, as written. The whole thing — 368 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Recovery Plan

Zweck

Aus Diagnose-Befund und Crawl-Issues einen priorisierten, phasengerechten Action-Plan ableiten. Beruecksichtigt Recovery-Phase, Do-Not-Touch-Prinzip, Batch-Change-Limits und (sofern aktiv) den Settlement Gate. Der Plan setzt keine SEO-Aenderungen automatisch um. Er dient der menschlichen Freigabe.

Change Governance

Mode: audit_only. Change Budget: 0. Keine Live-Shop-Writes.

Jede geplante Aenderung muss als Change Plan mit Risikopunkten ausgegeben werden (Format: change-budget.schema.json). Der Plan referenziert SEO_CHANGE_GOVERNOR.md fuer die Punkteberechnung. Human Approval Gate per SAFE_LIVE_CHANGE_RULES.md. Settlement-Gate-Pruefung pro SEO_SETTLEMENT_GATE.md.

Settlement Gate Pre-Check (Pflicht vor Planung)

Vor jeder Planung muss geprueft werden:

  1. Gibt es einen aktiven Settlement Gate? — Lies ~/.cache/seo-rescue/{slug}/recovery-gate.json. Falls Datei existiert und settlement_gate_active = true: weiter mit Schritt 2. Sonst: normaler Planungs-Ablauf.

    Writer dieser Datei ist recovery-audit (siehe commands/recovery-audit.md, Schritt 7: Settlement-Gate-Detection) — recovery-plan liest sie nur. Fehlt die Datei, gilt der Gate als never_triggered. Ausnahme: Wenn change-history.ndjson existiert und Eintraege mit triggered_settlement_gate: true ODER einen un-auditierten Major Batch (Schwellenwerte per SEO_SETTLEMENT_GATE.md section 3) enthaelt, zuerst /seo-rescue:recovery-audit ausfuehren, damit der Gate-State materialisiert wird — sonst Warnung gate_state_possibly_stale eintragen.

  2. Wann war der letzte Major Batch? — Aus change-history.ndjson letzten Eintrag mit triggered_settlement_gate: true lesen.

  3. Gibt es Re-Evaluation-Daten? — Mindestens 2 von: GSC-Pull nach started_at, SF-Crawl nach started_at, Live-HTTP-Checks, DataForSEO-Snapshot, Sistrix-Signal, Backlink-Audit.

  4. Sind Unlock-Kriterien erfuellt? — Per SEO_SETTLEMENT_GATE.md section 9: time, data, stability, decision.

Read the full file on GitHub · 368 lines

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. 12d ago First seen · 368 lines · 15 tokens per session scan A c899b053b5c8

Subscribe to this mod's changes

recovery-plan is a command published in the GitHub repository maxschottke-spec/seo-survival-kit (9 stars, last pushed 1mo ago), licensed MIT. It adds 15 tokens to every session and 4,992 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.