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.
git clone --depth 1 https://github.com/maxschottke-spec/seo-survival-kitWrote 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.
[](https://agentmods.dev/commands/maxschottke-spec/seo-survival-kit/recovery-audit)<a href="https://agentmods.dev/commands/maxschottke-spec/seo-survival-kit/recovery-audit"><img src="https://agentmods.dev/badge/commands/maxschottke-spec/seo-survival-kit/recovery-audit/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.
<a href="https://agentmods.dev/commands/maxschottke-spec/seo-survival-kit/recovery-audit"><img src="https://agentmods.dev/badge/commands/maxschottke-spec/seo-survival-kit/recovery-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00019 | $0.04085 |
| Opus 5 | $0.00010 | $0.02042 |
| Sonnet 5 | $0.00004 | $0.00817 |
| Haiku 4.5 | $0.00002 | $0.00409 |
Grade A, and why
recovery-audit 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.
How it starts
The opening of the file, as written. The whole thing — 291 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Recovery Audit
Zweck
Auditiert alle SEO-Aenderungen an einer Domain innerhalb eines Zeitraums: Change-Inventar, fehlgeschlagene Versuche, unverifizierte Aenderungen, Risiko- und Approval-Compliance, Rollback-Readiness, Settlement-Gate-Status und Hypothesen-Registry. Read-only gegenueber dem Live-Shop — das Audit stellt fest, was passiert ist, und bewertet es; es aendert nichts.
Change Governance
Mode: immer audit_only. Change Budget: 0. Keine Live-Shop-Writes. Schreibt nur Report-Artefakte nach ~/.cache/seo-rescue/{slug}/ (via lib/safe.js, siehe Schritt 9).
Settlement Gate Awareness
Dieses Command ist read-only gegenueber dem Live-Shop — ein aktiver Settlement Gate (references/SEO_SETTLEMENT_GATE.md) blockiert es NIE. Sonderrolle: recovery-audit ist der Writer der Gate-Datei ~/.cache/seo-rescue/{slug}/recovery-gate.json — alle anderen Commands (diagnose, plan, monitor, full) lesen sie nur. Die Gate-Detection selbst ist Teil des Ablaufs (Schritt 7).
Trigger
/seo-rescue:recovery-audit <domain> [--days 14]
Input-Kontrakt
| Feld | Quelle | Pflicht |
|---|---|---|
domain |
CLI-Argument | ja |
--days |
CLI-Flag | nein — Default: 14 |
--days definiert das Audit-Fenster: period_end = jetzt, period_start = jetzt minus --days Tage. Wird das Command vom Orchestrator (recovery-full) ohne Flag aufgerufen, gilt der Default 14.
Ablauf
Schritt 1: Domain normalisieren
Normalisiere den Input via normalizeDomain() aus lib/safe.js — gibt input_domain, domain, canonical_domain, slug zurueck.
Schritt 2: Cache-Verzeichnis anlegen
ensureDomainDir(slug) — Modus 0700, Abbruch bei Symlink.
Schritt 3: Run-ID generieren
Falls eine run_id vom Orchestrator (recovery-full) uebergeben wurde: diese unveraendert verwenden, KEIN eigenes Prefix erzeugen. Sonst generiere eine eindeutige Run-ID fuer diesen Lauf:
node -e "const { randomUUID } = require('crypto'); console.log('aud-' + randomUUID().slice(0,8) + '-' + Date.now())"
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.
- 12d ago First seen · 291 lines · 19 tokens per session scan A 17cb455c03e2
recovery-audit is a command published in the GitHub repository maxschottke-spec/seo-survival-kit (9 stars, last pushed 1mo ago), licensed MIT. It adds 19 tokens to every session and 4,085 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.
Other commands, from other repositories
seo-content
Route to the content-seo skill to brief, write, review, optimize, or publish public SEO content.
spec-driven
Decompose a compound request (multiple deliverables, skills, pillars, or decision/check gates) into spec + plan + result-check before any downstream skill runs.
prototype
You are building a proof-of-concept for the current Grainulator sprint. Read CLAUDE.md for sprint context and claims.json for existing research claims.
init
Install the formatters this repository needs, with every command visible before it runs.
brand-generate
Generate an on-brand document from a saved Brand Profile.
genshijin-compress
A command for safely shortening Markdown or text files into the genshijin style.