Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/maxschottke-spec/seo-survival-kitnpx agentmods add commands/maxschottke-spec/seo-survival-kit/recovery-monitorWrote 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-monitor)<a href="https://agentmods.dev/commands/maxschottke-spec/seo-survival-kit/recovery-monitor"><img src="https://agentmods.dev/badge/commands/maxschottke-spec/seo-survival-kit/recovery-monitor/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-monitor"><img src="https://agentmods.dev/badge/commands/maxschottke-spec/seo-survival-kit/recovery-monitor.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 | $0.00015 | $0.05188 |
| Opus 5 | $0.00008 | $0.02594 |
| Sonnet 5 | $0.00003 | $0.01038 |
| Haiku 4.5 | $0.00002 | $0.00519 |
Grade A, and why
recovery-monitor 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 — 370 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Recovery Monitor
Zweck
Woechentliches Recovery-Tracking. Holt aktuelle VI + Keyword-Daten, berechnet Recovery-Score, appendet an die History-Datei. Laeuft auch bei fehlenden Datenquellen durch und schreibt einen Partial-Eintrag — der Zeitstempel allein ist wertvoll fuer die Zeitreihe.
Change Governance
Mode: read_only. Change Budget: 0. Keine Live-Shop-Writes. Schreibt nur History-Artefakte (history.ndjson, append-only, via lib/safe.js).
Wenn change-history.ndjson existiert, wird sie fuer die Change-History-Integration gelesen und im Eintrag referenziert (siehe ## Change History Integration). Jede Score-Bewegung traegt Quelle und Confidence.
Settlement Gate Awareness
Dieses Command ist read-only gegenueber dem Live-Shop (audit_only, Change Budget 0, schreibt nur Cache-Artefakte) — ein aktiver Settlement Gate (references/SEO_SETTLEMENT_GATE.md) blockiert es NIE. Es muss den Gate-State aber kennen und ausweisen:
- Lies
~/.cache/seo-rescue/{slug}/recovery-gate.json, falls vorhanden. Writer dieser Datei istrecovery-audit(siehecommands/recovery-audit.md, Schritt 7: Settlement-Gate-Detection) — recovery-monitor liest sie nur. Fehlt die Datei, gilt der Gate alsnever_triggered: keine Warnung, normaler Ablauf. - Falls
settlement_gate_active = true:-
Monitoring laeuft normal weiter — read-only Tracking ist waehrend eines aktiven Gates immer erlaubt und ausdruecklich erwuenscht (der Gate braucht Re-Evaluation-Daten).
-
In den History-Eintrag (Top-Level) das Feld
settlement_gate_statusaufnehmen, gespiegelt aus der Gate-Datei:"settlement_gate_status": { "active": true, "next_allowed_review_date": "2026-06-06", "unlock_status": "blocked" }(
unlock_status:blocked | partial | open, direkt aus der Gate-Datei uebernommen.) -
In der User-Ausgabe (Delta-Report) eine Zeile ausgeben:
Settlement Gate: AKTIV bis {next_allowed_review_date} — read-only Monitoring erlaubt, Live-Aenderungen blockiert -
Jeder Empfehlungstext darf KEINE sofortigen Live-Aenderungen vorschlagen. Naechste Schritte als "jetzt vorbereiten/Drafts erstellen, Ausfuehrung nach Gate-Re-Evaluation" formulieren (
prepare_now_execute_later-Prinzip ausSEO_SETTLEMENT_GATE.md). -
Score-Bewegung waehrend aktivem Gate: Wenn der Recovery Score stark gefallen ist (Drop > 15 Punkte gegenueber dem letzten History-Eintrag), KEINE korrigierende Live-Aktion empfehlen. Stattdessen empfehlen, die Beobachtung in die Gate-Re-Evaluation am
next_allowed_review_datemitzunehmen — der Gate existiert genau dafuer, dass frisches Post-Batch-Rauschen nicht sofort beantwortet wird. Das gilt auch fuer Rollback-Empfehlungen aus der Change-History-Integration: Anomalies werden geflagged und fuer die Re-Evaluation dokumentiert; ob daraus ein Emergency-Rollback perSEO_SETTLEMENT_GATE.mdsection 7 wird, entscheidet der Operator.
-
- Falls Gate-Datei fehlt oder
settlement_gate_active = false:settlement_gate_status: { "active": false }in den History-Eintrag schreiben. Keine User-Ausgabe-Zeile noetig.
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 · 370 lines · 15 tokens per session scan A 0259e656ba57
recovery-monitor 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 5,188 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.