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.
npx skills add SaikaAco/saika-hermes-skills --skill hermes-backup-recoverygit clone --depth 1 https://github.com/SaikaAco/saika-hermes-skillsWrote 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/skills/saikaaco/saika-hermes-skills/hermes-backup-recovery)<a href="https://agentmods.dev/skills/saikaaco/saika-hermes-skills/hermes-backup-recovery"><img src="https://agentmods.dev/badge/skills/saikaaco/saika-hermes-skills/hermes-backup-recovery/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/skills/saikaaco/saika-hermes-skills/hermes-backup-recovery"><img src="https://agentmods.dev/badge/skills/saikaaco/saika-hermes-skills/hermes-backup-recovery.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 | $0.00052 | $0.02340 |
| Opus 5 | $0.00026 | $0.01170 |
| Sonnet 5 | $0.00010 | $0.00468 |
| Haiku 4.5 | $0.00005 | $0.00234 |
Grade A, and why
hermes-backup-recovery 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 — 250 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hermes Backup and Recovery
Overview
Protect Hermes with two complementary recovery layers:
sanitized control-plane text → local Git history → readable rollback
raw recovery state + safe databases → encrypted Restic snapshot → disaster recovery
The Git layer is intentionally incomplete and secret-free. The encrypted snapshot is the recovery layer and may contain credentials, sessions, logs, source state, databases, and other sensitive files according to the operator's approved scope.
A backup is not complete because a command exited successfully. Completion requires an atomic snapshot manifest, database consistency evidence, repository checks, and periodic restore verification.
When to use
Use when:
- backing up Hermes configuration, profiles, skills, plugins, cron state, sessions, logs, source trees, or memory databases;
- designing an encrypted Restic repository over local, S3-compatible, or rclone-backed storage;
- capturing live SQLite databases safely;
- defining backup retention and integrity gates;
- verifying that a snapshot can restore on a clean machine;
- documenting disaster-recovery credentials and cutover controls.
Do not use as a substitute for service-specific exports, application-level replication, or legal retention policy. Never assume a cloud provider's account recovery replaces independent recovery credentials.
Required tools and operator inputs
Typical prerequisites:
- Restic;
- Git;
- Python with the standard-library
sqlite3module; - rclone only when the chosen backend requires it;
- a credential manager independent of both the backup destination and protected machine.
The operator must define:
- approved source roots;
- encrypted repository endpoint;
- exclusion policy;
- credential-file locations;
- retention schedule;
- verification frequency;
- recovery machine and cutover authority.
This skill does not install tools, create remotes, or request secrets. Authentication material must be entered through trusted local tooling and must never be pasted into an agent conversation.
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 · 250 lines · 52 tokens per session scan A 2c48aa75413e
hermes-backup-recovery is a skill published in the GitHub repository SaikaAco/saika-hermes-skills (2 stars, last pushed 14d ago), licensed MIT. It adds 52 tokens to every session and 2,340 once invoked, about $0.0003 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 skills, from other repositories
hunt-sqli
Hunting skill for sqli vulnerabilities. Built from 12 public bug bounty reports including modern NoSQL injection (Rocket.Chat CVE-2021-22911 MongoDB $regex, Mongoose ORM CVE-2024-53900 $where bypass), modern ORM raw-fragment SQLi (Django CVE-2024-42005, Sequelize GHSA-wrh9-cjv3-2hpw), second-order SOQL injection…
hunt-nosqli
Hunt NoSQL Injection — MongoDB operator injection ($where, $regex, $gt, $ne), CouchDB, Redis command injection, auth bypass via NoSQLi, data dump. Use when target uses MongoDB/Mongoose, CouchDB, Redis, or shows NoSQL error messages.
hunt-supabase
Hunt Supabase exploitation — Supabase anon key discovery in JS bundles, REST API table enumeration with anon key, Row Level Security (RLS) bypass via missing organizationid check, RPC function abuse returning cross-organization data, Storage bucket listing, Auth signUp/signIn with anon key, multi-tenant enumeration…
firebase-supabase-attack
Exploit Firebase/Supabase for data via JS config leak probe.
hermes-mnemosyne
Mnemosyne is Hermes' primary local-first memory engine — SQLite with vector + FTS5 hybrid search, 19+ tools, auto-consolidation, and a standalone CLI. It's a pip-installed plugin (not a built-in toolset) discovered via $HERMESHOME/plugins/mnemosyne/.
db
Run read-only SQL queries against Supabase databases (local or remote). Use when inspecting schema, debugging data, checking migrations, or answering questions about database state.