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 allcolor/PawFlow-Agents --skill backup-operationsgit clone --depth 1 https://github.com/allcolor/PawFlow-AgentsWrote 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/allcolor/pawflow-agents/backup-operations)<a href="https://agentmods.dev/skills/allcolor/pawflow-agents/backup-operations"><img src="https://agentmods.dev/badge/skills/allcolor/pawflow-agents/backup-operations/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/allcolor/pawflow-agents/backup-operations"><img src="https://agentmods.dev/badge/skills/allcolor/pawflow-agents/backup-operations.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 36 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00037 | $0.00625 |
| Opus 5 | $0.00018 | $0.00313 |
| Sonnet 5 | $0.00007 | $0.00125 |
| Haiku 4.5 | $0.00004 | $0.00063 |
Grade A, and why
backup-operations 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 9d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Backup operations
Passphrase custody — read this before enabling backups
The backup is encrypted with a key derived from the backup_passphrase
secret via scrypt. There is no recovery mechanism if that passphrase is
lost in this first version of the package (no wrap_escrow-style second
key yet, unlike the multi-wrap design sketched for PawFlow's own
encryption-at-rest module). This is the correct guarantee for
confidentiality (nobody — including PawFlow or the cloud provider — can
decrypt without the passphrase), but it means the backup is the exact same
single point of failure as the passphrase itself. Tell the user this in
plain terms before they enable nightly-backup for real data, not only in
this file: "if you lose this passphrase, the backup becomes permanently
unrecoverable, with nothing PawFlow or the cloud provider can do about it."
Recommend writing the passphrase down somewhere durable and offline (or
sharing it with a second trusted person at the firm) rather than storing it
only in one person's head or one password manager entry.
What never needs backing up
Anything already republished as open data by a public source — e.g. the
content reachable through the legal-kb MCP (justicelibre.org) if the
firm.legal-assistant package is also installed — should never be pointed
at by source_path. It is already durably published elsewhere; backing it
up here only wastes storage and upload time for zero recovery value.
What to check before trusting a restore
restore_from_backupreportsfiles_restoredandfiles_failedexplicitly — do not declare a restore successful without checkingfiles_failedis empty.- A decrypt failure on the manifest itself (wrong passphrase, or
destination_rootpointing at a backup written by a different passphrase/package) fails loudly with an explicit error rather than silently producing garbage — if you see that error, stop and confirm the passphrase and destination path with the user rather than retrying with guesses. manifest_timestamplets you restore an older point in time instead of the latest state — useful when the most recent backup captured a mistake (e.g. a file deleted by accident) that an earlier manifest still references.
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.
- 9d ago First seen · 56 lines · 37 tokens per session scan A 9b0776eeb7d0
backup-operations is a skill published in the GitHub repository allcolor/PawFlow-Agents (25 stars, last pushed yesterday), licensed MIT. It adds 37 tokens to every session and 625 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
conversational-ux
Design voice and conversational interfaces — dialog flows, error recovery, and persona. Use when the interface speaks and listens rather than being tapped. For graphical input collection, use form-design.
research-repository
Build a repository that makes findings findable, reusable, and cumulative across teams. Use when the same research keeps getting redone. For synthesising one study, use affinity-diagram.
form-design
Design a form end to end — field order, grouping, validation, and completion. Use when the artifact is a form. For product-wide error strategy use error-handling-ux; for first-run signup use onboarding-design.
peak-end-rule
Apply the Peak-End Rule — a flow is remembered by its most intense moment and its last. Use when designing completion, celebration, or cancellation moments. For sustaining engagement mid-flow, use zeigarnik-effect.
law-of-similarity
Apply the Law of Similarity — shared colour, shape, or size signals that elements belong to one category. Use when signalling relationships across distance. For grouping by position, use law-of-proximity.
law-of-common-region
Apply the Law of Common Region — a shared container, background, or border groups elements regardless of spacing. Use when grouping must survive a tight layout. For grouping by spacing alone, use law-of-proximity.