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 flonat/flonat-research --skill tailscale-mosh-recovergit clone --depth 1 https://github.com/flonat/flonat-researchWrote 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/flonat/flonat-research/tailscale-mosh-recover)<a href="https://agentmods.dev/skills/flonat/flonat-research/tailscale-mosh-recover"><img src="https://agentmods.dev/badge/skills/flonat/flonat-research/tailscale-mosh-recover/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/flonat/flonat-research/tailscale-mosh-recover"><img src="https://agentmods.dev/badge/skills/flonat/flonat-research/tailscale-mosh-recover.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 | $0.00069 | $0.03976 |
| Opus 5 | $0.00034 | $0.01988 |
| Sonnet 5 | $0.00014 | $0.00795 |
| Haiku 4.5 | $0.00007 | $0.00398 |
Grade D, and why
tailscale-mosh-recover scanned grade D with 2 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 8d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
sudo rm -f /usr/local/bin/tailscale Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
sudo rm -rf /Applications/Tailscale.app How it starts
The opening of the file, as written. The whole thing — 267 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tailscale + Mosh Recovery (Headless Mac mini)
Problem
After a Tailscale update or daemon restart on a headless Mac mini, mosh sessions break. Common symptoms (any combination):
tailscale statusreturns:failed to connect to local Tailscale service; is Tailscale running?mosh <host>returns:could not get canonical name for <host>: nodename nor servname provided, or not known, thenConnection closed by UNKNOWN port 65535, thenDid not find remote IP address (is SSH ProxyCommand disabled?).- Tailscale GUI app CLI returns:
Tailscale.CLIError error 1. which tailscalereports a path that does not actually exist on disk.tailscale upregisters the machine as<hostname>-1(a duplicate of the original node — IP changed).
The two underlying problems are causally linked: Tailscale daemon trouble forces a re-auth → new Tailscale IP → existing mosh-server processes are bound to the old IP and become unreachable.
Context / Triggers
| Sign | Likely cause |
|---|---|
Mac mini's tailscale status says daemon not running |
GUI app daemon needs a logged-in user session — won't run headless |
which tailscale returns a path that ls says doesn't exist |
Shell PATH cache + missing symlink (often the Homebrew symlink dropped during update) |
Two Tailscale installs: GUI app at /Applications/Tailscale.app AND Homebrew Cellar |
Dual install — one's daemon is fighting for the socket |
mosh fails only after a working tailscale up re-registration |
Stale mosh-server processes bound to the prior Tailscale IP |
Old hostname offline + new hostname <name>-1 in admin console |
Re-auth created a new node; old one is stale |
Solution
Work in this order: Layer 1 (Tailscale daemon) then Layer 2 (mosh cleanup). If only mosh is broken and tailscale status is healthy, skip Layer 1.
Layer 1: Tailscale daemon health (headless Mac mini)
The headless constraint: the standalone Tailscale.app GUI bundle's daemon needs an active user session. On a headless Mac mini (no monitor, no auto-login), the GUI daemon never starts. The right setup for headless is Homebrew's tailscale package run as a launchd service — it's a system service that survives reboots without any logged-in user.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 8d ago First seen · 267 lines · 69 tokens per session scan D aa111c1a5d36
tailscale-mosh-recover is a skill published in the GitHub repository flonat/flonat-research (133 stars, last pushed 17d ago), licensed MIT. It adds 69 tokens to every session and 3,976 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it D with 2 findings (asks for root, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
fin-paper-convert
Compile LaTeX to PDF and convert to target journal format.
fin-paper-plan
Generate structured paper outline adapted to target journal.
doc-audit
Evaluate one project document in detail — a workbook section, big picture, strategy map, handoff message, paper, brief, or primer — without editing it. Runs the mechanical lint, builds a claim ledger, types every headline against the eight claim statuses in CLAUDE.md, traces cited evidence to the scripts and logs that…
latex-compile
Compile a LaTeX document and fix every error plus aesthetic issue (overfull/underfull boxes, widows, alignment, fonts) for a clean PDF and log. Use this instead of running pdflatex/latexmk manually — it avoids the latexmk stale-log trap and silent grep failures on binary log output, and it reformats rather than…
claim-audit
Audit what a passing script actually established, before writing any prose about it — build the computed-object ledger, rewrite every check's label as the weakest statement that makes its body pass, and separate the verdict on someone else's work from your own new claim. Run after the script passes and BEFORE the…
nb-to-wolfbook
Convert Mathematica .nb or .m files to Wolfbook .wb format so they open and run in VS Code. Use when bringing existing .nb/.m files into Wolfbook, or to make an existing .wb bridge-safe.