agentmods.dev

tentaflake: Skill for Claude Code

.agents/skills/handle-the-host/SKILL.md

handle-the-host is a skill for Claude Code, Codex from timfewi/tentaflake. It costs 20 tokens per session (454 once invoked), scanned B, original, MIT.

A guide for connecting to and maintaining a tentaflake machine over Tailscale SSH. Tailscale creates a private network between approved devices, so the machine does not need an open public SSH port.

In plain words
What is it for?
Use it to connect to a deployed machine, inspect its NixOS and containers, rebuild its configuration, or run commands that require elevated access.
Why use it?
It provides a standard path for inspecting the machine, checking its agent containers, rebuilding NixOS, and debugging remote problems.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is timfewi/tentaflake's own configuration. It tells Claude Code and Codex how to work on tentaflake itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything tentaflake configures →

not rated 32repo changed 4d ago B scan 20 tokens original MIT
View source ↗ timfewi/tentaflake tentaflake.dev
Reuse

Borrowing it

Nothing to install: this file belongs to timfewi/tentaflake. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/timfewi/tentaflake/main/.agents/skills/handle-the-host/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/timfewi/tentaflake

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for handle-the-host

README.md
[![agentmods](https://agentmods.dev/badge/skills/timfewi/tentaflake/handle-the-host/github.svg)](https://agentmods.dev/skills/timfewi/tentaflake/handle-the-host)
Your own site
<a href="https://agentmods.dev/skills/timfewi/tentaflake/handle-the-host"><img src="https://agentmods.dev/badge/skills/timfewi/tentaflake/handle-the-host/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.

agentmods 80×15 button for handle-the-host

Your own site · 80×15
<a href="https://agentmods.dev/skills/timfewi/tentaflake/handle-the-host"><img src="https://agentmods.dev/badge/skills/timfewi/tentaflake/handle-the-host.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 20 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 454 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00020 $0.00454
Opus 5.5 $0.00008 $0.00182
Sonnet 5.5 $0.00004 $0.00091
Haiku 4.5 $0.00002 $0.00045

Measured 4d ago against content hash 9e707880cc73, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

handle-the-host scanned grade B with 1 finding 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 4d 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.

<admin>@<host>`; an interactive sudo session may need `ssh -t`). Do not add
.agents/skills/handle-the-host/SKILL.md · 35 lines

What it actually says

Handle the host

  1. Resolve the operator-supplied host/account and existing authorization before mutations. Preserve authentication/recovery access. Local management flags do not prove enrollment or remote grants; follow management policy.
  2. Connect through the approved private path (for Tailscale, tailscale ssh <admin>@<host>; an interactive sudo session may need ssh -t). Do not add passwordless sudo, Serve/Funnel or firewall holes to repair a connection.
  3. Read tentaflake status, health and doctor --security. Resolve canonical IDs, units and state from /etc/tentaflake/agents.tsv, backend/flake from /etc/tentaflake/cli.conf. Never assume runtime prefixes or /etc/nixos.
  4. Bound logs with journalctl -u <exact-unit> --since '1 hour ago' -n 100 --no-pager. Never dump OCI environments or credentials. --hide redacts diagnostic names; other logs still need privacy review.
  5. Perform only the authorized operation. Prefer tentaflake start|stop|restart <id>; stop includes loaded brokers. Scaffolds refuse execution. Build/review updates before authorized activation; quota migration, rollback, publication and credential rotation require authority covering their target/action.
  6. Check affected services/application behavior afterward and report evidence gaps. Host readiness is not provider/vendor acceptance or Research VPN readiness. See operations.

For the optional host API, use canonical IDs, separate action/log/worker grants and original request IDs after lost replies. Draft configuration never applies itself. Review complete worker argv/digest; first decision wins, approval preserves offline authority, and queued drain is not execution success. Never kill/restart a worker just to force a drain.

Changes

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.

  1. 4d ago Changed · -30 lines · -3 tokens per session 9e707880cc73
  2. 1mo ago Changed · -119 lines · -18 tokens per session 57b3537dbed6
  3. 2mo ago First seen · 184 lines · 41 tokens per session scan B eef72edd8cfd

Subscribe to this mod's changes

handle-the-host is a skill published in the GitHub repository timfewi/tentaflake (32 stars, last pushed yesterday), licensed MIT. It adds 20 tokens to every session and 454 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

DebuggingDevOps and cloudagentscybersecurityinfrastructure-as-codelinuxnix-flake
Related

handle-the-host compared with skills from other repositories

handle-the-host next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
handle-the-hosttimfewi/tentaflakeSkill32yesterdayMITB20Claude Code, Codex
analyzing-linux-elf-malware26zl/cybersec-toolkitSkill894d agoMITB88Claude Code
analyzing-linux-elf-malwaremarysatasselshaped667/skills-collection-1Skill123d agoMITB88Claude Code, Codex
analyzing-linux-elf-malwarepinkpixel-dev/skills-collection-1Skill92mo agoApache-2.0B88Claude Code, Codex
analyzing-linux-kernel-rootkitsmarysatasselshaped667/skills-collection-1Skill123d agoMITB65Claude Code, Codex
analyzing-linux-elf-malwareMikaru0Mystic/sectinelSkill124mo agoApache-2.0B88Claude Code
analyzing-linux-kernel-rootkitspinkpixel-dev/skills-collection-1Skill92mo agoApache-2.0B65Claude Code, Codex