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 Drizzy07x/Skillquiver --skill handle-host-boundariesgit clone --depth 1 https://github.com/Drizzy07x/SkillquiverWrote 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/drizzy07x/skillquiver/handle-host-boundaries)<a href="https://agentmods.dev/skills/drizzy07x/skillquiver/handle-host-boundaries"><img src="https://agentmods.dev/badge/skills/drizzy07x/skillquiver/handle-host-boundaries/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/drizzy07x/skillquiver/handle-host-boundaries"><img src="https://agentmods.dev/badge/skills/drizzy07x/skillquiver/handle-host-boundaries.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 | $0.00046 | $0.00607 |
| Opus 5 | $0.00023 | $0.00303 |
| Sonnet 5 | $0.00009 | $0.00121 |
| Haiku 4.5 | $0.00005 | $0.00061 |
Grade A, and why
handle-host-boundaries 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 — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Handle Host and Destructive Boundaries
Respond to the capability mismatch before attempting the underlying task.
Hard Stop Before Action
When a named capability is not exposed and the dependent action requires the user's choice, consent, or approval:
- Do not run a command, inspect or modify the workspace, draft a patch, call a dependent tool, or otherwise start the dependent action.
- This stop still applies when the same request tells you to choose, consent, approve, default, or continue on the user's behalf.
- State that the named capability is unavailable, ask the exact pending question directly in plain chat, and end the response.
- Resume only after a later user message supplies the choice or explicit approval. The fallback instruction in the original request is not an answer.
Workflow
- Identify the current host and the named skill or tool from the capabilities actually exposed in the session.
- If it is unavailable, state the exact boundary directly. Do not search for, invoke, or fabricate it.
- Apply the hard stop above before any dependent action. Never invent the user's choice, consent, or approval.
- Do not inspect or modify another host's configuration as a substitute for an unavailable capability, and never propose broader permissions in the current host as a substitute. Explicitly authorized AGENTS.md or CLAUDE.md file maintenance through improve-agent-instructions is allowed when filesystem access is available; unavailable runtime loading remains unverified.
- Preserve the safe underlying goal through a capability that is available. For a simple question, ask it directly in plain chat. If the missing mechanism carries consent or security semantics that chat cannot preserve, stop and request an authorized mechanism.
Destructive roots
For deletion at a drive root, home directory, repository root, workspace root, or a target derived from an unresolved variable or glob:
- Refuse before running any command.
- Explain the risk to the operating system and unrelated data.
- State: "I need the exact narrow target and your explicit authorization before any destructive action." A general cleanup goal is not authorization.
- Offer a read-only inventory when it can help the user choose a safe target.
What ships with it
1 file 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.
- 9d ago First seen · 62 lines · 46 tokens per session scan A 6f78bfd93316
handle-host-boundaries is a skill published in the GitHub repository Drizzy07x/Skillquiver (2 stars, last pushed 17d ago), licensed MIT. It adds 46 tokens to every session and 607 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 2026-08-31.
Other skills, from other repositories
delegate
Let Claude Architect route a versioned implementation spec through the trusted MCP runtime, independently review the Candidate Artifact, record a decision, and integrate only accepted bytes. Use for implementation delegation, Producer selection, or commitment-boundary review.
commit
A guided process for committing code changes to Git. It checks the working tree, follows a conventional commit format, links a task when available, reviews the changes, and asks for approval.
codex
Run the Codex CLI directly in the user's checkout for code analysis, refactoring, or automated editing without Claude Architect's verified delegation lifecycle.
orient
Internal skill for commands. Render the shared orientation snapshot - active task, what's in flight, what's next - tracker-universal. Do not trigger on user conversation; only when a command needs the snapshot.
actor-fetch-personality
Internal skill for commands. Fetch and validate personality from URL or file path for Actor agent. Do not trigger on user conversation - only when commands need personality loading.
x-multi-llm-align
A review process in which two sub-agents examine an API, data format, event schema, or workflow from their separate implementation perspectives. The user passes documents and feedback between them over multiple rounds.