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 GreenLv/skillferry --skill setup-skillferrygit clone --depth 1 https://github.com/GreenLv/skillferryWrote 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/greenlv/skillferry/setup-skillferry)<a href="https://agentmods.dev/skills/greenlv/skillferry/setup-skillferry"><img src="https://agentmods.dev/badge/skills/greenlv/skillferry/setup-skillferry/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/greenlv/skillferry/setup-skillferry"><img src="https://agentmods.dev/badge/skills/greenlv/skillferry/setup-skillferry.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 | $0.00040 | $0.00644 |
| Opus 5.5 | $0.00016 | $0.00258 |
| Sonnet 5.5 | $0.00008 | $0.00129 |
| Haiku 4.5 | $0.00004 | $0.00064 |
Grade A, and why
setup-skillferry 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 2mo 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
setup-skillferry
Set up and keep a portable agent workspace healthy with skillferry: one versioned, Git-friendly definition of skills, global rules, and MCP connection templates that renders into Codex, Claude Code, and DeepSeek Harness (DSH) — without ever copying secrets or runtime state.
When to use
- Installing skillferry on a new machine or after a reinstall.
- Adding a new agent (target) to an existing workspace.
- Diagnosing
skillferry doctorexit codes 1/2/3. - Deciding whether an asset belongs in the workspace or stays machine-local.
Workflow
- Install:
pipx install skillferry(orpython -m pip install skillferry). Confirm withskillferry --version. - Create or fetch a workspace:
skillferry init my-workspace, or clone the private Git repository that holds your workspace definition. - Preview:
skillferry planin the workspace root. Read the portability grade for every asset —native,translated,degraded,manual,unsupported— and resolve every conflict before applying. - Apply:
skillferry apply. The tool backs up every changed file (recoverable under the local state directory) and writes only files it owns, tracked in a per-path hash ledger. - Verify:
skillferry doctormust exit 0. Exit 2 means safe drift (apply), exit 3 means a human decision (read the conflict reasons). - Check in: commit workspace changes to Git; pull on other machines and
re-run
apply.
Rules of thumb
- Anything a machine owns (auth, sessions, caches, sqlite state, absolute
machine paths) never belongs in the workspace.
[protect]exists to make that refusal explicit. - Secrets are references, not values: MCP env entries are
secret:env/NAMEorsecret:file/PATH. Each machine supplies the real values locally; the shareable export (skillferry export <destination>) never expands them. - The workspace is target-neutral. Use
overlays/platform/*.tomlfor OS differences andoverlays/target/*.tomlfor agent differences — never fork the workspace per agent.
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.
- 2mo ago First seen · 58 lines · 40 tokens per session scan A f9eadc4e8190
setup-skillferry is a skill published in the GitHub repository GreenLv/skillferry (0 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 40 tokens to every session and 644 once invoked, about $0.0002 per session on Opus 5.5. 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.
setup-skillferry compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| setup-skillferryGreenLv/skillferry | Skill | 0 | 2mo ago | Apache-2.0 | A | 40 | Claude Code, Codex |
| feishuHmbown/CodeWhale | Skill | 41k | today | MIT | A | 33 | Claude Code, Codex |
| interviewHmbown/CodeWhale | Skill | 41k | today | MIT | A | 40 | Claude Code, Codex |
| refocusingmvschwarz/openrig | Skill | 8.7k | yesterday | Apache-2.0 | A | 59 | Claude Code |
| recipe-create-meet-spacegoogleworkspace/cli | Skill | 32k | 5d ago | Apache-2.0 | A | 18 | Claude Code, Codex |
| log-error-digestzebbern/claude-code-guide | Skill | 4.7k | yesterday | MIT | A | 71 | Claude Code, Codex |
| code-documenterzebbern/claude-code-guide | Skill | 4.7k | yesterday | MIT | A | 39 | Claude Code, Codex |