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 steffenpharai/skyward --skill clawhub-skillgit clone --depth 1 https://github.com/steffenpharai/skywardWrote 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/steffenpharai/skyward/clawhub-skill)<a href="https://agentmods.dev/skills/steffenpharai/skyward/clawhub-skill"><img src="https://agentmods.dev/badge/skills/steffenpharai/skyward/clawhub-skill/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/steffenpharai/skyward/clawhub-skill"><img src="https://agentmods.dev/badge/skills/steffenpharai/skyward/clawhub-skill.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 | $0.00058 | $0.01029 |
| Opus 5 | $0.00029 | $0.00515 |
| Sonnet 5 | $0.00012 | $0.00206 |
| Haiku 4.5 | $0.00006 | $0.00103 |
Grade A, and why
skyward 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.
The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
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 · 71 lines · 58 tokens per session scan A c56e18ea233c
skyward is a skill published in the GitHub repository steffenpharai/skyward (1 stars, last pushed 2mo ago), with no licence file. It adds 58 tokens to every session and 1,029 once invoked, about $0.0003 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
werewolf-6p
Six-player Werewolf rules for a permanent Agent host, with the user choosing to join the randomized player pool or spectate.
avalon-8-10p
Eight-to-ten-player Avalon rules for a permanent Agent host, with the user choosing to join the randomized player pool or spectate.
review
/review — the unified review gate. Use when the user says '/review', '/review design', '/review security', '/review gates', '/review ultra', 'review the UI', 'check design fidelity', 'verify the redesign', 'security review', 'is this safe to merge', 'check for vulnerabilities', 'review the diff', 'review the agent's…
backlog-migrate
Use when a project's backlog has drifted — '/backlog-migrate', 'the backlog status is wrong/unreliable', 'we keep re-picking work that's already done', 'backlog.md is huge / hundreds of KB', 'clean up the backlog', 'too many sprint folders', 'migrate the backlog to the new format', or after adopting the open/wip enum…
onboard
Use right after install.sh — '/onboard', 'how do I get started', 'set up the workflow', 'onboard the project'. Auto-generates the project-understanding docs the orchestrator + every dispatched agent read: the ARCHITECTURE map (docs/setup/codebase-orientation.md), the CONVENTIONS reference…
recover
Safely recover from partial-dispatch failures, orphan worktrees, mid-merge aborts, accidental main commits, and lost branches. Inventories git state, classifies the failure mode with the user's confirmation, then walks through the recovery options for that class with explicit per-step confirmation. Use when the user…