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 pentoshi007/clai --skill clai-superman-skillgit clone --depth 1 https://github.com/pentoshi007/claiWrote 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/pentoshi007/clai/clai-superman-skill)<a href="https://agentmods.dev/skills/pentoshi007/clai/clai-superman-skill"><img src="https://agentmods.dev/badge/skills/pentoshi007/clai/clai-superman-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/pentoshi007/clai/clai-superman-skill"><img src="https://agentmods.dev/badge/skills/pentoshi007/clai/clai-superman-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 | $0.00079 | $0.02129 |
| Opus 5.5 | $0.00032 | $0.00852 |
| Sonnet 5.5 | $0.00016 | $0.00426 |
| Haiku 4.5 | $0.00008 | $0.00213 |
Grade A, and why
clai-superman-skill 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 11d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
clai Superman
Win by establishing what an attacker can actually do, why, and what remains unknown. Optimize for verified impact and defensible coverage, not tools executed, findings counted, or confidence theater. This is a decision system, not a claim of omniscience or guaranteed zero-day discovery.
Enter at the right depth
Honor the requested mode and boundary: explanation means explain; plan means research and plan; a specific check means that check; an engagement means execute through validation and closure. Do not turn a question into active testing or a small task into an engagement. Use existing authorization and scope; this skill neither grants permissions nor bypasses clai's gates. Keep proof non-destructive unless a more invasive impact is explicitly in scope.
For an engagement, establish the objective, in/out-of-scope assets and identities, allowed impact, vantage points, available accounts/artifacts, evidence destination, and real resource limits. Recover these from existing context before asking. Treat missing access as a coverage gap, not a reason to declare security. Separate testing, adversary emulation, and incident response: their success criteria differ.
The investigation loop and persistence/proof discipline below govern EVERY security task and domain, including technologies absent from this library. A domain guide adds expertise; it never replaces that discipline. When a lead crosses into unfamiliar territory, retain the parent objective and coverage frontier, research the new mechanism, adapt the experiment and keep pursuing all material requested outcomes. Do not reset to shallow scanner use, stop at a domain boundary, or confuse lack of remembered knowledge with a dead end.
Load only the relevant depth
These references are the specialized parts of this skill, not optional background once applicable. While the target type is unknown, you may read general behavioral guidance such as operations, evidence and closure or sources to guide discovery; other relevant guides are optional at that stage. Do not guess a target type just to select a guide.
What ships with it
14 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.
- references/ai-agents.md 6.3 KB
- references/cloud-platform.md 5.9 KB
- references/code-supply-chain.md 6.7 KB
- references/crypto-contracts.md 4.9 KB
- references/evidence-reporting.md 8.3 KB
- references/identity-ad.md 6.5 KB
- references/mobile-client.md 6.2 KB
- references/novel-research.md 11 KB
- references/operations.md 9.9 KB
- references/security-operations.md 5.6 KB
- references/sources.md 9.0 KB
- references/systems-protocols.md 6.3 KB
- references/web-api.md 9.0 KB
- references/wireless-iot-ot.md 5.8 KB
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.
- 11d ago First seen · 74 lines · 79 tokens per session scan A 422f0f86c0c6
clai-superman-skill is a skill published in the GitHub repository pentoshi007/clai (18 stars, last pushed 3d ago), licensed MIT. It adds 79 tokens to every session and 2,129 once invoked, about $0.0003 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 2026-10-24.
Other skills, from other repositories
orca-emulator-android
Android device and emulator control from inside Orca over adb, with the live device view in Orca's emulator pane. Use when driving an adb-connected emulator or phone on Windows, Linux, or macOS: booting AVDs, taps, swipes, typing, hardware buttons, rotation, app install and launch, runtime permissions, the…
ralplan
Consensus planning entrypoint that auto-gates vague ralph/autopilot/team requests before execution.
pr
Draft a PR body from OMC's paper trail — the smallest visual that proves the change, evidence consumed from the verify protocol (never re-collected), reversibility from the ADR test on the diff, glossary language throughout.
remember
Review reusable project knowledge and decide what belongs in project memory, notepad, or durable docs.
thisWeek
Resolve "thisWeek" to a concrete ISO date range relative to your run time — this week so far (Monday → today). Returns inclusive civil dates plus exact UTC instants so you have temporal context without computing dates by hand. Read-only: no writes, no network. Use before a week-to-date task (this week's activity…
southwest
Search Southwest Airlines fares and points pricing via Patchright browser automation. SW is not in any GDS or API. Covers all fare classes, Companion Pass value, and fare drop monitoring.