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 Azzygoatcoder/agent-useful-skills --skill using-superpowersgit clone --depth 1 https://github.com/Azzygoatcoder/agent-useful-skillsWrote 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/azzygoatcoder/agent-useful-skills/using-superpowers)<a href="https://agentmods.dev/skills/azzygoatcoder/agent-useful-skills/using-superpowers"><img src="https://agentmods.dev/badge/skills/azzygoatcoder/agent-useful-skills/using-superpowers.svg" alt="Measured on agentmods" 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 | $0.00032 | $0.00556 |
| Opus 5 | $0.00016 | $0.00278 |
| Sonnet 5 | $0.00006 | $0.00111 |
| Haiku 4.5 | $0.00003 | $0.00056 |
Grade A, and why
using-superpowers 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 6d 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The Rule
Check whether a skill clearly applies before acting on a task. When one does, invoke it — and say so.
Before entering plan mode: only use the optional brainstorming/planning flow when the task is genuinely ambiguous or large. Small, well-specified tasks skip it.
Then announce "Using [skill] to [purpose]" and follow the skill exactly. If it has a checklist, create a todo per item.
Proportion matters. Skill ceremony is a tool, not a tax. Small, unambiguous tasks don't need the full process — use subagent-driven-development's lightweight path or just do the fix. Don't force a heavyweight skill onto something that's clearly a quick fix.
Skill Priority
When multiple skills apply, process skills come first — they set the approach, then implementation skills (frontend-design, etc.) carry it out. Brainstorming and systematic-debugging are Superpowers' most common process skills, but the rule holds for any of them.
- "Let's build X" → if large/ambiguous, use the optional planning flow first; otherwise implement directly.
- "Fix this bug" → superpowers:systematic-debugging first, then domain skills.
Worth a Second Look
These thoughts are signals to check whether a skill genuinely applies — not automatic triggers:
| Thought | Check |
|---|---|
| "I need more context first" | A skill might tell you HOW to gather it. |
| "Let me explore the codebase first" | Skills can guide the exploration. |
| "This doesn't need a formal skill" | Ask: would the skill's discipline prevent a real mistake here? |
| "I remember this skill" | Skills evolve — read the current version if you invoke it. |
If the check comes back no, proceed without it. The point is noticing, not guilt.
Platform Adaptation
If your harness appears here, read its reference file for special instructions:
- Codex:
references/codex-tools.md - Pi:
references/pi-tools.md - Antigravity:
references/antigravity-tools.md
What ships with it
4 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.
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.
- 6d ago First seen · 51 lines · 32 tokens per session scan A d90b9d40f8ea
using-superpowers is a skill published in the GitHub repository Azzygoatcoder/agent-useful-skills (6 stars, last pushed 8d ago), licensed MIT. It adds 32 tokens to every session and 556 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
dsh-plugin-dev
An authoritative development guide for DeepSeek Harness plugins. DeepSeek Harness is a system where models, tools, services, events, and adapters are built as plugins.
dsh-plugin-client
A development guide for the browser interface of a DSH plugin, including its package structure, registered interface locations, and build setup.
dsh-plugin-dev
A guide for creating and debugging DeepSeek Harness plugins, which are add-ons packaged as npm modules with configuration files.
dsh-plugin-i18n
A pattern for giving a DSH plugin’s user interface English and Chinese text that changes immediately when the selected language changes.
dsh-dependency-audit
A guide for reviewing and upgrading project dependencies, which are third-party packages the project relies on. It covers security warnings, installation scripts, lock files, breaking changes, tests, rollback plans, and reducing unnecessary dependencies.
dsh-git-commit
A Git commit guide for writing standardised commit messages and performing basic checks before committing code. Git commits are saved checkpoints in a project’s history.