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 tolgakisaogullari/SumelaOS --skill using-superpowersgit clone --depth 1 https://github.com/tolgakisaogullari/SumelaOSWrote 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/tolgakisaogullari/sumelaos/using-superpowers)<a href="https://agentmods.dev/skills/tolgakisaogullari/sumelaos/using-superpowers"><img src="https://agentmods.dev/badge/skills/tolgakisaogullari/sumelaos/using-superpowers/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/tolgakisaogullari/sumelaos/using-superpowers"><img src="https://agentmods.dev/badge/skills/tolgakisaogullari/sumelaos/using-superpowers.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 | $0.00037 | $0.02306 |
| Opus 5 | $0.00018 | $0.01153 |
| Sonnet 5 | $0.00007 | $0.00461 |
| Haiku 4.5 | $0.00004 | $0.00231 |
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 10d 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<execution_workflow> Run this dispatch loop BEFORE every response. Do NOT skip it for "simple" tasks. EXCEPTION: When dispatched as a focused task subagent, skip this skill.
STEP 1 — Authority hierarchy (resolve conflicts)
Order: user explicit instructions → .sumela/sumela-prompt.md → loaded skill bodies → .sumela/rules/*.md → IDE default. User instructions ALWAYS override; the user is in control. If a skill body and the prompt file disagree on session bootstrap or signal capture, the prompt file wins. If a rule contradicts a loaded skill workflow, the skill wins for that workflow phase.
STEP 2 — Signal capture from previous turn (silent)
Apply .sumela/sumela-prompt.md <signal_capture> exactly. High/medium-confidence correction, confirmation, decision, friction, challenge, resolution, or preference signals load self-improvement-curator and create pending queue entries. (resolution = a bug/problem the agent fixed on its own — capture the generalized lesson, not the instance; preference = a proactive standing user instruction.) Mutations still flow only through /evolve.
STEP 3 — Information gap check (silent, BUT enforced via canonical contract)
Before answering, ask: "Do I need context I don't already have?" Apply the canonical <information_gap_routing> block BEFORE drafting.
For deep workflows (ingest, code-commit, lint) or when multi-collection Qdrant routing is needed (wiki_pages, code_chunks), load using-second-brain and follow its INFORMATION GAP RESOLUTION section.
NEVER skip Tier-2 routing for matching call-graph/structural questions (FAMILY B); Tier-1 (FAMILY A session history) is best-effort — skip when chat_history is known-empty.
STEP 3b — Proactive Impact Analysis (silent, before code changes)
WHEN: Before modifying any function, class, method, or file — if the graphify-code-graph plugin is active (.sumela/memory-plugins/graphify-code-graph/scripts/query-graph.py exists).
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.
- 10d ago First seen · 107 lines · 37 tokens per session scan A 690f095242d4
using-superpowers is a skill published in the GitHub repository tolgakisaogullari/SumelaOS (4 stars, last pushed 15d ago), licensed MIT. It adds 37 tokens to every session and 2,306 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…