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 learn-by-exploration/ai-powerhouse --skill agent-routinggit clone --depth 1 https://github.com/learn-by-exploration/ai-powerhouseWrote 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/learn-by-exploration/ai-powerhouse/agent-routing)<a href="https://agentmods.dev/skills/learn-by-exploration/ai-powerhouse/agent-routing"><img src="https://agentmods.dev/badge/skills/learn-by-exploration/ai-powerhouse/agent-routing/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/learn-by-exploration/ai-powerhouse/agent-routing"><img src="https://agentmods.dev/badge/skills/learn-by-exploration/ai-powerhouse/agent-routing.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 | $0.00029 | $0.01290 |
| Opus 5 | $0.00015 | $0.00645 |
| Sonnet 5 | $0.00006 | $0.00258 |
| Haiku 4.5 | $0.00003 | $0.00129 |
Grade A, and why
agent-routing 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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Routing — Which Tool to Use
Read this before reading any other skill description. It will save you 10-15K tokens.
Quick Reference Table
| You want to... | Use this | Notes |
|---|---|---|
| Build a new feature (>2h) | superpowers-writing-plans |
Creates spec + bite-sized task plan |
| Execute a written plan | superpowers-subagent-driven-development |
Spawns workers per task, reviews each |
| Fix a bug | Write failing test first, then ecc-code-reviewer |
TDD loop: red → green → review |
| Debug a mystery failure | superpowers-systematic-debugging |
Root-cause methodology |
| Review code quality | ecc-code-reviewer |
Checks style, correctness, tests |
| Security review | ecc-security-reviewer |
Auth, secrets, injection, OWASP |
| Language-specific review | ecc-<lang>-reviewer |
python, go, rust, typescript, etc. |
| Refactor / clean up | ecc-refactor-cleaner |
Dead code, extract, rename |
| Architecture decision | ecc-architect |
System design, layer assignment |
| Check if similar was built before | mem-mem-search |
Search past sessions first |
| Plan with memory-aware phases | mem-make-plan |
Phased plan with past context |
| Execute multi-agent plan | mem-do |
Run phases with subagents |
| Parallel independent tasks | superpowers-dispatching-parallel-agents |
2+ truly independent workstreams |
| UI/UX design decision | uiux-ui-ux-pro-max |
67 styles, 161 rules |
| Generate a design system | uiux-design-system |
Tokens, components, guidelines |
| Multi-agent orchestration (enterprise) | ruflo-sparc + ruflo-swarm-orchestration |
SPARC methodology + swarm |
| Consensus across agents | ruflo-raft-manager or ruflo-quorum-manager |
Distributed agent coordination |
Decision Tree
What are you doing?
│
├─ PLANNING a new feature or large change
│ ├─ Have you solved something similar before?
│ │ └─ YES → mem-mem-search first, then plan
│ ├─ Solo developer, <1 week work → ecc-planner
│ ├─ Small team OR 1-2 weeks → superpowers-writing-plans (recommended default)
│ ├─ Large scope, enterprise → ruflo-sparc (full SDLC with 17 modes)
│ └─ Need architecture decision first → ecc-architect → then plan
│
├─ IMPLEMENTING (have a plan)
│ ├─ Executing task list → superpowers-subagent-driven-development
│ ├─ Parallel workstreams → superpowers-dispatching-parallel-agents
│ └─ Memory-aware execution → mem-do
│
├─ FIXING a bug
│ ├─ 1. Write test that reproduces the bug (TDD: RED)
│ ├─ 2. Implement fix (TDD: GREEN)
│ ├─ 3. ecc-code-reviewer (verify no regression)
│ └─ Mystery/flaky → superpowers-systematic-debugging first
│
├─ REVIEWING code
│ ├─ General quality → ecc-code-reviewer
│ ├─ Security → ecc-security-reviewer
│ ├─ Language-specific → ecc-<lang>-reviewer
│ └─ UI/UX → gsd-ui-auditor
│
├─ REFACTORING
│ ├─ Dead code / cleanup → ecc-refactor-cleaner
│ └─ Architecture change → ecc-architect first
│
└─ MEMORY & CONTINUITY
├─ "Did we solve this before?" → mem-mem-search
├─ "What did we do last session?" → mem-timeline-report
└─ "Explore codebase efficiently" → mem-smart-explore
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 · 111 lines · 29 tokens per session scan A 7072f3ffb8e3
agent-routing is a skill published in the GitHub repository learn-by-exploration/ai-powerhouse (2 stars, last pushed 2mo ago), licensed MIT. It adds 29 tokens to every session and 1,290 once invoked, about $0.0001 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
impeccable
Create distinctive, production-grade frontend interfaces with high design quality. Generates creative, polished code that avoids generic AI aesthetics. Use when the user asks to build web components, pages, artifacts, posters, or applications, or when any design skill requires project context. Call with 'craft' for…
open
Boot the session, load context from the vault, and surface what matters.
Self-Review
Spawn a reviewer subagent with 4-6 specific verification questions before declaring non-trivial code work done. Triggers when changes are >30 LOC, multi-file, hot-path, prompt-affecting, or genuinely uncertain. Bad asks produce bad answers — this skill forces structured verification questions, not "is this good?".
Skill Audit
List every installed skill, when it was last invoked, how often, and whether the description still matches the trigger patterns the principal actually uses. Flags dead skills for retirement and frequently-needed-but-missing capabilities for skill creation. Pairs with Caddy.
sprite-spec
Iris's sprite design specification skill. Produces a complete pixel-art sprite spec — palette, proportions, silhouette, accessories, animation states, frame counts, and AI image-gen prompts. Returns honesty ledger.
ui-architecture
Iris's new UI surface design skill. Takes a brief for a new screen, component, or design system and produces a complete visual architecture spec — component tree, layout grid, interaction states, breakpoints, tokens. No code.