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 regen-coordination/org-os-template --skill skills-curatorgit clone --depth 1 https://github.com/regen-coordination/org-os-templateWrote 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/regen-coordination/org-os-template/skills-curator)<a href="https://agentmods.dev/skills/regen-coordination/org-os-template/skills-curator"><img src="https://agentmods.dev/badge/skills/regen-coordination/org-os-template/skills-curator/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/regen-coordination/org-os-template/skills-curator"><img src="https://agentmods.dev/badge/skills/regen-coordination/org-os-template/skills-curator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00026 | $0.02056 |
| Opus 5 | $0.00013 | $0.01028 |
| Sonnet 5 | $0.00005 | $0.00411 |
| Haiku 4.5 | $0.00003 | $0.00206 |
Grade A, and why
skills-curator 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 8d 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 — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skills Curator
When to Use
Before any non-trivial initiative. Specifically:
- Before
superpowers:writing-plansruns for an implementation plan that introduces new domains (frontend, design system, ML, data pipeline, etc.) - After
superpowers:brainstormingproduces a design spec - When an operator says "what skills should we use", "scope skills for", or asks for a "Phase 0"
- When a new project crosses 2+ specialized domains and the agent stack hasn't been picked
Skip when:
- The initiative is a routine task in an already-equipped project (no new domains)
- The skill stack is locked by an existing convention (e.g., the project's CLAUDE.md mandates specific skills)
Why It Exists
Building well requires the right tools. Picking tools mid-build creates rework and inconsistency. Phase 0 separates deciding what to use from building with it — the same way that brainstorming separates deciding what to build from building it.
This skill produces a single artifact (docs/plans/YYYY-MM-DD-skills-curation.md) that any later phase can audit. It also creates a clean retrospective surface: at v1 of the initiative, every chosen skill gets a promote/improve/drop verdict against measured value.
Procedure
Step 1 — Read the design spec or brief
Read the initiative's design spec (typically at docs/superpowers/specs/YYYY-MM-DD-<topic>-design.md) or the operator's brief. Extract:
- Domains involved (e.g., frontend, design system, color, animation, accessibility, data pipeline, deploy, testing)
- Tech stack constraints (e.g., Astro + React, vanilla, framework-locked)
- Design surface needs (component library, color manipulation, motion, a11y)
- Process needs (TDD, parallel agents, code review)
Step 2 — Identify candidate sources
Default sources to scan:
agentskills.io— community skill marketplaceskills.sh— skill marketplacegithub.com/VoltAgent/awesome-design-md— design.md templates and design-system skillsgithub.com/anthropics/skills— official Anthropic skill catalog- Already-installed superpowers skills (process layer — usually already present)
- Project-local skills at
skills/,.agents/skills/, or instance equivalent
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.
- 8d ago First seen · 222 lines · 26 tokens per session scan A 8074b0b57b5f
skills-curator is a skill published in the GitHub repository regen-coordination/org-os-template (5 stars, last pushed 6d ago), licensed MIT. It adds 26 tokens to every session and 2,056 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 2026-09-03.
Other skills, from other repositories
skypilot-multi-cloud-orchestration
Multi-cloud orchestration for ML workloads with automatic cost optimization. Use when you need to run training or batch jobs across multiple clouds, leverage spot instances with auto-recovery, or optimize GPU costs across providers.
givemeanode-agent-compute
Operate GiveMeANode GPU nodes, batch jobs, storage, and rollout sandboxes through its connected MCP server with bounded spend, durable recovery, and explicit approval for paid or destructive actions.
architecture-diagram
Dark-themed SVG architecture/cloud/infra diagrams as HTML.
makefile-generation
Generates Makefiles with testing, linting, formatting, and automation targets. Use when starting a project or standardizing build automation.
port-mass-scan
Port scan /8-/24 with Masscan+RustScan and nmap banners.
terraform-search-import
Discover existing cloud resources using Terraform Search queries and bulk import them into Terraform management. Use when bringing unmanaged infrastructure under Terraform control, auditing cloud resources, or migrating to IaC.