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 captkernel/Skills_Curator --skill skills-curator-claudeaigit clone --depth 1 https://github.com/captkernel/Skills_CuratorWrote 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/captkernel/skills_curator/skills-curator-claudeai)<a href="https://agentmods.dev/skills/captkernel/skills_curator/skills-curator-claudeai"><img src="https://agentmods.dev/badge/skills/captkernel/skills_curator/skills-curator-claudeai/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/captkernel/skills_curator/skills-curator-claudeai"><img src="https://agentmods.dev/badge/skills/captkernel/skills_curator/skills-curator-claudeai.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 | $0.00128 | $0.03873 |
| Opus 5 | $0.00064 | $0.01937 |
| Sonnet 5 | $0.00026 | $0.00775 |
| Haiku 4.5 | $0.00013 | $0.00387 |
Grade A, and why
skills-curator scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
3. **Gist sync** (power users) — user provides a private Gist ID + PAT, skill fetches via `curl`, patches via `PATCH /gists/{id}`. How it starts
The opening of the file, as written. The whole thing — 319 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skills Curator (claude.ai edition)
Decide once. Re-decide never.
The intelligence layer for Claude skills, adapted for claude.ai (web + desktop). Same judgment model as the Claude Code version — evaluate before installing, persist decisions, recommend by project fit, customize stack-mismatched skills — re-architected for claude.ai's sandbox-per-conversation runtime.
| Claude Code | claude.ai (this edition) | |
|---|---|---|
| Persistence | ~/.claude/skills/registry.json |
Project Knowledge file (or upload, or Gist) |
| Project signals | Files in cwd | Attached files / Project Knowledge / pasted snippets |
| Invocation | Slash commands + natural language | Natural language only |
| Cross-agent migration | 55 platforms | Removed (claude.ai isn't a CLI agent) |
| Customize output | Written to ~/.claude/skills/<fork>/ |
Written to /mnt/user-data/outputs/<fork>.zip |
First activation in a session
The first time the skill activates in a conversation, open with this two-line orientation before answering, then continue with whatever was asked:
🧭 Skills Curator loaded — your intelligence layer for Claude skills (claude.ai edition). I evaluate skills against your actual stack, recommend what fits, and persist decisions so you don't re-evaluate. Working on your request now.
Skip the orientation if you're about to surface concrete picks from a registry the user has already pinned — those are more useful than a generic intro. Don't repeat in later turns of the same conversation.
How persistence works on claude.ai
The sandbox is fresh every conversation. There's no ~/.claude/skills/registry.json that survives across sessions. Three modes, picked in this order based on what the user has set up:
- Project Knowledge (recommended) —
skills_registry.jsonin Project Knowledge is auto-read at session start. After updates, the skill writes/mnt/user-data/outputs/skills_registry.jsonso the user can download and swap. - Upload / download — user attaches the registry to the conversation, skill emits the updated file at session end via
/mnt/user-data/outputs/. - Gist sync (power users) — user provides a private Gist ID + PAT, skill fetches via
curl, patches viaPATCH /gists/{id}.
What ships with it
5 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.
- 11d ago First seen · 319 lines · 128 tokens per session scan A 6886e75f8449
skills-curator is a skill published in the GitHub repository captkernel/Skills_Curator (2 stars, last pushed 18d ago), licensed MIT. It adds 128 tokens to every session and 3,873 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
analytics-strategy
Design measurement frameworks including event taxonomy, KPI hierarchy, dashboard architecture, attribution models, and analytics implementation strategy. Use this skill whenever the user wants to plan analytics, design dashboards, build event taxonomies, define KPIs, set up tracking, or audit existing measurement.…
content-strategy
Develop a content strategy covering editorial positioning, content pillars, formats, calendar, governance, and topical authority planning. Use this skill whenever the user wants to plan a content program, define content pillars, build an editorial calendar, structure topic clusters, set up content governance, or align…
incident-response
Manage active production incidents through detection, triage, mitigation, communication, and resolution with structured roles and decision-making. Use this skill whenever the user has an active incident, a production issue, a service outage, a security incident, or needs to plan incident response procedures. Triggers…
stakeholder-communication
Communicate effectively with stakeholders across functions and seniority levels. Use this skill when writing status updates, preparing executive reviews, sharing technical decisions with non-technical audiences, managing up, communicating bad news, or designing the communication cadence for a project. Triggers on…
agb-begriff-vorformuliert-305
Für AGB Begriff Vorformuliert 305: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: agb-begriff-vorformuliert-305.
review-work
Post-implementation gate review: run manual QA on the real surface yourself, then launch ONE gate reviewer (never a panel) to audit goal, constraints, code quality, security, missed context, and QA evidence. Use before a PR handoff or when the user explicitly asks to review completed work.