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 JansenAnalytics/claudex --skill skill-indexgit clone --depth 1 https://github.com/JansenAnalytics/claudexWrote 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/jansenanalytics/claudex/skill-index)<a href="https://agentmods.dev/skills/jansenanalytics/claudex/skill-index"><img src="https://agentmods.dev/badge/skills/jansenanalytics/claudex/skill-index.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 | $0.00060 | $0.00897 |
| Opus 5 | $0.00030 | $0.00449 |
| Sonnet 5 | $0.00012 | $0.00179 |
| Haiku 4.5 | $0.00006 | $0.00090 |
Grade A, and why
skill-index scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Index
Claudex ships with 160+ skills. Auto-loading by description matching works well for the common case, but sometimes you need to explicitly enumerate what's available — for planning multi-step work, for answering "do we have anything for X", or for spotting gaps.
This skill teaches you how to query the skill catalog without scanning every SKILL.md by hand.
Quick reference
# Where the catalog lives (generated by scripts/skill-index.sh)
INDEX=$HOME/.claude-agent/data/skill-index.json
SKILLS_DIR=$HOME/.claude-agent/.claude/skills
Common queries
# All skills in a category
jq -r '.[] | select(.category == "security") | "\(.name) — \(.description)"' "$INDEX"
# All skills with a specific tag
jq -r '.[] | select(.tags // [] | index("docker")) | .name' "$INDEX"
# Only stable skills (skip experimental/beta when reliability matters)
jq -r '.[] | select(.maturity == "stable") | .name' "$INDEX"
# Skills with external dependencies (need INSTALL.md)
jq -r '.[] | select((.external_deps // []) | length > 0) | "\(.name): \(.external_deps | join(", "))"' "$INDEX"
# Count by category
jq -r '[.[] | .category] | group_by(.) | map({category: .[0], count: length}) | .[] | "\(.count)\t\(.category)"' "$INDEX" | sort -rn
# Search descriptions for a keyword (fallback when category/tag don't match)
jq -r --arg q "$KEYWORD" '.[] | select(.description | test($q; "i")) | "\(.name) — \(.description)"' "$INDEX"
When to use
- Planning a complex task — list relevant skills upfront so you don't reinvent
- Answering "what can Claudex do for X" — give the user a real list, not a hand-wave
- Spotting gaps — if a category has only 1 skill, that's a tell
- Audit/maintenance — find all experimental skills to harden, or deprecated ones to remove
Fallback when the index isn't built
If $INDEX doesn't exist yet (skill-index.sh hasn't run), grep frontmatter directly:
# All skills with a given category
grep -l "^category: security" "$SKILLS_DIR"/*/SKILL.md | xargs -n1 dirname | xargs -n1 basename
# All skill names + descriptions (raw)
for f in "$SKILLS_DIR"/*/SKILL.md; do
awk '/^name:/ {name=$2} /^description:/ {sub(/^description: */, ""); print name " — " $0; exit}' "$f"
done
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.
- 4d ago First seen · 76 lines · 60 tokens per session scan A 7c960a5cce4f
skill-index is a skill published in the GitHub repository JansenAnalytics/claudex (5 stars, last pushed 2mo ago), licensed MIT. It adds 60 tokens to every session and 897 once invoked, about $0.0003 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
skill-finder
Find the right Affitor skill for your goal. Triggers on: "which skill should I use", "find me a skill", "what skills are available", "help me choose a skill", "skill for SEO", "skill for email", "explore skills", "I'm new to Affitor", "what can Affitor do", "search skills", "skill for blog writing", "skill for landing…
auto
Intent-classified router, the front door to OrchestKit and the DEFAULT entry point for any goal-shaped request. Classifies a plain-English goal and routes it to the right specialist skill. Routing is never overhead, so use it even when the target skill seems obvious; skip only when already executing inside another…
find-skills
Discovers, searches, and installs skills from multiple AI agent skill marketplaces (400K+ skills) using the SkillKit CLI. Supports browsing official partner collections (Anthropic, Vercel, Supabase, Stripe, and more) and community repositories, searching by domain or technology, and installing specific skills from…
skill-router
Find the right skill in the PCL standard library and compose several when a task spans domains. Use when the user asks which skill applies, cannot find a capability, wants to know what the library covers, is starting a task that spans several domains, or when the task involves choosing between overlapping skills…
skill-finder
Aktiver Finder/Router für die eigenen lokalen Skills (Analogon zu using-superpowers). IMMER zu Beginn einer nicht-trivialen Aufgabe nutzen, um zu prüfen, ob ein user-Skill passt, und zum richtigen Skill zu routen. Aktiviert sich bei „welcher Skill passt", „gibt es dafür einen Skill", „skill finden", oder generell vor…
autovault-skill
Understand AutoVault-managed skills and how to install or update them. Use when a skill is visible via symlink, when authoring or editing SKILL.md, or before touching /.autovault/skills. Vault writes must go through autovault add-local or MCP proposeskill/updateskill so AutoVault re-signs; never hand-edit vaulted…