Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add MadAppGang/magus/plugin install setupWrote 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/madappgang/magus/index-skills)<a href="https://agentmods.dev/skills/madappgang/magus/index-skills"><img src="https://agentmods.dev/badge/skills/madappgang/magus/index-skills/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/madappgang/magus/index-skills"><img src="https://agentmods.dev/badge/skills/madappgang/magus/index-skills.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 | $0.00044 | $0.03468 |
| Opus 5.5 | $0.00018 | $0.01387 |
| Sonnet 5.5 | $0.00009 | $0.00694 |
| Haiku 4.5 | $0.00004 | $0.00347 |
Grade A, and why
index-skills 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 1mo 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 — 297 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Index skills
Renders every skill reachable from the current project into one markdown file, with the number that actually matters attached to each: its listing cost.
Why the cost column exists
Claude Code injects the description of every model-invocable skill into
every turn, budgeted at:
context_tokens x 4 x skillListingBudgetFraction (fraction defaults to 0.01)
There is no 8,000 hard cap — verified against the 2.1.223 binary, where
tBt() computes (contextTokens ?? 200000) * 4 * fraction with no Math.min.
8,000 is what that yields at the 200,000-token fallback, so it is a floor, not a
ceiling: a 1M-context model gets 40,000. --context <tokens> measures against a
specific model.
The budget is global across every installed skill — all plugins, all
marketplaces, plus ~/.claude/skills. It is not per-plugin. The listing
function takes one flat array and compares one total.
When the corpus overflows, Claude Code does not error. It switches from fits
to priority mode and shortens descriptions — stripping exactly the
keywords the matcher needs to route a request. A skill that quietly stopped
firing usually did not break; it got crowded out. The index makes that visible
before it bites.
Because the budget scales with the window, a corpus can fit on the model you
develop against and overflow on the model a user runs. The default here is the
200,000-token floor for that reason: what fits at 200k fits everywhere.
skillListingMaxDescChars separately caps each description at 1536.
A skill carrying disable-model-invocation: true costs zero and stays fully
reachable by explicit /plugin:name. That is the lever for getting back under
budget, and the index shows exactly which skills to pull it on.
Run it
bun ${CLAUDE_PLUGIN_ROOT}/skills/index-skills/scripts/index-skills.ts
The scope is detected from the directory, not guessed from its name:
| Scope | Detected when | Indexes |
|---|---|---|
repo |
.claude-plugin/marketplace.json, or any plugins/<x>/plugin.json |
plugins/*/skills/** and repo-level skills/ — what this marketplace ships |
project |
anything else | .claude/skills, ~/.claude/skills autodiscovery, and every installed plugin — what you can invoke from here |
What ships with it
1 file 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.
- 1mo ago First seen · 297 lines · 44 tokens per session scan A 825cb8aa1bc6
index-skills is a skill published in the GitHub repository MadAppGang/magus (13 stars, last pushed today), licensed MIT. It adds 44 tokens to every session and 3,468 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-04.
Other skills, from other repositories
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…