fused-render-index

fused-render-index is a skill for Claude Code, Codex from fusedio/fused-render. It costs 36 tokens per session (1,813 once invoked), scanned A, original, MIT.

A machine-wide index of files and directories stored in Parquet format, with JavaScript and DuckDB ways to query it. It is built by a background scan and can be searched without walking the filesystem.

In plain words
What is it for?
Build file search boxes, paging result tables, disk-usage summaries, file-type breakdowns, or bulk SQL and analytical queries over the filesystem index.
Why use it?
It avoids repeatedly scanning or checking huge numbers of files, which makes machine-wide searches and summaries more practical.

Skill for Claude CodeCodex

Part of the fused-render plugin — 15 skills shipped together

Install

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.

agentmods
npx agentmods add skills/fusedio/fused-render/fused-render-index
Any agent
npx skills add fusedio/fused-render --skill fused-render-index
Clone the repo
git clone --depth 1 https://github.com/fusedio/fused-render

Made for: Claude Code, Codex.

Or install fused-render, the plugin that ships this one along with the rest of its 15 skills.

Wrote 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.

agentmods badge for fused-render-index

README.md
[![agentmods](https://agentmods.dev/badge/skills/fusedio/fused-render/fused-render-index.svg)](https://agentmods.dev/skills/fusedio/fused-render/fused-render-index)
Your own site
<a href="https://agentmods.dev/skills/fusedio/fused-render/fused-render-index"><img src="https://agentmods.dev/badge/skills/fusedio/fused-render/fused-render-index.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,813 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00036 $0.01813
Opus 5 $0.00018 $0.00907
Sonnet 5 $0.00007 $0.00363
Haiku 4.5 $0.00004 $0.00181

Measured yesterday against content hash f544dcd53788, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

fused-render-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 yesterday.

The scan reads SKILL.md. This mod also ships 1 executable file (reader.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/fused-render-index/SKILL.md · 87 lines

How it starts

The opening of the file, as written. The whole thing — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.

The file index

fused-render keeps parquet index of filesystem (one row per file, one per dir). Read it, don't os.walk/find/per-row stat. Three ways in:

Need Path
Interactive UI reads (search box, tiles, table) fused.fileIndex.* (JS)
Bulk/analytical Python (aggregate, join, pandas) duckdb over parquet directly
Index management (scan, roots/ignore, repos) raw fetch + X-Fused: 1 on POSTs

Readiness rule (the one that matters)

Zero rows means BOTH "no matches" and "no index yet". Rendering second as first = silent lie this design exists to prevent. Both JS calls resolve with ready: {indexed, scanning, stale, reason} (reason: no-index / not-covered / null — outdated is a /api/git-repos value only, never on the bridge); Python reader returns (None, None) for empty store. indexed: false → "building / not indexed", never "no results". stale never means "matches fs" — index always slightly behind.

JS: fused.fileIndex

Two methods, whole bridge:

  • search({root, q, limit}) — one folder's corpus, /api/fs/walk entry shape + covered, fresh, age_s, truncated. Per-keystroke cheap. covered: false = 200 + a state, not error.
  • query({sql, limit}) — ONE read-only SQL statement over views files, dirs{columns, rows (positional arrays), truncated}. limit default 200, cap 5000. Totals, breakdowns, path matches — all query.

Facts:

  • No bind parameters — quote user strings yourself, double '. Guard (fused_render/index/guarded_query.py): one statement, read-only types, two views only, 10 s wall clock, duckdb errors surface verbatim as 400 (show them).
  • Failures reject Error with .message (duckdb/server text), .type, .status — render .message.
  • Index calls not superseded like runPython's: slower earlier keystroke's reply can land last. Guard own renders (below).
  • Page of rows ≠ match count — ask count(*) separately to page.
  • Not on bridge (raw fetch, POSTs need X-Fused: 1): /api/index/scan, /api/index/scan-folder, /api/index/cancel, /api/index/rank, /api/index/config, /api/index/status, /api/index/stats, /api/index/delete, /api/index/ask (spends AI credits — button, not debounce), GET /api/git-repos. /api/index/status's error field = data (last scan's failure), not throw.

Read the full file on GitHub · 87 lines

Files

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.

Changes

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.

  1. yesterday Changed · -271 lines · -24 tokens per session f544dcd53788
  2. 5d ago First seen · 358 lines · 60 tokens per session scan A b85336df3feb

Subscribe to this mod's changes

fused-render-index is a skill published in the GitHub repository fusedio/fused-render (11 stars, last pushed today), licensed MIT. It adds 36 tokens to every session and 1,813 once invoked, about $0.0002 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

microsoft/ai-agents-for-beginners · 200 tokens

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…

vercel/next.js · 95 tokens

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.

microsoft/vscode · 53 tokens

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…

microsoft/vscode · 71 tokens

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…

vercel/next.js · 83 tokens