fzf

fzf is a skill for Claude Code from danielsimonjr/fzf-mcp. It costs 94 tokens per session (716 once invoked), scanned A, original, MIT.

A playbook for using fzf, a command-line tool that ranks approximate matches, through an MCP server. It covers filtering a list, finding file names, and searching file contents when exact matching is not suitable.

In plain words
What is it for?
Use it to fuzzy-filter an existing list, search file names under a directory, or search file contents with optional file patterns. It does not add tools itself; it guides use of the server’s existing tools.
Why use it?
It helps locate files, text, or candidates despite typos, partial words, or uncertain names. The playbook also helps choose between fuzzy matching and exact or indexed lookup.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the fzf-mcp plugin — 1 skill, 1 MCP server shipped together

Good fit Use it to fuzzy-filter an existing list, search file names under a directory, or search file contents with optional file patterns. It does not add tools itself; it guides use of the server’s existing tools.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/danielsimonjr/fzf-mcp/fzf
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.

Any agent
npx skills add danielsimonjr/fzf-mcp --skill fzf
Clone the repo
git clone --depth 1 https://github.com/danielsimonjr/fzf-mcp

Made for: Claude Code.

Or install fzf-mcp, the plugin that ships this one along with the rest of its 1 skill, 1 MCP server.

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 fzf

README.md
[![agentmods](https://agentmods.dev/badge/skills/danielsimonjr/fzf-mcp/fzf/github.svg)](https://agentmods.dev/skills/danielsimonjr/fzf-mcp/fzf)
Your own site
<a href="https://agentmods.dev/skills/danielsimonjr/fzf-mcp/fzf"><img src="https://agentmods.dev/badge/skills/danielsimonjr/fzf-mcp/fzf/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.

agentmods 80×15 button for fzf

Your own site · 80×15
<a href="https://agentmods.dev/skills/danielsimonjr/fzf-mcp/fzf"><img src="https://agentmods.dev/badge/skills/danielsimonjr/fzf-mcp/fzf.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 94 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 716 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00094 $0.00716
Opus 5 $0.00047 $0.00358
Sonnet 5 $0.00019 $0.00143
Haiku 4.5 $0.00009 $0.00072

Measured 10d ago against content hash 673ef23d8266, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

fzf 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 10d 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.

skills/fzf/SKILL.md · 31 lines

How it starts

The opening of the file, as written. The whole thing — 31 lines — stays where its author put it; the contents beside it link to each section on GitHub.

fzf

A judgment layer over the fzf-mcp server's 3 tools — fuzzy, typo-tolerant matching backed by fzf, the command-line fuzzy finder. This skill adds no tools of its own: every action below is one of the server's existing MCP tools. Its job is to steer you toward the right tool for the shape of the input (a list you already have vs. a directory tree vs. file contents), and to flag when fzf is the wrong choice because an indexed/exact lookup would be faster.

Skill root: this skill ships inside the fzf-mcp plugin (repo danielsimonjr/fzf-mcp, skills/fzf/). Slash trigger: /fzf.

Tool map

Tool Purpose
fuzzy_filter Rank/filter a candidate list you already have in hand (e.g. an array of package names, tool names, or prior search results) against a fuzzy query. No filesystem access.
fuzzy_search_files Fuzzy file-name find, walking the filesystem recursively from a starting directory.
fuzzy_search_content Fuzzy grep of file contents across a directory tree, optionally scoped by file pattern.

Use fuzzy_filter when the candidates are already in memory (no need to touch disk). Use fuzzy_search_files / fuzzy_search_content when you need to discover files or matches by walking a directory — these are the two that pay the filesystem-walk cost.

If a tool isn't loaded, fetch its schema first: ToolSearch select:mcp__plugin_fzf-mcp_fzf-mcp__fuzzy_search_files.

fzf vs Everything

fzf = fuzzy/typo-tolerant matching that walks the filesystem live — works anywhere, including paths an index doesn't cover, but slower on large trees. Everything (everything-mcp, /everything skill) = instant, index-backed, best for exact/glob/regex file-name lookups on indexed drives. Prefer Everything for a known exact name or pattern; drop to fzf for approximate/fuzzy queries or for paths Everything doesn't index.

Gotcha: fzf walks the filesystem

fuzzy_search_files and fuzzy_search_content recurse the directory tree live — this is slow on huge trees (deep node_modules, large monorepos) compared to an indexed lookup. It's also the reason fzf is the right fallback for ~\Dropbox (which Everything does not index on this machine) — but Dropbox's on-demand ("online-only") file stubs are a known risk for filesystem walks in general (the same class of issue as verified iCloud/OneDrive stub gotchas elsewhere on this machine), so avoid walking Dropbox trees blind and prefer scoping the directory argument narrowly rather than searching from a Dropbox root.

Read the full file on GitHub · 31 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. 10d ago First seen · 31 lines · 94 tokens per session scan A 673ef23d8266

Subscribe to this mod's changes

fzf is a skill published in the GitHub repository danielsimonjr/fzf-mcp (3 stars, last pushed 3d ago), licensed MIT. It adds 94 tokens to every session and 716 once invoked, about $0.0005 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 2026-08-31.