fzf-mcp: Instructions file for Codex

AGENTS.md

fzf-mcp AGENTS.md is an instructions file for Codex, OpenCode from danielsimonjr/fzf-mcp. It costs 953 tokens per session, scanned A, original, MIT.

Repository instructions for fzf-mcp, a local server that lets an agent search files and file contents using fzf, a fuzzy finder, and findstr or grep.

In plain words
What is it for?
Use them when changing, testing, or configuring fzf-mcp, especially when updating its search tools or checking that the source and bundle behave the same way.
Why use it?
They document the repository's unusual setup, including two code copies that must stay in sync and a built file that is launched instead of the source file.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: reads .claude/ paths; mentions .claude-plugin; mentions Claude Code.

This is danielsimonjr/fzf-mcp's own configuration. It tells Codex and OpenCode how to work on fzf-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything fzf-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to danielsimonjr/fzf-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/danielsimonjr/fzf-mcp/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/danielsimonjr/fzf-mcp

Made for: Codex, OpenCode.

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-mcp AGENTS.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/danielsimonjr/fzf-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/danielsimonjr/fzf-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 953 This file is loaded in full into every session.
When invoked 953 The same file — it is already loaded in full.
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 $0.00953 $0.00953
Opus 5.5 $0.00381 $0.00381
Sonnet 5.5 $0.00191 $0.00191
Haiku 4.5 $0.00095 $0.00095

Measured 1mo ago against content hash 3fa816d43c00, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

fzf-mcp AGENTS.md 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.

AGENTS.md · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — fzf-mcp

How to operate on this repo without breaking it. Read this and MEMORY.md before making changes. Pairs with TODO.md (open work).

What this is

MCP server (@danielsimonjr/fzf-mcp, CommonJS, Windows-primary) that wraps the fzf fuzzy finder plus findstr/grep for content search. Tools: fuzzy_search_files, fuzzy_search_content, fuzzy_filter. install-fzf.js (postinstall) downloads the fzf binary into bin/.

The things that bite

  1. The plugin is plugin/, not the repo root. The marketplace installs only plugin/ (a git-subdir source). That directory holds .claude-plugin/plugin.json, .mcp.json, bundle/ and skills/, and no package.json or lockfile. Claude Code therefore runs no npm ci/bun install and the install has no node_modules.

    • src/*.ts is the source; bun run bundle writes plugin/bundle/index.cjs. Commit the rebuilt bundle; CI fails when the committed bundle is stale.
    • The bundle requires Node built-ins only. Keep it so: a runtime dependency that esbuild cannot inline breaks the installed plugin.
    • Change the version in package.json, plugin/.claude-plugin/plugin.json, the server version in src/index.ts, and the marketplace entry together.
  2. The running server is the plugin cache copy (~/.claude/plugins/cache/local-marketplace/fzf-mcp/<version>/). Repo commits do not change it until the marketplace entry is updated and the plugin is reinstalled.

  3. CRLF churn — normalize to LF before staging. (.gitattributes now enforces LF, but existing working-tree flips may linger.) Before staging an edited file:

    tr -d '\r' < index.js > index.js.tmp && mv -f index.js.tmp index.js
    git diff HEAD --stat -- index.js   # should be tiny
    

    Confirm a suspected EOL flip with git diff HEAD --ignore-all-space -- <file> (empty = pure EOL). Stage narrowly — never git add -A.

  4. Never spawn a bare executable name. On Windows spawn("fzf") / spawn("findstr") lets CreateProcess search the CWD first (binary planting).

    • fzf: resolveFzfPath() requires an absolute FZF_PATH or probes known absolute locations, and throws instead of a bare name. Resolved lazily (at spawn time).
    • archive extract (install-fzf.js): uses absolute %SystemRoot%\System32\tar.exe.
    • Still bare (tracked in TODO): findstr/grep in runSearchCommand.

Read the full file on GitHub · 70 lines

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. 1mo ago Changed · -2 lines · -6 tokens per session 3fa816d43c00
  2. 2mo ago First seen · 72 lines · 959 tokens per session scan A 8fd190b26f86

Subscribe to this mod's changes

fzf-mcp AGENTS.md is an instructions file published in the GitHub repository danielsimonjr/fzf-mcp (3 stars, last pushed 24d ago), licensed MIT. It adds 953 tokens to every session, about $0.0038 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 2026-08-31.

Related

fzf-mcp AGENTS.md compared with instructions from other repositories

fzf-mcp AGENTS.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
fzf-mcp AGENTS.mddanielsimonjr/fzf-mcpInstructions file324d agoMITA953Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode