agentmods.dev

mcp-zoekt: Agent for Claude Code

.github/agents/copilot-instructions.md

copilot-instructions is an agent for Claude Code from jahales/mcp-zoekt. It costs 0 tokens per session (851 once invoked), scanned A, original, Apache-2.0.

A generated set of coding guidelines based on a project's feature plans. It records technologies, dependencies, storage assumptions, and other implementation context.

In plain words
What is it for?
Use it to guide development across features involving TypeScript, Node.js, Vitest, MCP servers, Zod, Pino, Zoekt, Docker, and related project components.
Why use it?
It gives coding agents a shared reference for how planned features should be built and which tools or versions they should use.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

This is jahales/mcp-zoekt's own configuration. It tells Claude Code how to work on mcp-zoekt 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 mcp-zoekt configures →

not rated 5repo 1mo ago A scan 0 tokens original Apache-2.0
View source ↗ jahales/mcp-zoekt
Reuse

Borrowing it

Nothing to install: this file belongs to jahales/mcp-zoekt. 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/jahales/mcp-zoekt/main/.github/agents/copilot-instructions.md
Clone the repo
git clone --depth 1 https://github.com/jahales/mcp-zoekt

Made for: Claude Code.

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 copilot-instructions

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

Your own site · 80×15
<a href="https://agentmods.dev/agents/jahales/mcp-zoekt/copilot-instructions"><img src="https://agentmods.dev/badge/agents/jahales/mcp-zoekt/copilot-instructions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 851 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00000 $0.00851
Opus 5 $0.00000 $0.00426
Sonnet 5 $0.00000 $0.00170
Haiku 4.5 $0.00000 $0.00085

Measured 9d ago against content hash e248ecc2249f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

copilot-instructions scanned grade A with 1 finding 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 9d 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

- TypeScript 5.x, Node.js 18+ + Vitest 2.x (projects feature), @modelcontextprotocol/sdk (test client), node:child_process (subprocess spawning) (002-e2e-integration-tests)
.github/agents/copilot-instructions.md · 47 lines

How it starts

The opening of the file, as written. The whole thing — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.

code-search Development Guidelines

Auto-generated from all feature plans. Last updated: 2026-02-13

Active Technologies

  • TypeScript 5.x, Node.js 18+ + Vitest 2.x (projects feature), @modelcontextprotocol/sdk (test client), node:child_process (subprocess spawning) (002-e2e-integration-tests)

  • N/A (tests use embedded fixture files) (002-e2e-integration-tests)

  • TypeScript 5.x with strict mode + @modelcontextprotocol/sdk ^1.0.0, zod ^3.0.0, pino ^8.0.0 (003-zoekt-mcp-tools)

  • N/A (stateless server; Zoekt manages index storage) (003-zoekt-mcp-tools)

  • TypeScript 5.x with strict mode + @modelcontextprotocol/sdk, Zod (validation), Pino (logging) (004-pagination-logic)

  • N/A (stateless pagination via cursor encoding) (004-pagination-logic)

  • TypeScript 5.5+ with strict mode, ES2022 target + @modelcontextprotocol/sdk ^1.25.2, zod ^3.23.0, pino ^9.0.0 (005-zoekt-list-api)

  • N/A (stateless HTTP client to Zoekt backend) (005-zoekt-list-api)

  • POSIX shell (BusyBox/Alpine) + zoekt-mirror-github, zoekt-git-index (already in zoekt:local image) (006-continuous-reindex)

  • Docker volume (zoekt-data) — shared between sync and webserver containers (006-continuous-reindex)

  • TypeScript 5.x, strict mode, ES2022 target + @modelcontextprotocol/sdk ^1.25.2, pino ^9.0.0, zod ^3.23.0 (007-enhance-logging)

  • N/A — this feature is purely about log output, not persistence (007-enhance-logging)

  • TypeScript 5.x (ES2022 target, NodeNext modules, strict mode) + @modelcontextprotocol/sdk ^1.25.2, pino ^9.0.0, zod ^3.23.0 (008-workingtree-multi-org)

  • Zoekt index files on Docker volumes (/data/index), no database (008-workingtree-multi-org)

  • TypeScript 5.x, Node.js 18+ + @modelcontextprotocol/sdk, zod, pino (logging) (001-zoekt-mcp-infra)

Project Structure

src/
tests/

Commands

npm test; npm run lint

Code Style

TypeScript 5.x, Node.js 18+: Follow standard conventions

Recent Changes

  • 008-workingtree-multi-org: Added TypeScript 5.x (ES2022 target, NodeNext modules, strict mode) + @modelcontextprotocol/sdk ^1.25.2, pino ^9.0.0, zod ^3.23.0
  • 007-enhance-logging: Added TypeScript 5.x, strict mode, ES2022 target + @modelcontextprotocol/sdk ^1.25.2, pino ^9.0.0, zod ^3.23.0
  • 006-continuous-reindex: Added POSIX shell (BusyBox/Alpine) + zoekt-mirror-github, zoekt-git-index (already in zoekt:local image)
  • 005-zoekt-list-api: Added TypeScript 5.5+ with strict mode, ES2022 target + @modelcontextprotocol/sdk ^1.25.2, zod ^3.23.0, pino ^9.0.0

Read the full file on GitHub · 47 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. 9d ago First seen · 47 lines · 0 tokens per session scan A e248ecc2249f

Subscribe to this mod's changes

copilot-instructions is an agent published in the GitHub repository jahales/mcp-zoekt (5 stars, last pushed 1mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 851 tokens. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Building agentsWriting and docsai-toolscode-searchmcpmodel-context-protocolzoekt
Related

Other agents, from other repositories

semble-search

Code search agent for exploring any codebase. Use for finding code by intent, locating implementations, understanding how something works, or discovering related code. Prefer over runshellcommand/readfile for any semantic or exploratory question.

MinishLab/semble · 46 tokens

semble-search

Code search agent for exploring any codebase. Use for finding code by intent, locating implementations, understanding how something works, or discovering related code. Prefer over Bash/Read for any semantic or exploratory question.

MinishLab/semble · 44 tokens

semble-search

Code search agent for exploring any codebase. Use for finding code by intent, locating implementations, understanding how something works, or discovering related code. Prefer over shell/read tools for any semantic or exploratory question.

MinishLab/semble · 44 tokens

security-reviewer

A separate agent that reviews security-sensitive code changes without editing files or reading sensitive configuration. It focuses on authentication, permissions, payments, deletion, and handling of outside input.

ezBuilder/code-brain · 27 tokens

pkm-capture

Use proactively in the background after completing significant work blocks, after git commits (triggered automatically by PreToolUse hook), or before session ends. Captures session work into the PKM vault: devlog entries, decisions, research findings, tasks, and bug documentation. Conservative — most exchanges produce…

AdrianV101/obsidian-pkm-plugin · 476 tokens

vault-explorer

Use proactively when researching what the vault knows about a topic, before creating new notes, or when exploring existing knowledge and connections. Run in foreground — results inform the caller's next steps. Examples: Context: User asks about a topic before creating new content. user: "What does the vault already…

AdrianV101/obsidian-pkm-plugin · 252 tokens