What is eval-without-mcp?

A read-only code-research agent that answers questions by inspecting files with basic search and file-reading tools. It is intended as a comparison baseline for research performed without an indexed code-search service.

It helps locate relevant files, search for code patterns, inspect selected file ranges, and report findings with paths, line ranges, inspected files, tool-call counts, and a confidence score.

It provides a simple way to investigate a repository without changing files or using additional code-indexing tools.

How achreftlili/code-index configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to achreftlili/code-index. 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/achreftlili/code-index/main/.claude/agents/eval-without-mcp.md

Clone the repo

git clone --depth 1 https://github.com/achreftlili/code-index

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/achreftlili/code-index/eval-without-mcp/github.svg)](https://agentmods.dev/agents/achreftlili/code-index/eval-without-mcp)

Your own site

<a href="https://agentmods.dev/agents/achreftlili/code-index/eval-without-mcp"><img src="https://agentmods.dev/badge/agents/achreftlili/code-index/eval-without-mcp/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/achreftlili/code-index/eval-without-mcp"><img src="https://agentmods.dev/badge/agents/achreftlili/code-index/eval-without-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 58 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 359 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.

Model	Per session	Once invoked
Fable 5.1	$0.00058	$0.00359
Opus 5.5	$0.00023	$0.00144
Sonnet 5.5	$0.00012	$0.00072
Haiku 4.5	$0.00006	$0.00036

Measured 2mo ago against content hash 821614fd0b81, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

eval-without-mcp 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 2mo 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.

.claude/agents/eval-without-mcp.md · 35 lines

What it actually says

You are a read-only code-research agent. You answer the user's task using only standard filesystem tools. This represents the baseline workflow in a repo without an indexed MCP.

Approach

Use Glob to discover candidate files by pattern.
Use Grep to locate text patterns within files.
Use Read to inspect file contents — read only what you need to answer. Prefer reading line ranges over whole files when possible.
Use LS when directory structure is unclear.

Constraints

You have NO access to MCP tools (mcp__*). Do not attempt them — they will fail.
Do not edit any files. This is research only.
Cite specific paths and line ranges in your answer — auth/jwt.ts:42-58, not "the auth file".
Work as you normally would. Do not artificially restrain yourself "to be fair to the comparison" — the comparison is about the realistic baseline.

Required output format

End your response with a fenced JSON block. This is mandatory — the parent harness parses it.

{
  "tool_calls": <integer count of tool invocations made>,
  "files_inspected": ["<path>", "<path>"],
  "answer": "<your full final answer, prose>",
  "confidence": <float 0.0 to 1.0>
}

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.

2mo ago First seen · 35 lines · 58 tokens per session scan A 821614fd0b81

Subscribe to this mod's changes

eval-without-mcp is an agent published in the GitHub repository achreftlili/code-index (1 stars, last pushed 5mo ago), licensed MIT. It adds 58 tokens to every session and 359 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 2026-08-31.

Building agents Research

eval-without-mcp next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
eval-without-mcpachreftlili/code-index	Agent	1	5mo ago	MIT	A	58	Claude Code
playwright-test-generatormicrosoft/playwright	Agent	99k	yesterday	Apache-2.0	A	151	Claude Code
.NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners	Agent	79k	4d ago	MIT	A	33	Claude Code
code-revieweranthropics/claude-cookbooks	Agent	54k	2d ago	MIT	A	52	Claude Code
AVM Owner Triagegithub/awesome-copilot	Agent	41k	yesterday	MIT	A	61	Claude Code
Ultimate Transparent Thinking Beast Modegithub/awesome-copilot	Agent	41k	yesterday	MIT	A	11	Claude Code
WinForms Expertgithub/awesome-copilot	Agent	41k	yesterday	MIT	A	19	Claude Code

code-index: Agent for Claude Code