semantic-edit-mcp: Instructions file for Claude Code

CLAUDE.md

semantic-edit-mcp CLAUDE.md is an instructions file for Claude Code from jbr/semantic-edit-mcp. It costs 2,449 tokens per session, scanned A, original, Apache-2.0.

Repository guidance for a Rust MCP server that edits source code by targeting its syntax tree rather than raw lines or characters. MCP, or Model Context Protocol, is a way for an AI tool to call an external server; the guidance also describes commands and snapshot tests.

In plain words
What is it for?
Use it when working on the semantic-edit-mcp repository, especially its syntax-aware editing, Rust checks, MCP server command, or snapshot test suite.
Why use it?
It gives coding agents the project-specific rules needed to build, test, format, and check this server correctly. Snapshot tests compare saved expected results with actual tool output.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

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

Reuse

Borrowing it

Nothing to install: this file belongs to jbr/semantic-edit-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/jbr/semantic-edit-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/jbr/semantic-edit-mcp

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 semantic-edit-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jbr/semantic-edit-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/jbr/semantic-edit-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/jbr/semantic-edit-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/jbr/semantic-edit-mcp/claude-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 semantic-edit-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/jbr/semantic-edit-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/jbr/semantic-edit-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,449 This file is loaded in full into every session.
When invoked 2,449 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 $0.02449 $0.02449
Opus 5 $0.01224 $0.01224
Sonnet 5 $0.00490 $0.00490
Haiku 4.5 $0.00245 $0.00245

Measured 3d ago against content hash fb22e13ad27d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-17, from the pricing page.

Security

Grade A, and why

semantic-edit-mcp CLAUDE.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 3d 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.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

What this is

An MCP (Model Context Protocol) server for AST-aware code editing. Instead of line/character edits, edits target tree-sitter AST nodes located by a short text anchor, then the whole file is reformatted with the language's native formatter and re-parsed to guarantee the result is still syntactically valid before anything touches disk.

Commands

cargo build                          # build
cargo test                           # run all tests (the snapshot suite + unit tests)
cargo fmt --all -- --check           # formatting check (CI gate)
cargo clippy                         # lint (CI gate)
cargo run -- serve                   # run the MCP stdio server locally

Snapshot tests (the main test surface)

Most behavior is covered by data-driven snapshot tests under tests/snapshots/, discovered and run by src/tests/snapshot_runner.rs via the single run_snapshot_tests Rust test. Each test is a directory containing args.json (one tool call or an array of them), an optional input.<ext>, and the expected response.txt / output.<ext>.

TEST_FILTER=rust cargo test                    # run a category (prefix match)
TEST_FILTER=rust::attributes cargo test        # run one test (exact, "::"-joined path)
TEST_FILTER=json,rust cargo test               # multiple, comma-separated
UPDATE_SNAPSHOTS=1 cargo test                  # regenerate all expected files
UPDATE_SNAPSHOTS=1 TEST_FILTER=rust::attributes cargo test   # regenerate one

When a snapshot fails, the summary prints the exact TEST_FILTER=... and UPDATE_SNAPSHOTS=1 ... commands to reproduce or accept it. Always review a diff before accepting it with UPDATE_SNAPSHOTS=1 — the whole point of the suite is to catch unintended formatting/targeting changes.

External formatter dependencies

Editing relies on language-native formatters being on PATH; an edit fails (and is reported as unsafe) if its formatter is missing or errors:

Read the full file on GitHub · 97 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. 3d ago First seen · 97 lines · 2,449 tokens per session scan A fb22e13ad27d

Subscribe to this mod's changes

semantic-edit-mcp CLAUDE.md is an instructions file published in the GitHub repository jbr/semantic-edit-mcp (5 stars, last pushed 2d ago), licensed Apache-2.0. It adds 2,449 tokens to every session, about $0.0122 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 2026-09-14.

Related

Other instructions, from other repositories

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 8,838 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,259 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens