patchloom

Patchloom

One binary. Every platform. Structured file edits for AI agents.

Patchloom is a single-binary CLI that gives AI coding agents safe, structured file editing on any operating system. It edits JSON, YAML, and TOML by selector (not regex), preserves comments, understands code structure across 20 languages, batches multiple file edits into one tool call, and works identically on Linux, macOS, and Windows.

# Edit a YAML value by selector without breaking comments or formatting
patchloom doc set config.yaml database.port 5432 --apply

# Batch 6 file edits into a single tool call
patchloom batch --apply <<'EOF'
doc.set package.json version "2.0.0"
doc.set config.yaml app.version "2.0.0"
doc.set config.toml project.version "2.0.0"
replace README.md "1.0.0" "2.0.0"
replace CHANGELOG.md "1.0.0" "2.0.0"
file.create VERSION "2.0.0"
EOF

Why Patchloom? | Install | Quick start | Commands | Comparison | Architecture | Status

Why Patchloom?

The problem

AI agents edit files through tool calls. Each call is a round-trip back to the LLM. When a task touches config files, that process has three failure modes:

• Syntax corruption. The agent uses text replacement on JSON, YAML, or TOML and produces invalid output (mismatched braces, broken indentation, lost comments).
• Round-trip tax. Editing 6 files means 6 separate tool calls. Each one waits for the LLM to generate, execute, read the result, and plan the next call.
• Platform fragmentation. On Linux the agent uses sed, jq, grep. On Windows, none of those exist. The agent falls back to verbose PowerShell or makes errors with unfamiliar syntax.

How patchloom solves each one

Problem	How patchloom solves it
Syntax corruption	doc commands parse the file, change the value by selector path, and write valid output. Comments and formatting are preserved. No regex needed.
Round-trip tax	batch and tx combine N operations into 1 tool call. Six file edits become one command with atomic rollback on failure.
Platform fragmentation	Single static binary with zero dependencies. Same commands, same flags, same behavior on Linux, macOS, and Windows.

What changes with patchloom

Without patchloom (6 tool calls) Agent: edit file 1 ─── tool call ───▶ 15s Agent: edit file 2 ─── tool call ───▶ 15s Agent: edit file 3 ─── tool call ───▶ 15s Agent: edit file 4 ─── tool call ───▶ 15s Agent: edit file 5 ─── tool call ───▶ 15s Agent: edit file 6 ─── tool call ───▶ 15s Total: ~90s

With patchloom batch (1 tool call) Agent: batch with all 6 edits ─── tool call ───▶ 25s 5 round-trips saved Total: ~25s

Key capabilities

Capability	What it does	Example
Parser-backed edits	Edit JSON/YAML/TOML by selector, preserving comments and formatting	doc set config.yaml db.port 5432 --apply
Batch N files in 1 call	batch and tx combine operations into one tool call with rollback	batch --apply < ops.txt
Comment preservation	YAML/TOML comments survive all edits, including array resizing	doc append config.yaml tags '"v2"' --apply
Heading-aware markdown	Edit sections, tables, and bullets by heading, not line number	md table-append README.md --heading "API" --row "| new | row |" --apply
AST-aware code ops	List, rename, replace, and analyze symbols across 20 languages	ast rename src/ --old old_name --new new_name --apply
Atomic rollback	strict: true reverts every file if format or validate steps fail	tx plan.json --apply
MCP server	Expose all operations as structured MCP tool calls	patchloom mcp-server
Optional CLI sandbox	Reject ../ / absolute path escapes from --cwd on reads and writes (off by default; MCP always on)	patchloom --cwd <ws> --contain search … / create … --apply
Cross-platform	Identical behavior on Linux, macOS, Windows. No sed, jq, grep required.	Same binary everywhere

When to use patchloom vs native tools

Patchloom is not a replacement for all file operations. Its instructions tell agents exactly when to use it and when native tools are faster:

Task	Use patchloom?	Why
Edit a JSON/YAML/TOML value by selector	Yes	Parser guarantees valid output, preserves comments
Edit 3+ files in one task	Yes	batch/tx eliminates round-trips
Append a row to a markdown table	Yes	Heading-aware, no line number guessing
Read a single file	No	Native read_file is faster
Simple text search	No	Native grep is faster
Single-file text replacement	No	Native search_replace is faster

Correctness over speed

Patchloom is not faster than native tools for simple, single-file edits. Use native tools for those. But native text replacement cannot safely edit structured files: a sed on YAML can corrupt indentation, strip comments, or produce invalid syntax. doc set parses the file, changes the value by selector, and writes valid output. That guarantee is the point.

Where patchloom is faster is multi-file batching. Six file edits via native tools means six round-trips to the LLM. One batch call does the same work in a single round-trip.

Benchmark details (Claude Opus 4 via Grok Build, 11 tasks)

Task                    PL-CLI    MCP    Native
──────────────────────  ──────  ──────  ──────
search                   18.5s   12.7s   13.9s  ◀ ~same
replace                  36.1s   26.6s   26.1s  ◀ ~same
doc_set                  30.9s   16.9s   13.7s  ◀ native fastest
md_table                 15.5s   13.5s   15.3s  ◀ MCP fastest
tx_multi_file            41.4s   28.5s   22.9s  ◀ native fastest
batch_6_files            50.6s   46.6s   30.3s  ◀ native fastest
batch_mixed_ops          24.7s   13.6s   20.9s  ◀ MCP fastest
yaml_comment_preserve    18.1s   11.6s   16.1s  ◀ MCP fastest
md_insert                15.0s   11.7s   15.7s  ◀ MCP fastest
file_ops                 26.0s   16.6s   17.2s  ◀ ~same
tidy                     45.0s   30.3s   41.7s  ◀ MCP fastest
──────────────────────  ──────  ──────  ──────
TOTAL                   321.9s  228.5s  233.8s

MCP mode wins overall (228.5s vs 233.8s native) because structured tool calls skip shell syntax construction entirely. MCP wins 5/11 tasks; native wins 3/11; 3 are ties. CLI mode is always slowest due to shell construction overhead.

Install

# Homebrew (macOS/Linux)
brew install patchloom/tap/patchloom

# crates.io (requires Rust 1.95+, includes MCP server)
cargo install patchloom

# Scoop (Windows)
scoop bucket add patchloom https://github.com/patchloom/scoop-bucket
scoop install patchloom/patchloom

# Chocolatey (Windows; community feed — newer versions may lag moderation)
choco install patchloom

# npm / npx (downloads the platform binary from GitHub Releases)
npx patchloom --version
# or: npm install -g patchloom

Pre-built binaries for Linux, macOS, and Windows are on the Releases page. See Installation for shell installer scripts, source builds, and shell completion setup.

• MCP Registry name: mcp-name: io.github.patchloom/patchloom

Editor extension

Install the companion extension for VS Code, Cursor, Windsurf, or VSCodium:

• VS Code Marketplace
• Open VSX Registry

The extension auto-discovers the CLI (or installs it for you), generates AGENTS.md, configures MCP servers, and adds Quick Actions to the command palette. See the Editor Extension guide for details.

Quick start

1. Set up your project

patchloom init

This creates AGENTS.md in a new project or appends the rules to an existing agent instructions file, offers shell completions, and detects MCP configuration opportunities. Pass -y to skip confirmation prompts.

If you only want the rules text:

patchloom agent-rules >> AGENTS.md

# Or tailor the output:
patchloom agent-rules --mode mcp >> AGENTS.md            # MCP-only (no CLI examples)
patchloom agent-rules --platform windows >> AGENTS.md    # Windows-only syntax

If .vscode/ or .cursor/ exists, init also prints ready-to-copy .vscode/mcp.json or .cursor/mcp.json snippets.

Your AI agent reads AGENTS.md and learns when to use patchloom vs native tools.

2. Edit a config file safely

# Parser-backed: changes the value, preserves comments and formatting
patchloom doc set config.yaml database.port 5432 --apply

3. Batch multiple edits into one call

patchloom batch --apply <<'EOF'
doc.set config.json version "2.0"
md.upsert_bullet AGENTS.md "Rules" "- Always test"
replace src/main.rs "v1" "v2"
EOF

Or use a JSON plan with format and validate lifecycle:

{
  "version": 1,
  "operations": [
    { "op": "doc.set", "path": "config.json", "selector": "version", "value": "2.0" },
    { "op": "md.upsert_bullet", "path": "AGENTS.md", "heading": "Rules", "bullet": "- Always test" },
    { "op": "replace", "path": "src/main.rs", "old": "v1", "new": "v2" }
  ],
  "format": [{ "cmd": "cargo fmt --all" }],
  "validate": [{ "cmd": "cargo test", "required": true }]
}

patchloom tx plan.json --apply

tx plans are trusted input. format and validate run their cmd fields through the host shell (sh -c on Unix, cmd /C on Windows), so only run plans you trust.

4. Or use MCP for structured tool calls (no shell syntax)

After installing with MCP support, start the server:

patchloom mcp-server

MCP-capable agents call patchloom tools directly as structured JSON, with no shell quoting or command construction. The agent sends {"path": "config.json", "selector": "version", "value": "2.0"} instead of building patchloom doc set config.json version '"2.0"' --apply.

See the MCP setup guide for per-agent configuration and the full security model.

Using VS Code, Cursor, or Windsurf? The Patchloom extension handles setup automatically: it installs the binary, runs init, and configures your editor's MCP settings.

As a Rust library

Add patchloom as a dependency (omit CLI/MCP/AST with default-features = false):

[dependencies]
patchloom = { default-features = false }

use patchloom::api::{self, ApplyMode, ReplaceOptions, edit_error_kind, EditErrorKind};
use std::path::Path;

// Replace text (preview only, no disk write)
let result = api::replace_text(
    Path::new("src/config.rs"),
    "old_value", "new_value",
    &ReplaceOptions::default(),
    ApplyMode::Preview,
    None,
)?;
println!("{}", result.diff);

// Fail closed: zero matches become EditErrorKind::NoMatch (agent hosts)
let opts = ReplaceOptions { require_change: true, ..Default::default() };
match api::replace_in_content("body", "missing", "x", &opts) {
    Ok(r) => println!("changed={}", r.changed),
    Err(e) => assert_eq!(edit_error_kind(&e), Some(EditErrorKind::NoMatch)),
}
// Invalid options and bad regex peel InvalidInput (CLI/tx typed errors included)
match api::replace_in_content("body", "", "x", &ReplaceOptions::default()) {
    Err(e) => assert_eq!(edit_error_kind(&e), Some(EditErrorKind::InvalidInput)),
    Ok(_) => panic!("empty pattern must error"),
}

// Set a value in a JSON file
api::doc_set(
    Path::new("config.json"),
    "version",
    serde_json::json!("2.0"),
    ApplyMode::Apply,
    None,
)?;

// Multi-doc YAML: merge into document 0 (selector None = root only)
api::doc_merge(
    Path::new("stream.yaml"),
    serde_json::json!({"env": "prod"}),
    ApplyMode::Apply,
    None,
    Some("0"),
)?;

// Sole-path text load: binary / invalid UTF-8 → EditErrorKind::InvalidInput
let _text = api::load_text(Path::new("notes.md"))?;

All API types are Send + Sync. Beyond the api module, utility modules are also public: containment (workspace path guarding), exec (shell command execution), files (file-walking, load_text_strict, binary detection), backup (restore_path_from_latest_backup for post-Apply validate/revert), and write (atomic file writes with policy transformations). Library users needing temp dirs (e.g. agents) can use PathGuard::builder(cwd).allow_temp_directory() (handles /tmp on macOS); see the containment and api module rustdocs. Multi-doc bare keys and wrong-root merges peel to EditErrorKind::TypeError via edit_error_kind. Create/rename dest-exists peels to EditErrorKind::AlreadyExists (or api::is_already_exists / api::error_kind_str for CLI-stable "already_exists" strings). Fine-grained kinds also have bool peels (is_not_found, is_conflicts, is_changes_detected, is_type_error, is_format_failed, is_guard_rejected, is_invalid_input, is_no_match) matching edit_error_kind.

Replace fail-closed / shell-token options: CLI replace --require-change and --command-position (also plan/MCP fields and ReplaceOptions on the library). Library-only AST mutators: ast_rename / ast_replace_in_symbol / ast_rename_batch (feature ast + files), and FunctionSigEdit::parse_rust. Full surface: docs.rs/patchloom.

Getting started

Resource	What you'll learn
Installation	Install options and shell completions
Core concepts	Write modes, transaction plans, exit codes
MCP setup	Configure patchloom as an MCP server for your agent
Editor extension	VS Code, Cursor, Windsurf, and VSCodium integration
Quickstart	5-minute walkthrough
Reference	Every command, operation, and mode
Examples	Transaction plan templates

Commands

Agent-optimized (these are faster or safer than native tools)

Command	What it does	When to use
batch	Line-oriented multi-file edits in 1 call	Editing 3+ files with simple syntax
tx	JSON plan with format/validate lifecycle	Complex multi-file edits with rollback
doc	Parser-backed JSON/YAML/TOML edits	Changing config values without breaking syntax
md	Heading-aware markdown edits	Updating tables, sections, bullets in docs
ast	AST-aware symbol operations (20 languages)	Renaming identifiers, listing symbols, impact analysis
patch	Apply unified diffs with stale detection	Replaying patches safely
tidy	Text-file whitespace and newline normalization	CI checks for text tidiness
mcp-server	MCP protocol server	MCP-capable agents (no shell syntax)

General-purpose (also useful in scripts and CI)

Command	Description
search	Fast literal or regex search across text files (supports --glob/--exclude/--ignore-file for layered custom ignore files, --max-results, -C context, etc.)
replace	Mechanical string replacement across text files with diff preview
append	Append content to an existing file
prepend	Prepend content to an existing file
create	Create a new file with content
delete	Delete a file
rename	Move (rename) a file
read	Read file contents with optional line range
status	Show which files have uncommitted changes
explain	Summarize a tx plan in plain English
undo	Restore files from a backup created by --apply
completions	Generate shell completions (bash, zsh, fish, elvish)
init	Set up patchloom in a project (agent rules, completions, MCP)
schema	Export operation schemas with tier filtering and system prompts
agent-rules	Generate agent instructions for your project

How patchloom compares

Tool	Strength	Where patchloom differs
jq	JSON query/transform	patchloom also handles YAML, TOML, markdown; batches across files; preserves comments
yq	YAML/JSON query/transform	patchloom preserves YAML comments via CST editing; adds markdown, batching, atomic transactions
dasel	Multi-format get/set	patchloom adds batching (N edits in 1 call), atomic rollback, format/validate lifecycle
sd	Regex find/replace	patchloom adds parser-backed structured edits; batching; never produces invalid JSON/YAML
comby	Structural code patterns	patchloom targets config files and agent workflows, not source code pattern matching

The key difference: patchloom is designed for AI agent workflows. One batch or tx call replaces N sequential tool calls, cutting round-trips and eliminating partial-failure states.

vs agent-native editing tools

The table above compares patchloom to human CLI tools. But agents already have built-in editing: Claude Code's edit_file, Cursor's apply, Grok Build's search_replace, Aider's /code blocks. Why add patchloom on top?

Agent-native tools use text matching. They find a block of text and replace it. This works for source code but fails on structured config files:

Agent uses search_replace on YAML database: # Production settings host: db.prod.internal port: 5432 # PostgreSQL default pool_size: 10 The agent replaces port: 5432 with port: 5433. Result depends on implementation. Many agents lose the inline comment, break indentation, or fail to match because of surrounding context changes.

Agent uses patchloom doc set patchloom doc set config.yaml \ database.port 5433 --apply The YAML parser changes the value at the selector path. Comments, indentation, key ordering, and all other formatting are preserved. The output is always valid YAML.

Limitation of agent-native tools	How patchloom addresses it
Comment destruction	CST-level YAML/TOML editing preserves all comments
One file per tool call	batch/tx edit N files in 1 call (6.7x faster in benchmarks)
No rollback	tx with strict: true reverts all files if validation fails
Platform-dependent	Same binary and syntax on Linux, macOS, Windows
Stale context risk	patch apply uses fuzz matching to handle context drift

When to keep using native tools: Single-file reads, simple text search, single-file text replacement where comments don't matter. Patchloom's agent-rules tell agents exactly when to use each approach.

How it works with your AI agent

Two integration modes, same capabilities:

flowchart LR
    subgraph CLI["CLI mode (any agent)"]
        direction TB
        A["patchloom agent-rules >> AGENTS.md"] --> B["Agent reads AGENTS.md"]
        B --> C{"What kind of edit?"}
        C -->|Simple edit| D["Native tool (faster)"]
        C -->|Config edit| E["patchloom doc (safer)"]
        C -->|Markdown edit| F["patchloom md (smarter)"]
        C -->|Multi-file edit| G["patchloom batch (batched)"]
    end

    subgraph MCP["MCP mode (MCP-capable agents)"]
        direction TB
        H["patchloom mcp-server"] --> I["Agent discovers tools via MCP"]
        I --> J["Structured JSON tool calls"]
        J --> K["No shell syntax needed"]
    end

Status

3800+ tests across 23 commands. Tested with Grok 4.3, GPT-5.4, and Claude Opus 4.6.

Component	Status
CLI	Published on crates.io, Homebrew, Scoop, Chocolatey (choco install patchloom), and npm (npx patchloom). winget package under community review.
MCP server	Official MCP Registry name io.github.patchloom/patchloom (stdio; crates.io / npm packages; see server.json). Local MCPB for Smithery / desktop hosts: make pack-mcpb (mcpb/). Glama directory prep: root glama.json + manual Add MCP Server (see MCP setup)
Editor extension	Published on VS Code Marketplace and Open VSX

Full command reference

Every command, flag, transaction operation, and exit code is documented in the Command Reference (also available at docs/reference/README.md).

License

Licensed under either of:

• MIT license (LICENSE)
• Apache License, Version 2.0 (LICENSE-APACHE)

at your option.

Contributing

See CONTRIBUTING.md.

For local verification before opening a pull request, run make check. It matches the main Linux CI gate: formatting, clippy, unit tests (including feature-matrix jobs), integration tests, PTY tests, release-notes structure, test hygiene, and generated-doc freshness (check-patchloom-md, check-readme). While iterating locally, make check-fast is the same except it skips only check-patchloom-md (it still runs check-readme so a drifted test-count badge fails before CI).

All commits must be signed off with git commit -s.

Agent integration tests

make agent-test runs 19 pytest scenarios that verify AI agents correctly use patchloom when given instructions. make bench-agent runs 3-way benchmarks (CLI vs MCP vs native) across 11 tasks. Use MODEL=X to switch models and RUNS=N for variance reduction. Requires an LLM API key. Not part of make check. See tests/agent/README.md for details.

Security

For current security reporting guidance, see SECURITY.md.