AgentToolDrop

11 of 66

Trail-code

Builds a tree-sitter code map of your repo and serves it, plus saved team learnings, to coding agents

  • score 62
  • 10.5k stars
  • 96.2 stars/day since creation
  • pushed
  • MIT

Install the CLI with npm, then run init in your repo

npm install -g @trailhq/trail-code   # install the CLI, once
trail init                      # in your repo: build the graft map, set up .trail/, wire your agents

Copied from the project's docs at github.com/trailhq/Trail-Code

Why you'd want it

trail init parses your repo with tree-sitter into a map of files, functions and who calls what, with no model or API key, and refreshes it when the code changes. It registers an MCP server with six tools (trail_find_code, trail_file_api, trail_trace_calls, trail_find_all, trail_repo_map, trail_check_freshness), and in Claude Code adds hooks that put matching files into each prompt and show what depends on a file after an edit. Agents can also save decisions as markdown learnings in .trail/learnings/, committed with the code, and trail check compares a branch diff against them.

Best for

  • Giving agents a call graph of a large repo
  • Blast-radius checks after edits
  • Sharing team decisions through git

Use it when

You want Claude Code, Cursor, Codex or another MCP agent to find the right code and see what depends on it without repeated grepping. It also fits teams that want agent-saved decisions kept in the repo and checked before a PR.

Skip it if

trail init writes hooks, a statusline and MCP entries, and by default also edits user-level files such as ~/.claude/settings.json and ~/.codex/config.toml (skip with --no-global). It reads your past Claude Code sessions and, when gh is signed in, review comments on the last 50 merged PRs to seed learnings, and it sends anonymous usage stats unless you run trail telemetry disable; the optional trail build --deep calls the model provider you choose with your own key. The README marks the team workspace, skills and guardrails as coming soon, and the repo is about three months old.

Editor's note

Formerly graft; the old package @nanonets/graft and the graft command still work. No GitHub releases are published; the package is on npm.

Same category or shared tags.

  1. Rank 58

    Packs a repository into one AI-friendly file in XML, Markdown, JSON or plain text

    • score 26
    • 28.9k stars
    • 15.7 stars/day last 5 days
    • pushed
    • v1.18.1 on
    • MIT

    Run with npx

    npx repomix@latest
    Use it when, skip it if, stats for Repomix

    Why you'd want it

    Repomix reads a local or remote repository, respects .gitignore and .repomixignore, uses Secretlint to leave out files that match known credential formats, and writes one file with a summary, directory structure and file contents, plus token counts per file. The --compress option uses Tree-sitter to keep key code elements with fewer tokens, and large outputs can be split into parts. It also runs as an MCP server (repomix --mcp) and can generate Claude Agent Skills from a codebase.

    Best for

    • Feeding a whole codebase to a chat model
    • Checking token counts before sending context
    • Packing a remote GitHub repo for reference

    Use it when

    You want to hand an LLM a full or filtered snapshot of a repository in one file, or let an agent pack repos through MCP.

    Skip it if

    Your coding agent already reads files in your workspace and you have no need for a single packed file. By default the MCP server can read any path the host user can, so use --sandbox with untrusted clients.

    Stats

    New and rising score
    26 of 100
    Stars per day, last 5 days
    15.7
    Release
    v1.18.1,
    License
    MIT
    Pricing
    Open source
    Works with
    Any MCP client, Claude Code, Cursor, VS Code, Claude Desktop, Docker, Web
    Forks
    1,721
    Open issues
    156
    GitHub checked
  2. Rank 24

    CLI that lets agents create, read and edit Word, Excel and PowerPoint files without Office installed

    • score 51
    • 32.2k stars
    • 35.1 stars/day last 5 days
    • pushed
    • v1.0.158 on
    • Apache-2.0

    Install with Homebrew

    brew install officecli
    Use it when, skip it if, stats for OfficeCLI

    Why you'd want it

    OfficeCLI is a single binary that creates, reads and modifies .docx, .xlsx and .pptx files from the command line, with no Office installation needed. Every command supports --json output and elements are addressed by paths such as /slide[1]/shape[2], so an agent does not have to handle OOXML namespaces. It can render documents to HTML or PNG so an agent can look at its output and fix layout, and it evaluates Excel formulas on write. It also ships template merge for {{key}} placeholders, a dump command that turns a document into replayable batch JSON, and a built-in MCP server.

    Best for

    • Agent-generated decks, reports and spreadsheets
    • Batch edits and template fill in CI
    • Extracting document content to JSON

    Use it when

    You want an agent to produce or edit Word, Excel or PowerPoint files from a shell or over MCP, including in headless or Docker environments with no Office install.

    Skip it if

    You are wary of piping a script into your shell; the README's one-line installer is curl into bash, and a package manager or manual download is also listed. The install step also writes a skill file into every agent config it detects, checks for updates in the background by default, and view screenshot pipes rendered HTML through a headless browser while watch starts a local HTTP server. The README's claims of being the first and best, its fidelity claims and its comparison table are the project's own and were not checked here, so test your own documents first. The raw XML commands can rewrite document parts directly.

    Stats

    New and rising score
    51 of 100
    Stars per day, last 5 days
    35.1
    Release
    v1.0.158,
    License
    Apache-2.0
    Pricing
    Open source
    Works with
    Claude Code, Cursor, Codex, Windsurf, VS Code, macOS, Linux, Windows
    Forks
    2,196
    Open issues
    93
    GitHub checked
  3. Rank 3

    Gives a coding agent skills, a CLI and a shared knowledge base for modding PC games you own

    • score 79
    • 8.5k stars
    • 143 stars/day last 5 days
    • pushed
    • MIT

    Install as a Claude Code plugin

    /plugin marketplace add rehan-remade/universal-modder
    /plugin install universal-modder@universal-modder
    Use it when, skip it if, stats for universal-modder

    Why you'd want it

    universal-modder packages Agent Skills, three subagents and a Python CLI called um that a coding agent uses to mod a game: um scan finds Steam, Epic and Xbox installs and fingerprints the engine, loaders, anti-cheat and save folders, um backup snapshots saves, and um fal, um sprite and um render3d make and fit art, 3D and audio for the engine. The mod-any-game skill runs a fixed loop of recon, a backed-up lab, reading the real code, building one slice, testing it in the running game and writing a field note. Those field notes live in a knowledge base in the repo that agents search with um kb before starting and add to by pull request.

    Best for

    • Modding single-player PC games with an agent
    • Generating sprites and 3D assets for mods
    • Reusing other agents' modding notes

    Use it when

    You want Claude Code, Codex, Gemini CLI or another agent to work out how a game you own is built and ship a mod for it, with assets and an in-game test.

    Skip it if

    You play online games with anti-cheat: its own safety notes say injecting into an online client breaks the game's terms and gets accounts banned, and it refuses to do so. It touches game folders, saves, processes and your mouse and keyboard (asking first), asset generation needs a fal API key or a local ComfyUI server, and the repo is about two weeks old with no tagged release.

    Stats

    New and rising score
    79 of 100
    Stars per day, last 5 days
    143
    License
    MIT
    Pricing
    Open source
    Works with
    Claude Code, Codex, Gemini CLI, VS Code, Cursor, Windows
    Forks
    939
    Open issues
    31
    GitHub checked

For agents

The same entry, as files an agent can read without scraping this page.

# read one entry
curl -s https://agenttooldrop.com/tools/trail-code.md

# list the MCP servers in the catalog
curl -s https://agenttooldrop.com/tools.json \
  | jq -r '.tools[] | select(.category=="mcp-server") | .slug'