#7575th of 85 in Skills, plugins and rules

trail-code

Code graph and shared team learnings for Claude Code, Cursor and Codex

Stars: 10k
License: MIT
Last commit: Oct 2026
Language: TypeScript

Missed the latest GitHub check; these facts may be older.

Overview

Trail-code (formerly graft) parses a repo with tree-sitter into a graph of files, functions and callers, and gives coding agents matching files and edit impact through hooks and MCP tools. It also saves decisions and preferences from sessions as markdown in .trail/learnings/, shared through git, and trail check compares a branch against them before a PR. The README reports 33 of 50 SWE-bench Verified issues solved with the map versus 27 without.

Who it is for: Teams using Claude Code, Cursor or Codex on shared repos

Strengths

Code map built locally with tree-sitter, no model or API key, 23 languages
Learnings are plain markdown in git, reviewed in PRs, no server needed
trail check flags changes that contradict earlier team decisions before the PR
Claude Code wired via hooks; Cursor and Codex via MCP tools and instruction files

Weaknesses

Benchmark figures are the project's own; the SWE-bench sample is only 50 issues
Team workspace, skills and guardrails kinds are marked as coming soon
Day-one session mining reads Claude Code transcripts only, using Claude Sonnet
Sends anonymous telemetry by default, opt-out

What it needs

no GPU
Docker
Needs Node.js, git
Models: Claude Code, Cursor, Codex

Also in Skills, plugins and rules

See all 85

Also in Skills, plugins and rules
Rank	Project	Score
1	skillsAgent skills for planning, TDD, debugging and code review291.3k starsMIT	94 out of 100
2	eccAgents, skills, hooks and rules bundle for Claude Code, Codex and other harnesses279.5k starsMIT	94 out of 100
3	cavemanCuts token use in coding agents with terse replies and compressed inputs Live demo ↗ (opens in a new tab)111.9k starsApache-2.0	94 out of 100
#4	ponytailSkill prompt that makes coding agents write less code and add tests163.6k starsMIT	92 out of 100
#5	impeccableDesign skill with 24 commands and a detector for AI-generated frontends Live demo ↗ (opens in a new tab)81.2k starsApache-2.0	92 out of 100

How to choose

Check which agent it targets and whether it works with the version you run.
Read what it adds to every prompt; big rule sets cost tokens on each call.
Prefer add-ons you can turn off per project.

Health

Releases: Not checked
Top contributor: Not checked
Security advisories: Not checked
Package advisories: Not checked
OpenSSF Scorecard: Not checked

Not read for this project yet: each refresh reads the facts of a few projects. Bots and coding-agent accounts are left out of the commit counts. Not part of the score: how we check.

License in plain words

MIT Permissive

Use it at work: Yes
Change it and rebrand it: Yes
Sell it or host it for others: Yes

Your part: Keep the copyright and license notice in copies you ship.

A plain summary, not legal advice. Read the license on GitHub ↗ (opens in a new tab)

#75 of 85 in Skills, plugins and rules on Archestack, as of 15 Oct 2026.

In your README

The badge updates twice a day.

[![Archestack](https://archestack.com/badge/trailhq/trail-code.svg)](https://archestack.com/best-of-vibe-coding/projects/trail-code/)

How badges work

On your site or blog

A card with the rank, score and signals, in light or dark to match the reader.

<iframe src="https://archestack.com/embed/best-of-vibe-coding/trail-code/" title="trail-code on Archestack" width="400" height="270" style="border:0;max-width:100%" loading="lazy"></iframe>

Preview the card

Best of Vibe Coding on GitHub

Each review comes from the project's README and facts we check on GitHub. The fix form opens with trail-code filled in.