Skip to content
Back to search

feature-track

MarketplaceWorks with Claude CodeGitHub

Lightweight, repo-native shared memory plugins for AI coding agents.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/junsw--feature-track/badge.svg)](/listings/junsw--feature-track)

HTML

<a href="/listings/junsw--feature-track"><img src="/api/listings/junsw--feature-track/badge.svg" alt="findsafeskills safety rating" /></a>

Install

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

npx skills add JunsW/feature-track

Re-run the command any time to update. Or copy [SKILL.md](skills/feature-tracking/SKILL.md) and [references/](skills/feature-tracking/references/) into:

- **Claude Code:** `~/.claude/skills/feature-tracking/` - **Cursor:** `.cursor/rules/feature-tracking.mdc` (use the body of `SKILL.md`, without frontmatter) - **Codex:** `~/.codex/skills/feature-tracking/` for personal use or `.codex/skills/feature-tracking/` for a project

The complete portable rule set lives in [skills/feature-tracking/](skills/feature-tracking/).

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

.claude-plugin/marketplace.json · Manifest · 40 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. {
  2. "name": "feature-track",
  3. "owner": {
  4. "name": "Feature Track contributors"
  5. },
  6. "description": "Lightweight, repo-native shared memory plugins for AI coding agents.",
  7. "version": "0.1.0",
  8. "metadata": {
  9. "description": "Lightweight, repo-native shared memory plugins for AI coding agents.",
  10. "version": "0.1.0"
  11. },
  12. "plugins": [
  13. {
  14. "name": "feature-track",
  15. "source": "./plugins/feature-track-claude",
  16. "description": "Lightweight, repo-native shared memory for Claude Code.",
  17. "version": "0.1.0",
  18. "author": {
  19. "name": "Feature Track contributors"
  20. },
  21. "license": "MIT",
  22. "keywords": [
  23. "ai-agent-memory",
  24. "agent-context",
  25. "claude-code",
  26. "documentation",
  27. "feature-tracking",
  28. "repo-native",
  29. "shared-memory"
  30. ],
  31. "category": "Productivity",
  32. "tags": [
  33. "memory",
  34. "shared-memory",
  35. "documentation",
  36. "coding-agents"
  37. ]
  38. }
  39. ]
  40. }
README.md · README · 194 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # Feature Track
  2. ![License](https://img.shields.io/badge/license-MIT-green.svg)
  3. ![Version](https://img.shields.io/badge/version-0.1.0-blue.svg)
  4. Lightweight, repo-native shared memory for AI coding agents.
  5. Feature Track keeps Codex, Claude Code, and other AI coding tools aligned on each long-lived feature: its status, source-of-truth docs, decisions, risks, and recent changes.
  6. > Spec frameworks help agents plan the next change. Feature Track helps agents remember the feature.
  7. It is not chat-history search, an opaque memory database, or a full spec-driven development framework. It is a portable, low-friction Markdown memory layer that lives inside your repo through `docs/features/`.
  8. ## Why
  9. AI coding agents are good at making changes, but they lose project context easily:
  10. - feature knowledge is scattered across PRDs, API notes, plans, chats, and old commits
  11. - agents repeat discovery because there is no current feature index
  12. - stale plans can look authoritative after reality has changed
  13. - switching tools, sessions, or agents often resets project memory
  14. - small teams and solo developers usually do not want heavyweight process
  15. Feature Track gives every important feature a small living track file plus a global index. The track does not replace your docs. It points to the docs that still matter and records the current truth.
  16. ## Who It Is For
  17. Feature Track is designed for:
  18. - teams that want shared project memory without heavyweight process
  19. - solo developers and indie hackers using AI coding tools
  20. - brownfield projects with useful but scattered docs
  21. - teams using Codex, Claude Code, or multiple agent tools
  22. - projects that need traceable feature context across sessions
  23. ## Core Idea
  24. ```text
  25. docs/features/
  26. ├── README.md # global feature index
  27. └── <feature-id>/
  28. ├── README.md # current feature memory
  29. ├── prd/
  30. ├── api/
  31. ├── plans/
  32. └── archive/
  33. ```
  34. Each feature track answers:
  35. - What is true now?
  36. - Which docs are the current source of truth?
  37. - What decisions should future agents preserve?
  38. - What risks, migrations, or rollout constraints matter?
  39. - What changed recently?
  40. ## Philosophy
  41. - Memory, not ceremony.
  42. - Current truth over stale specs.
  43. - Link first, migrate later.
  44. - Adopt in minutes, improve over time.
  45. - Works with your docs, not around them.
  46. Feature Track is built for brownfield projects first. You can start by linking existing PRDs, API docs, plans, and design notes instead of moving everything into a new system.
  47. ## Quick Start
  48. ```bash
  49. npx skills add JunsW/feature-track
  50. ```
  51. Re-run the command any time to update. Or copy [SKILL.md](skills/feature-tracking/SKILL.md) and [references/](skills/feature-tracking/references/) into:
  52. - **Claude Code:** `~/.claude/skills/feature-tracking/`
  53. - **Cursor:** `.cursor/rules/feature-tracking.mdc` (use the body of `SKILL.md`, without frontmatter)
  54. - **Codex:** `~/.codex/skills/feature-tracking/` for personal use or `.codex/skills/feature-tracking/` for a project
  55. The complete portable rule set lives in [skills/feature-tracking/](skills/feature-tracking/).
  56. ## What Feature Memory Looks Like
  57. This repository uses Feature Track on itself. The global index lives at [docs/features/README.md](docs/features/README.md):
  58. ```md
  59. | Feature | Status | Track | Source Of Truth | Updated | Notes |
  60. |---|---|---|---|---|---|
  61. | Codex Plugin | active | [README](codex-plugin/README.md) | [README](../../README.md), [plugin manifest](../../plugins/feature-track/.codex-plugin/plugin.json) | 2026-07-06 | Publish-ready Codex plugin wrapper for the existing Feature Tracking skill |
  62. | Claude Code Plugin | active | [README](claude-code-plugin/README.md) | [README](../../README.md), [plugin manifest](../../plugins/feature-track-claude/.claude-plugin/plugin.json), [marketplace](../../.claude-plugin/marketplace.json) | 2026-07-06 | Marketplace-ready Claude Code plugin wrapper for the Feature Tracking skill |
  63. ```
  64. A feature track keeps the current operational memory close to the docs and files that prove it:
  65. ```md
  66. ## Current Status
  67. Feature Track now targets a mature Codex plugin path for Codex users.
  68. ## Source Of Truth
  69. - Product intro and install path: [README](../../../README.md)
  70. - Plugin manifest: [plugin.json](../../../plugins/feature-track/.codex-plugin/plugin.json)
  71. ## Decisions
  72. - Package the Codex path as a single-skill plugin first.
  73. - Keep MCP servers, apps, and hooks out of v0.1.
  74. ```
  75. See [docs/features/codex-plugin/README.md](docs/features/codex-plugin/README.md) and [docs/features/claude-code-plugin/README.md](docs/features/claude-code-plugin/README.md) for the full real tracks.
  76. ## How Agents Use It
  77. At the start of work, an agent reads `docs/features/README.md`, opens the relevant feature track, and follows the current source-of-truth links instead of rediscovering context from scratch. After changes, the agent updates the feature track with the actual outcome: changed behavior, decisions, risks, tests, and recent changes.
  78. `validate` turns this from loose Markdown into checkable memory. It catches index drift, missing required sections, feature tracks missing from the global index, and broken local links before stale context spreads into future sessions.
  79. ## How It Compares
  80. Full spec-driven tools are useful when you want every change to move through proposals, spec deltas, task lists, and archive steps.
  81. Feature Track is lighter. It focuses on long-term feature context rather than controlling every change. It is a good fit when you want AI agents to stop forgetting what a feature is, without forcing a new development lifecycle.
  82. See [docs/comparison.md](docs/comparison.md) for more detail.
  83. <details>
  84. <summary><strong>Other Installation Options</strong></summary>
  85. <br>
  86. **Codex plugin:**
  87. ```bash
  88. codex plugin marketplace add JunsW/feature-track
  89. ```
  90. Then open `/plugins` and install **Feature Track**.
  91. **Claude Code plugin:**
  92. ```text
  93. /plugin marketplace add JunsW/feature-track
  94. /plugin install feature-track@feature-track
  95. ```
  96. **Local Python adapters:**
  97. ```bash
  98. python3 cli/feature_track.py install codex
  99. python3 cli/feature_track.py install claude-code --root .
  100. ```
  101. All installation paths expose the same `feature-tracking` workflow. Avoid installing both the Codex plugin and standalone Codex skill unless you are testing adapter behavior.
  102. </details>
  103. ## What The CLI Does
  104. - `init`: create `docs/features/README.md`
  105. - `add`: create a feature track and add it to the index
  106. - `validate`: check index drift, required sections, and broken local links
  107. - `install codex`: install the local Codex skill adapter
  108. - `install claude-code`: generate Claude Code project instructions and commands
  109. Validation is intentionally permissive by default so brownfield projects can adopt Feature Track gradually. Use `--ci` when you want stricter drift checks in automation.
  110. ## Repository Layout
  111. - `.github/workflows/ci.yml`: basic CI for CLI syntax and feature memory validation
  112. - `.claude-plugin/marketplace.json`: repo marketplace for the Claude Code plugin
  113. - `.agents/plugins/marketplace.json`: repo marketplace for the Codex plugin
  114. - `spec/feature-track-spec.md`: neutral Feature Track spec
  115. - `cli/feature_track.py`: lightweight no-dependency CLI
  116. - `plugins/feature-track/`: Codex plugin package
  117. - `plugins/feature-track-claude/`: Claude Code plugin package
  118. - `skills/feature-tracking/`: canonical portable Agent Skills package
  119. - `skills/claude-code/`: Claude Code adapter snippets and commands
  120. - `templates/`: reusable Markdown templates
  121. ## Status
  122. `v0.1.0` is the first public release of Feature Track. The core format is intentionally simple: a global feature index plus one Markdown track per feature under `docs/features/`.
  123. Today, Feature Track is best used as a lightweight documentation layer for Codex, Claude Code, or any agent workflow that can read and update files in your repo. The included plugins and CLI help create and validate that structure; the Markdown files remain the source of truth.
  124. The document structure is designed to stay stable as the project grows.
  125. ## Contributing
  126. Contributions are welcome. Please keep the spec portable, adapters lightweight, and validation friendly to existing projects. See [CONTRIBUTING.md](CONTRIBUTING.md).
  127. ## License
  128. Feature Track is released under the [MIT License](LICENSE).

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.