Agent skill

Feature Tracking

by JunsW in JunsW/feature-track

Maintain portable Feature Track docs for project features. An agent skill from JunsW/feature-track.

MITAuto-check passedBackend & APIs

Install Feature Tracking

skills CLI
$ npx skills add JunsW/feature-track --skill feature-tracking -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install JunsW/feature-track feature-tracking --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/JunsW/feature-track.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/feature-tracking .claude/skills/feature-tracking && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
feature-tracking
GitHub stars
108
Token cost
~339 tokens
SKILL.md length
140 words
Files
5 (incl. scripts, references)
Skills in repo
1
Repo updated
First seen
Licence
MIT

At a glance

Maintain portable Feature Track docs for project features. An agent skill from JunsW/feature-track.

  • Works in 4 steps: Read docs/features/README.md if it exists. → Identify the feature id from the… → Read docs/features//README.md if it… → …
  • Finishing feature work
  • Runs Python scripts from its folder; calls python3
  • Updating PRD/API/design/implementation docs

What it does

Feature Tracking is an agent skill from JunsW/feature-track. Maintain portable Feature Track docs for project features. Use when designing, planning, implementing, reviewing, or finishing feature work; creating or updating PRD/API/design/implementation docs; adding a new feature; or validating docs/features.

Its SKILL.md is about 340 tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including scripts and reference files (for example `references/feature-index-template.md`, `references/feature-readme-template.md` and `references/spec.md`).

It sits in Backend & APIs, covering API design and PRD writing. The repository describes itself as: Repo-native shared memory for AI coding agents. The licence is MIT.

When your agent uses it

  • Finishing feature work
  • Updating PRD/API/design/implementation docs
  • Adding a new feature
  • Validating docs/features

Example prompts

  • “/feature-tracking”

Requirements

  • Python 3

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Read docs/features/README.md if it exists.
  2. Identify the feature id from the request, code module, route, domain name, or existing docs.
  3. Read docs/features//README.md if it exists.
  4. If no track exists, create one and add it to the index.

What it can do on your machine

Read from SKILL.md and the folder at commit e742a77. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python3

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Feature Tracking loads about 339 tokens when it runs, and up to ~852 if it reads all its reference files. Until then it costs about 66 tokens; SKILL.md has 140 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~66
When it runs · the whole SKILL.md, loaded when a task matches
~339
With references · SKILL.md plus every file in references/, read only if the agent opens them
~852

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from JunsW/feature-track at commit e742a77, republished under its MIT licence (© JunsW). 140 words, ~339 tokens.

Download SKILL.mdSave it as .claude/skills/feature-tracking/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.
name
feature-tracking
description
Maintain portable Feature Track docs for project features. Use when designing, planning, implementing, reviewing, or finishing feature work; creating or updating PRD/API/design/implementation docs; adding a new feature; or validating docs/features.

Feature Tracking

Use Feature Track as the current operational memory for feature work. The neutral spec is the source of truth; this Codex skill is only an adapter.

Read references/spec.md before changing feature docs.

Default Workflow

Before feature work:

  1. Read docs/features/README.md if it exists.
  2. Identify the feature id from the request, code module, route, domain name, or existing docs.
  3. Read docs/features/<feature-id>/README.md if it exists.
  4. If no track exists, create one and add it to the index.

During work, update the feature track when behavior, decisions, endpoints, data models, dependencies, rollout constraints, tests, or source-of-truth links change.

Before completion:

  1. Update the feature README for the actual outcome.
  2. Update docs/features/README.md if status, source-of-truth links, dates, or notes changed.
  3. Run validation when available:
bash
python3 cli/feature_track.py validate --root .

If the project does not include this CLI, use scripts/validate_feature_tracks.py from this skill.

© JunsW, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 4 other files (scripts, references) in skills/feature-tracking of JunsW/feature-track.

  • SKILL.md
  • references/feature-index-template.md
  • references/feature-readme-template.md
  • references/spec.md
  • scripts/validate_feature_tracks.py

Open the folder on GitHubat commit e742a77

Compare with similar skills

Feature Tracking next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Feature Tracking compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Feature Tracking this skillJunsW/feature-track108—~339Automated safety check: PassMIT
Technical Spec Templatemohitagw15856/pm-claude-skills1.4k—~2.1kAutomated safety check: PassMIT
Prd V06 Technical Specificationmattgierhart/PRD-driven-context-engineering1791 repos~3.4kAutomated safety check: PassMIT
Spec Contract Compliance Reviewbbartling/open-fdd172—~1.4kAutomated safety check: PassCustom licence
Design An Interfacefossasia/eventyay-interpretation1.6k9 repos~842Automated safety check: PassApache-2.0
Dj Prefixed Ulidsdvf/opinionated-django109—~1.4kAutomated safety check: NotesMIT

Similar skills

  • Technical Spec Template

    mohitagw15856/pm-claude-skills

    Create structured technical specification documents that bridge product requirements and engineering implementation.

    1.4k GitHub stars~2.1k tokensUpdated yesterday
    Backend & APIsAuto-check passed
  • Prd V06 Technical Specification

    mattgierhart/PRD-driven-context-engineering

    Define implementation contracts (APIs and data models) that developers will build against during PRD v0.6 Architecture.

    179 GitHub starsUsed in 1 repo~3.4k tokens
    DatabasesAuto-check passed
  • A skill your agent uses to compare any codebase against a specification, API contract, protocol, policy, RFC, security baseline, or product requirements document.

    172 GitHub stars~1.4k tokensUpdated yesterday
    Legal & ComplianceAuto-check passed
  • Design An Interface

    fossasia/eventyay-interpretation

    Generate multiple radically different interface designs for a module using parallel sub-agents.

    1.6k GitHub starsUsed in 9 repos~842 tokens
    Backend & APIsAuto-check passed
  • Dj Prefixed Ulids

    dvf/opinionated-django

    Use Stripe-style prefixed ULID primary keys (e.g. An agent skill from dvf/opinionated-django.

    109 GitHub stars~1.4k tokensUpdated 1 mo ago
    Backend & APIsAuto-check: notes
  • Design Interface

    danielvm-git/bigpowers

    Generate multiple radically different interface designs for a module using parallel sub-agents, then compare trade-offs.

    256 GitHub stars~914 tokensUpdated 16 days ago
    Backend & APIsAuto-check passed

Questions about Feature Tracking

What does Feature Tracking do?

Maintain portable Feature Track docs for project features. An agent skill from JunsW/feature-track. Feature Tracking is an agent skill from JunsW/feature-track. Maintain portable Feature Track docs for project features.

When should I use Feature Tracking?

Feature Tracking fits situations like: finishing feature work; updating PRD/API/design/implementation docs; adding a new feature; validating docs/features.

How do I install Feature Tracking in Claude Code?

Run `npx skills add JunsW/feature-track --skill feature-tracking -a claude-code`. Or copy the skill folder (skills/feature-tracking in JunsW/feature-track) into .claude/skills/feature-tracking in your project. Claude Code loads it when a task matches its description.

How do I install Feature Tracking in Codex?

Run `npx skills add JunsW/feature-track --skill feature-tracking -a codex`. Or copy the skill folder (skills/feature-tracking in JunsW/feature-track) into .agents/skills/feature-tracking in your project. Codex loads it when a task matches its description.

Can I use Feature Tracking in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add JunsW/feature-track --skill feature-tracking -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/feature-tracking, .gemini/skills/feature-tracking, .github/skills/feature-tracking and .opencode/skills/feature-tracking in your project.

What does Feature Tracking need to run?

Going by SKILL.md and its folder, Feature Tracking needs Python for the scripts in its folder and the command-line tools its instructions call (python3). Our summary lists: Python 3.

Does Feature Tracking access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Feature Tracking safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Feature Tracking use?

Feature Tracking is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Feature Tracking use?

About 339 tokens (SKILL.md is roughly 1.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 513 tokens, read only when the agent opens those files.

What are the alternatives to Feature Tracking?

Skills that share tags, products or a category with Feature Tracking: Technical Spec Template (mohitagw15856/pm-claude-skills, 1.4k stars), Prd V06 Technical Specification (mattgierhart/PRD-driven-context-engineering, 179 stars), Spec Contract Compliance Review (bbartling/open-fdd, 172 stars) and Design An Interface (fossasia/eventyay-interpretation, 1.6k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Feature Tracking?

JunsW (a GitHub user) maintains it in JunsW/feature-track, which has 108 GitHub stars. The repository was last updated on July 16, 2026.

Source: JunsW/feature-track on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.