Agent skill

Feature

by garagon in garagon/nanostack

Add a feature to an existing project with a full sprint. An agent skill from garagon/nanostack.

Apache-2.0Auto-check passed

Install Feature

skills CLI
$ npx skills add garagon/nanostack --skill feature -a claude-code

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

GitHub CLI
$ gh skill install garagon/nanostack feature --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/garagon/nanostack.git skills-src && mkdir -p .claude/skills && cp -r skills-src/feature .claude/skills/feature && 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
GitHub stars
207
Token cost
~1.4k tokens
SKILL.md length
633 words
Files
2
Skills in repo
14
Repo updated
First seen
Licence
Apache-2.0

At a glance

Add a feature to an existing project with a full sprint. An agent skill from garagon/nanostack.

  • Works in 5 steps: Context → Plan → Build → …
  • The user knows what they want and the project already exists
  • SKILL.md covers Telemetry preamble, Setup, Session and Process, plus 2 more sections
  • Runs Shell scripts from its folder

What it does

Feature is an agent skill from garagon/nanostack. Add a feature to an existing project with a full sprint. Skips /think diagnostic, goes straight to planning. Use when the user knows what they want and the project already exists. Triggers on /feature.

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `bin/enforce-sprint.sh`).

The repository describes itself as: A workflow harness that helps AI coding agents plan, review, test, and ship safer code. The licence is Apache-2.0.

When your agent uses it

  • The user knows what they want and the project already exists

Example prompts

  • “/feature”

Requirements

  • A Bash shell

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Context
  2. Plan
  3. Build
  4. Review + Security + QA (parallel)
  5. Ship

What it can do on your machine

Read from SKILL.md and the folder at commit 0372aed. 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 script files (Shell), which the agent can run.

    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 loads about 1.4k tokens when it runs. Until then it costs about 52 tokens; SKILL.md has 633 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~52
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k

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); files beside SKILL.md are not scanned.

SKILL.md

The full file from garagon/nanostack at commit 0372aed, republished under its Apache-2.0 licence (© garagon). 633 words, ~1,421 tokens.

Download SKILL.mdSave it as .claude/skills/feature/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
feature
description
Add a feature to an existing project with a full sprint. Skips /think diagnostic, goes straight to planning. Use when the user knows what they want and the project already exists. Triggers on /feature.
concurrency
read
summary
Fast sprint for incremental features. Reads existing artifacts, plans, builds, reviews, audits, ships.
estimated_tokens
200

/feature — Add a Feature

Fast path for adding a feature to an existing project. Skips the /think diagnostic and runs the full sprint via skill invocations.

/feature Add import from JSON/CSV to restore backups

Telemetry preamble

Defensive telemetry init. No-op if telemetry is disabled via NANOSTACK_NO_TELEMETRY=1, ~/.nanostack/.telemetry-disabled, or if the helpers are removed.

bash
_P="$HOME/.claude/skills/nanostack/bin/lib/skill-preamble.sh"
[ -f "$_P" ] && . "$_P" feature
unset _P

Setup

Before anything else, ensure the project is configured. Run this once (skips if already done):

bash
[ -f .claude/settings.json ] || ~/.claude/skills/nanostack/bin/init-project.sh

Session

For a direct invocation, initialize the sprint session with autopilot and explicit plan auto-approval. When /think hands off a completed autopilot brief, keep that active session instead: do not archive it or initialize a replacement. Confirm its workspace matches the current project, type=development, autopilot=true, run_mode=normal, think is completed, no phase is in progress, and plan has not started. If that handoff state is inconsistent, stop and report it rather than overwrite the session.

bash
~/.claude/skills/nanostack/bin/session.sh init feature --autopilot --plan-approval auto

Manual feature work should use /think + /nano instead. /feature itself does not accept a manual mode flag.

Let /nano start the plan phase. Phase-gate enforcement depends on the active adapter; do not describe guided hosts as hook-enforced.

Process

You are the full-sprint coordinator. Invoke each specialist once and wait for its result. Continue routine work without asking permission between phases; stop for unresolved scope, unsafe test environments, blocking findings you cannot fix, or an action requiring user authorization.

Auto-approval is not publication permission. plan_approval=auto approves planning, not PR creation, merge, or deployment. Preserve /ship's preview and explicit authorization requirements. Tell delegated specialists to return their artifacts and findings to this coordinator, not launch another phase.

Step 1: Context

Resolve existing artifacts and solutions in one call:

bash
~/.claude/skills/nanostack/bin/resolve.sh feature

The output is JSON with upstream_artifacts (think, plan, ship paths if recent) and solutions (ranked past learnings). Read the checkpoint summaries. If no artifacts exist, read the codebase directly.

Step 2: Plan
Invoke /nano using the active host's skill mechanism.

Wait for /nano to complete. It saves its own artifact. Then immediately build.

Step 3: Build

Run session.sh phase-start build, then implement the approved plan. Run session.sh phase-complete build only after implementation finishes. Do not launch verification against an unfinished build.

Show full SKILL.md (299 more words)Show less
Step 4: Review + Security + QA (parallel)

Use native delegation only when the active host exposes it. Give each specialist the approved scope, build under test, and this boundary: inspect and report; do not edit product files, commit, or invoke another skill. QA must use isolated test data and output directories. Shared mutable services or fixtures require sequential verification.

Otherwise invoke /review, /security, and /qa sequentially using the host's skill mechanism. If delegation fails after any reader has started, wait for or cancel and confirm termination of that reader before falling back; never launch duplicate work against a still-running batch. Guided adapters rely on these instructions, not universal hook enforcement.

If verification finds blocking issues, wait for all readers to finish (or confirm cancellation), return to build, and apply repairs there. After any product change, re-run all three verification phases before /ship. Do not carry passing results from the previous build forward. If a repair exceeds approved scope, ask the user instead.

Feature: review + security + qa complete. Running /ship...

Step 5: Ship
Invoke /ship using the active host's skill mechanism.

/ship commits, creates PR if remote exists, generates sprint journal, runs /compound, and shows the result with next feature suggestions.

Telemetry finalize

Before returning control:

bash
_F="$HOME/.claude/skills/nanostack/bin/lib/skill-finalize.sh"
[ -f "$_F" ] && . "$_F" feature success
unset _F

Pass abort or error instead of success if the feature flow did not complete normally.

Rules

  • One orchestration owner. /feature owns planning, build, verification, and the authorized shipping handoff. Specialists return results; they do not start another sprint.
  • Invoke each skill through the active host's skill mechanism, not by reimplementing it inline.
  • Each skill saves its own artifact. You do not save artifacts — the skills do.
  • Between steps, show one line of status: Feature: review complete. Running /security...
  • Stop when scope, safety, or publication authorization requires a user decision.
  • If the feature already exists in the codebase, tell the user and suggest alternatives.

© garagon, Apache-2.0. 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 1 other file in feature of garagon/nanostack.

  • SKILL.md
  • bin/enforce-sprint.sh

Open the folder on GitHubat commit 0372aed

Compare with similar skills

Feature 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 compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Feature this skillgaragon/nanostack207—~1.4kAutomated safety check: PassApache-2.0
Sprint Planphuryn/pm-skills27k—~590Automated safety check: PassMIT
Sprint Status SnapshotDonchitos/Claude-Code-Game-Studios26k—~3kAutomated safety check: PassMIT
Sprint Plan BuilderDonchitos/Claude-Code-Game-Studios26k—~4.1kAutomated safety check: PassMIT
Skip Linkthedaviddias/Front-End-Checklist74k—~402Automated safety check: PassMIT
Skip Navigationthedaviddias/Front-End-Checklist74k—~443Automated safety check: PassMIT

Similar skills

  • Sprint Plan

    phuryn/pm-skills

    Plan a sprint with capacity estimation, story selection, dependency mapping, and risk identification.

    27k GitHub stars~590 tokensUpdated 23 days ago
    Product & Project ManagementAuto-check passed
  • Sprint Status Snapshot

    Donchitos/Claude-Code-Game-Studios

    Gives a fast, read-only sprint snapshot with burndown and emerging risks in under 30 lines, plus at most one concrete recommendation.

    26k GitHub stars~3k tokensUpdated 9 days ago
    Product & Project ManagementAuto-check passed
  • Sprint Plan Builder

    Donchitos/Claude-Code-Game-Studios

    Creates or updates a sprint plan from the current milestone, completed work and available capacity, sizing the story count to the project's granularity setting.

    26k GitHub stars~4.1k tokensUpdated 9 days ago
    Product & Project ManagementAuto-check passed
  • Skip Link

    thedaviddias/Front-End-Checklist

    A skill your agent uses when reviewing rendered HTML, interactive components, or design-system patterns related to Implement 'Skip to Content' links.

    74k GitHub stars~402 tokensUpdated 2 days ago
    Frontend & DesignAuto-check passed
  • Skip Navigation

    thedaviddias/Front-End-Checklist

    A skill your agent uses when reviewing rendered HTML, interactive components, or design-system patterns related to Include a skip navigation link.

    74k GitHub stars~443 tokensUpdated 2 days ago
    Frontend & DesignAuto-check passed
  • Sprint

    ww-w-ai/bkit-claude-code

    Sprint Management — generic sprint capability for ANY bkit user.

    601 GitHub stars~6.7k tokensUpdated 11 days ago
    Product & Project ManagementAuto-check: notes

More from garagon/nanostack

All 14 skills in this repo
  • Nano

    garagon/nanostack

    A skill your agent uses when starting non-trivial work (touching 3+ files, new features, refactors, bug investigations).

    207 GitHub stars~3.3k tokensUpdated 28 days ago
    Auto-check passed
  • Nano Run

    garagon/nanostack

    First-time setup and guided sprint. An agent skill from garagon/nanostack.

    207 GitHub stars~3k tokensUpdated 28 days ago
    Auto-check passed
  • Security

    garagon/nanostack

    Use before shipping to production. An agent skill from garagon/nanostack.

    207 GitHub stars~3.7k tokensUpdated 28 days ago
    Auto-check: notes
  • Ship

    garagon/nanostack

    A skill your agent uses when code is ready to ship — creates PRs, merges, deploys, and verifies.

    207 GitHub stars~4.2k tokensUpdated 28 days ago
    Auto-check passed
  • Compound

    garagon/nanostack

    Document what you learned during this sprint. An agent skill from garagon/nanostack.

    207 GitHub stars~2.2k tokensUpdated 28 days ago
    Auto-check passed
  • Conductor

    garagon/nanostack

    Orchestrate parallel agent sessions through a sprint. An agent skill from garagon/nanostack.

    207 GitHub stars~2.6k tokensUpdated 28 days ago
    Auto-check passed

Questions about Feature

What does Feature do?

Add a feature to an existing project with a full sprint. An agent skill from garagon/nanostack. Feature is an agent skill from garagon/nanostack. Add a feature to an existing project with a full sprint.

When should I use Feature?

Feature fits situations like: the user knows what they want and the project already exists.

How do I install Feature in Claude Code?

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

How do I install Feature in Codex?

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

Can I use Feature 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 garagon/nanostack --skill feature -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, .gemini/skills/feature, .github/skills/feature and .opencode/skills/feature in your project.

What does Feature need to run?

Going by SKILL.md and its folder, Feature needs a shell for the scripts in its folder. Our summary lists: A Bash shell.

Does Feature 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 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. Review the folder before installing.

What licence does Feature use?

Feature is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Feature use?

About 1.4k tokens (SKILL.md is roughly 5.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Feature?

Skills that share tags, products or a category with Feature: Sprint Plan (phuryn/pm-skills, 27k stars), Sprint Status Snapshot (Donchitos/Claude-Code-Game-Studios, 26k stars), Sprint Plan Builder (Donchitos/Claude-Code-Game-Studios, 26k stars) and Skip Link (thedaviddias/Front-End-Checklist, 74k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Feature?

garagon (a GitHub user) maintains it in garagon/nanostack, which has 207 GitHub stars. The repository holds 14 skills in this directory. The repository was last updated on September 10, 2026.

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