Agent skill

Perform Implement Plan

by POW-Software in POW-Software/ByteSync

Execute an implementation plan end-to-end in the ByteSync repo.

MITAuto-check passedAgent Workflows

Install Perform Implement Plan

skills CLI
$ npx skills add POW-Software/ByteSync --skill perform-implement-plan -a claude-code

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

GitHub CLI
$ gh skill install POW-Software/ByteSync perform-implement-plan --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/POW-Software/ByteSync.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/perform-implement-plan .claude/skills/perform-implement-plan && 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
perform-implement-plan
GitHub stars
172
Token cost
~426 tokens
SKILL.md length
203 words
Files
1
Skills in repo
4
Repo updated
First seen
Licence
MIT

At a glance

Execute an implementation plan end-to-end in the ByteSync repo.

  • Works in 5 steps: Confirm plan scope → Create a branch before implementation → Implement step by step → …
  • The user asks to implement a previously established plan step by step
  • SKILL.md covers Overview and Workflow
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Perform Implement Plan is an agent skill from POW-Software/ByteSync. Execute an implementation plan end-to-end in the ByteSync repo. Use when the user asks to implement a previously established plan step by step, requires creating a branch before coding, expects regular commits during progress, and wants build/test validation.

Its SKILL.md is about 430 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows, covering Planning and End-to-end testing. The repository describes itself as: ByteSync is a free and open-source tool for file synchronization, backup, and deduplication. It works locally or remotely, with no VPNs or firewall configuration required… The licence is MIT.

When your agent uses it

  • The user asks to implement a previously established plan step by step
  • Requires creating a branch before coding
  • Expects regular commits during progress
  • Wants build/test validation

Example prompts

  • “/perform-implement-plan”

Workflow steps

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

  1. Confirm plan scope
  2. Create a branch before implementation
  3. Implement step by step
  4. Respect repo conventions and validation
  5. Keep the user informed

What it can do on your machine

Read from SKILL.md and the folder at commit 397a1d1. 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

    No scripts in the folder and no shell commands in SKILL.md.

    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

Perform Implement Plan loads about 426 tokens when it runs. Until then it costs about 71 tokens; SKILL.md has 203 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~71
When it runs · the whole SKILL.md, loaded when a task matches
~426

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 POW-Software/ByteSync at commit 397a1d1, republished under its MIT licence (© POW-Software). 203 words, ~426 tokens.

Download SKILL.mdSave it as .claude/skills/perform-implement-plan/SKILL.md (or your agent's skills folder).
name
perform-implement-plan
description
Execute an implementation plan end-to-end in the ByteSync repo. Use when the user asks to implement a previously established plan step by step, requires creating a branch before coding, expects regular commits during progress, and wants build/test validation.

Plan Implementation

Overview

Implement a previously agreed plan in ByteSync, one step at a time, while enforcing branch creation and frequent commits.

Workflow

1) Confirm plan scope

Restate the implementation plan in brief. If the plan is not present in the conversation, ask for it before starting.

2) Create a branch before implementation

Create a new branch before making any code changes. The branch name must follow ByteSync guidelines:

  • Use one prefix only: feature/, fix/, refactor/, docs/, or test/
  • Avoid extra slashes beyond the prefix
  • Include the issue number if an issue exists (e.g., feature/1234-add-sync-filter)
  • Add a short English description
3) Implement step by step

Implement the plan in small, ordered steps. After each step:

  • Verify the change fits the plan
  • Commit the work with a concise English message
  • Keep commits focused and incremental
4) Respect repo conventions and validation

Follow the repo guidance (AGENTS.md), including:

  • Do not add unnecessary comments
  • Use FluentAssertions for tests
  • Build and test as separate commands
  • During intermediate commits, run only tests related to the changes when reasonable
  • At the end, run the full solution tests
5) Keep the user informed

Provide short progress updates after each step and call out any blockers or missing details before proceeding.

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

Files

Just SKILL.md in skills/perform-implement-plan of POW-Software/ByteSync.

Open the folder on GitHubat commit 397a1d1

Compare with similar skills

Perform Implement Plan 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.

Perform Implement Plan compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Perform Implement Plan this skillPOW-Software/ByteSync172—~426Automated safety check: PassMIT
Create Featurezacharyfmarion/openscad-studio238—~1.5kAutomated safety check: PassGPL-2.0
Sesori Plan Workersesori-ai/sesori_apps_monorepo126—~2.9kAutomated safety check: PassCustom licence
Bleudavila7/claude-code-templates32k—~8.9kAutomated safety check: PassMIT
Feature Development WorkflowQwenLM/qwen-code28k—~1.2kAutomated safety check: PassApache-2.0
Executing Plans Inlineobra/superpowers296k2 repos~5.1kAutomated safety check: PassMIT

Similar skills

  • Create Feature

    zacharyfmarion/openscad-studio

    A skill your agent uses when the user asks to take a feature or bug fix from prompt to implementation, especially prompts like "/create a new feature", "build this feature end-to-end", "take this…

    238 GitHub stars~1.5k tokensUpdated 1 mo ago
    Agent WorkflowsAuto-check passed
  • Sesori Plan Worker

    sesori-ai/sesori_apps_monorepo

    Execute plans and multi-step PR series end to end. An agent skill from sesori-ai/sesori_apps_monorepo.

    126 GitHub stars~2.9k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Bleu

    davila7/claude-code-templates

    A skill your agent uses whenever a developer wants to turn an idea into a complete, production-ready, end-to-end system plan BEFORE writing any code.

    32k GitHub stars~8.9k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Phased workflow for non-trivial qwen-code features: investigate, design doc, E2E test plan, baseline dry-run, implement, verify, self-audit, review and iterate.

    28k GitHub stars~1.2k tokensUpdated today
    DevelopmentAuto-check passed
  • Executing Plans Inline

    obra/superpowers

    Has the agent carry out an implementation plan itself, task by task in the current session, keeping a ledger, proving each step with a test and ending with one whole-branch review.

    296k GitHub starsUsed in 2 repos~5.1k tokens
    Agent WorkflowsAuto-check passed
  • Interview Me

    addyosmani/agent-skills

    Asks one question at a time, each with a best guess attached, until the agent is about 95 percent sure what you really want, before any plan, spec or code.

    103k GitHub starsUsed in 6 repos~3.8k tokens
    Agent WorkflowsAuto-check passed

More from POW-Software/ByteSync

  • Gh Issue Specifier

    POW-Software/ByteSync

    Analyze a GitHub issue in depth and produce a detailed specification based on codebase analysis.

    172 GitHub stars~643 tokensUpdated 5 mo ago
    Auto-check passed
  • Create PR

    POW-Software/ByteSync

    Push the current branch and create a Pull Request for ByteSync.

    172 GitHub stars~327 tokensUpdated 5 mo ago
    Auto-check passed
  • Implementation Plan

    POW-Software/ByteSync

    Produce a structured implementation plan (no code) from an existing specification or deep analysis.

    172 GitHub stars~391 tokensUpdated 5 mo ago
    Auto-check passed

Categories

Questions about Perform Implement Plan

What does Perform Implement Plan do?

Execute an implementation plan end-to-end in the ByteSync repo. Perform Implement Plan is an agent skill from POW-Software/ByteSync. Execute an implementation plan end-to-end in the ByteSync repo.

When should I use Perform Implement Plan?

Perform Implement Plan fits situations like: the user asks to implement a previously established plan step by step; requires creating a branch before coding; expects regular commits during progress; wants build/test validation.

How do I install Perform Implement Plan in Claude Code?

Run `npx skills add POW-Software/ByteSync --skill perform-implement-plan -a claude-code`. Or copy the skill folder (skills/perform-implement-plan in POW-Software/ByteSync) into .claude/skills/perform-implement-plan in your project. Claude Code loads it when a task matches its description.

How do I install Perform Implement Plan in Codex?

Run `npx skills add POW-Software/ByteSync --skill perform-implement-plan -a codex`. Or copy the skill folder (skills/perform-implement-plan in POW-Software/ByteSync) into .agents/skills/perform-implement-plan in your project. Codex loads it when a task matches its description.

Can I use Perform Implement Plan 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 POW-Software/ByteSync --skill perform-implement-plan -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/perform-implement-plan, .gemini/skills/perform-implement-plan, .github/skills/perform-implement-plan and .opencode/skills/perform-implement-plan in your project.

What does Perform Implement Plan need to run?

SKILL.md names no scripts, command-line tools or credentials: Perform Implement Plan is instructions for the agent only.

Does Perform Implement Plan 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 Perform Implement Plan 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 Perform Implement Plan use?

Perform Implement Plan 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 Perform Implement Plan use?

About 426 tokens (SKILL.md is roughly 1.7k 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 Perform Implement Plan?

Skills that share tags, products or a category with Perform Implement Plan: Create Feature (zacharyfmarion/openscad-studio, 238 stars), Sesori Plan Worker (sesori-ai/sesori_apps_monorepo, 126 stars), Bleu (davila7/claude-code-templates, 32k stars) and Feature Development Workflow (QwenLM/qwen-code, 28k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Perform Implement Plan?

POW-Software (a GitHub organization) maintains it in POW-Software/ByteSync, which has 172 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on May 7, 2026.

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