Agent skill

Implement

Implementation entry point. An agent skill from rsmdt/the-startup.

MITAuto-check passed

Install Implement

skills CLI

$ npx skills add rsmdt/the-startup --skill implement -a claude-code

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

GitHub CLI

$ gh skill install rsmdt/the-startup implement --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/rsmdt/the-startup.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/start/skills/implement .claude/skills/implement && 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/

Paste into Claude Code

Install the "implement" agent skill from https://github.com/rsmdt/the-startup/tree/main/plugins/start/skills/implement into .claude/skills/implement/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "implement", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/rsmdt/the-startup/tree/main/plugins/start/skills/implement

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add rsmdt/the-startup --skill implement -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install rsmdt/the-startup implement --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/rsmdt/the-startup.git skills-src && mkdir -p .agents/skills && cp -r skills-src/plugins/start/skills/implement .agents/skills/implement && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "implement" agent skill from https://github.com/rsmdt/the-startup/tree/main/plugins/start/skills/implement into .agents/skills/implement/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "implement", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add rsmdt/the-startup --skill implement -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install rsmdt/the-startup implement --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/rsmdt/the-startup.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/plugins/start/skills/implement .cursor/skills/implement && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "implement" agent skill from https://github.com/rsmdt/the-startup/tree/main/plugins/start/skills/implement into .cursor/skills/implement/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "implement", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/rsmdt/the-startup.git --path plugins/start/skills/implement

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add rsmdt/the-startup --skill implement -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install rsmdt/the-startup implement --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/rsmdt/the-startup.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/plugins/start/skills/implement .gemini/skills/implement && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "implement" agent skill from https://github.com/rsmdt/the-startup/tree/main/plugins/start/skills/implement into .gemini/skills/implement/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "implement", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install rsmdt/the-startup implement

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add rsmdt/the-startup --skill implement -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/rsmdt/the-startup.git skills-src && mkdir -p .github/skills && cp -r skills-src/plugins/start/skills/implement .github/skills/implement && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "implement" agent skill from https://github.com/rsmdt/the-startup/tree/main/plugins/start/skills/implement into .github/skills/implement/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "implement", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add rsmdt/the-startup --skill implement -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install rsmdt/the-startup implement --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/rsmdt/the-startup.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/plugins/start/skills/implement .opencode/skills/implement && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "implement" agent skill from https://github.com/rsmdt/the-startup/tree/main/plugins/start/skills/implement into .opencode/skills/implement/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "implement", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: implement
GitHub stars: 551
Token cost: ~1.3k tokens
SKILL.md length: 412 words
Files: 1
Skills in repo: 27
Repo updated: Aug 3, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Implementation entry point. An agent skill from rsmdt/the-startup.

Works in 4 steps: Resolve Spec → Detect Artifacts → Dispatch → …
Execute a completed specification
SKILL.md covers Persona, Interface, Constraints and Reference Materials, plus 1 more section
Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Implement is an agent skill from rsmdt/the-startup. Implementation entry point. Use to execute a completed specification. Auto-detects the decomposition tier (Direct, Incremental, or Factory) from spec artifacts and dispatches to the matching execution sub-skill.

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: The Agentic Startup - A collection of Claude Code commands, skills, and agents. The licence is MIT.

When your agent uses it

Execute a completed specification

Example prompts

“/implement”

Workflow steps

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

Resolve Spec
Detect Artifacts
Dispatch
Hand Off

What it can do on your machine

Read from SKILL.md and the folder at commit 88d447c. 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

Implement loads about 1.3k tokens when it runs. Until then it costs about 55 tokens; SKILL.md has 412 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~55
When it runs · the whole SKILL.md, loaded when a task matches: ~1.3k

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 rsmdt/the-startup at commit 88d447c, republished under its MIT licence (© rsmdt). 412 words, ~1,257 tokens.

Download SKILL.mdSave it as .claude/skills/implement/SKILL.md (or your agent's skills folder).

name: implement
description: Implementation entry point. Use to execute a completed specification. Auto-detects the decomposition tier (Direct, Incremental, or Factory) from spec artifacts and dispatches to the matching execution sub-skill.
user-invocable: true
argument-hint: spec ID to implement (e.g., 002), or file path

Persona

Act as the implementation entry-point dispatcher. Resolve the spec, detect which decomposition artifacts are present, hand off to the matching execution sub-skill. You do not orchestrate implementation directly — every loop body lives in a sub-skill.

Implementation Target: $ARGUMENTS

Interface

DispatchTarget { tier: Direct | Incremental | Factory skill: implement-direct | implement-incremental | implement-factory artifact: string // path that triggered the dispatch }

State { target = $ARGUMENTS specDirectory: string // resolved .start/specs/NNN-name/ path artifacts: { plan?: string // path to plan/README.md if present manifest?: string // path to manifest.md if present requirements?: string // path to requirements.md solution?: string // path to solution.md } dispatch: DispatchTarget }

Constraints

Always:

Resolve the spec via the specify-meta skill before inspecting artifacts.
Detect artifacts before dispatching — do not assume a tier.
Pass $ARGUMENTS through unchanged to the sub-skill.
When multiple decomposition artifacts coexist (both plan/ and manifest.md), ask the user which to run.
Surface what was detected so the user can confirm the dispatch target.

Never:

Implement code directly — sub-skills own all execution logic.
Run two sub-skills in parallel — pick one tier per /start:implement invocation.
Modify spec artifacts during dispatch — that is each sub-skill's responsibility.

Reference Materials

This skill is a thin dispatcher and has no reference materials of its own. Each sub-skill owns its references, examples, and templates:

implement-direct — phase-less orchestrator for low-complexity work
implement-incremental — linear phase loop for single-feature plans
implement-factory — factory loop with information barriers and retry

Workflow

Show full SKILL.md (190 more words)Show less

1. Resolve Spec

Use the specify-meta skill with $ARGUMENTS to resolve specDirectory. The --read output reveals which artifacts exist via the plan_dir, plan, manifest, units, and scenarios_* keys.

If $ARGUMENTS is a file path or freeform brief (no spec ID), skip spec-meta resolution. Treat this as a direct-mode invocation and route to implement-direct.

2. Detect Artifacts

Inspect the resolved spec directory for decomposition artifacts:

manifest_md    = exists(specDirectory / "manifest.md")
plan_readme    = exists(specDirectory / "plan" / "README.md")
requirements   = exists(specDirectory / "requirements.md")
solution       = exists(specDirectory / "solution.md")

3. Dispatch

Apply the routing rules:

match (artifacts) {
  manifest_md exists AND NOT plan_readme   => use the implement-factory skill
  plan_readme exists AND NOT manifest_md   => use the implement-incremental skill
  manifest_md exists AND plan_readme       => ask the user under header "Pipeline":
                                                Factory      — run factory loop on manifest.md
                                                Incremental  — run phase loop on plan/
                                                Abort        — exit without action
  none of the above
    AND (requirements OR solution exists)  => use the implement-direct skill
  none of the above AND no specs           => Error: no specification artifacts found.
                                              Run the specify skill first, or pass a brief.
}

Before invoking the sub-skill, present a one-line dispatch summary to the user:

Detected: manifest.md → routing to implement-factory

Detected: plan/README.md → routing to implement-incremental

Detected: only requirements.md and solution.md → routing to implement-direct

4. Hand Off

Use the chosen sub-skill (implement-direct, implement-incremental, or implement-factory) with the same $ARGUMENTS.

Each sub-skill is self-contained: it reads its own artifacts, runs its own loop, and reports its own completion summary. The dispatcher does not post-process sub-skill output.

Notes on tier mismatch

If the spec README decision log records a tier (e.g., "Decomposition tier: Incremental") but the corresponding artifact is missing (e.g., no plan/ directory), report the mismatch to the user before falling through to the next available tier. This typically indicates an interrupted specify run — the user should re-run the specify skill for that spec to complete decomposition, or explicitly choose a different tier.

Files

Just SKILL.md in plugins/start/skills/implement of rsmdt/the-startup.

Open the folder on GitHubat commit 88d447c

Compare with similar skills

Implement 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.

Implement compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Implement this skillrsmdt/the-startup	551	—	~1.3k	Automated safety check: Pass	MIT	2 mo ago
Implementing API Abuse Detection With Rate Limitingmukul975/Anthropic-Cybersecurity-Skills	34k	—	~3.4k	Automated safety check: Pass	Apache-2.0	1 mo ago
Implementing Siem Use Cases For Detectionmukul975/Anthropic-Cybersecurity-Skills	34k	—	~2.8k	Automated safety check: Pass	Apache-2.0	1 mo ago
Implementing Honeypot For Ransomware Detectionmukul975/Anthropic-Cybersecurity-Skills	34k	—	~3.9k	Automated safety check: Pass	Apache-2.0	1 mo ago
Detecting Suspicious Powershell Executionmukul975/Anthropic-Cybersecurity-Skills	34k	—	~923	Automated safety check: Pass	Apache-2.0	1 mo ago
Implementing Endpoint Detection With Wazuhmukul975/Anthropic-Cybersecurity-Skills	34k	—	~582	Automated safety check: Pass	Apache-2.0	1 mo ago

Similar skills

Implementing API Abuse Detection With Rate Limiting
mukul975/Anthropic-Cybersecurity-Skills
Implements API abuse detection using token bucket, sliding window, and fixed window rate-limiting algorithms backed by Redis, including adaptive limits that tighten during detected attacks and relax…
34k GitHub stars~3.4k tokensUpdated 1 mo ago
Backend & APIsAuto-check passed
Implementing Siem Use Cases For Detection
mukul975/Anthropic-Cybersecurity-Skills
Implements SIEM detection use cases by designing correlation rules, threshold alerts, and behavioral analytics mapped to MITRE ATT&CK techniques across Splunk, Elastic, and Sentinel.
34k GitHub stars~2.8k tokensUpdated 1 mo ago
SecurityAuto-check passed
Implementing Honeypot For Ransomware Detection
mukul975/Anthropic-Cybersecurity-Skills
Deploys canary files, honeypot shares, and decoy systems to detect ransomware activity at the earliest possible stage.
34k GitHub stars~3.9k tokensUpdated 1 mo ago
DevOps & CloudAuto-check passed
Detecting Suspicious Powershell Execution
mukul975/Anthropic-Cybersecurity-Skills
Hunt for suspicious PowerShell execution (T1059.001) such as encoded commands, download cradles, AMSI bypass, and constrained language mode evasion using EDR telemetry (CrowdStrike, Microsoft…
34k GitHub stars~923 tokensUpdated 1 mo ago
SecurityAuto-check passed
Implementing Endpoint Detection With Wazuh
mukul975/Anthropic-Cybersecurity-Skills
Deploys and configures Wazuh SIEM/XDR for endpoint detection, covering agent authentication and management, custom decoder and rule XML creation, alert querying via the Wazuh REST API, rule testing…
34k GitHub stars~582 tokensUpdated 1 mo ago
SecurityAuto-check passed
Implementing Ransomware Kill Switch Detection
mukul975/Anthropic-Cybersecurity-Skills
Analyzes ransomware kill switch mechanisms, including mutex-based execution guards, domain-based kill switches (e.g.
34k GitHub stars~2.4k tokensUpdated 1 mo ago
DevOps & CloudAuto-check passed

Questions about Implement

What does Implement do?

Implementation entry point. An agent skill from rsmdt/the-startup. Implement is an agent skill from rsmdt/the-startup. Implementation entry point.

When should I use Implement?

Implement fits situations like: execute a completed specification.

How do I install Implement in Claude Code?

Run `npx skills add rsmdt/the-startup --skill implement -a claude-code`. Or copy the skill folder (plugins/start/skills/implement in rsmdt/the-startup) into .claude/skills/implement in your project. Claude Code loads it when a task matches its description.

How do I install Implement in Codex?

Run `npx skills add rsmdt/the-startup --skill implement -a codex`. Or copy the skill folder (plugins/start/skills/implement in rsmdt/the-startup) into .agents/skills/implement in your project. Codex loads it when a task matches its description.

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

What does Implement need to run?

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

Does Implement 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 Implement 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 Implement use?

Implement 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 Implement use?

About 1.3k tokens (SKILL.md is roughly 5k 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 Implement?

Skills that share tags, products or a category with Implement: Implementing API Abuse Detection With Rate Limiting (mukul975/Anthropic-Cybersecurity-Skills, 34k stars), Implementing Siem Use Cases For Detection (mukul975/Anthropic-Cybersecurity-Skills, 34k stars), Implementing Honeypot For Ransomware Detection (mukul975/Anthropic-Cybersecurity-Skills, 34k stars) and Detecting Suspicious Powershell Execution (mukul975/Anthropic-Cybersecurity-Skills, 34k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Implement?

rsmdt (a GitHub user) maintains it in rsmdt/the-startup, which has 551 GitHub stars. The repository holds 27 skills in this directory. The repository was last updated on August 3, 2026.

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

Install Implement

Facts

At a glance

What it does

When your agent uses it

Example prompts

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Persona

Interface

Constraints

Reference Materials

Workflow

1. Resolve Spec

2. Detect Artifacts

3. Dispatch

4. Hand Off

Notes on tier mismatch

Files

Compare with similar skills

Similar skills

More from rsmdt/the-startup

Questions about Implement