Agent skill

Implement Incremental

by rsmdt in rsmdt/the-startup

Linear phase-loop orchestrator for single-feature implementation plans.

MITAuto-check passedAgent Workflows

Install Implement Incremental

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

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

GitHub CLI
$ gh skill install rsmdt/the-startup implement-incremental --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-incremental .claude/skills/implement-incremental && 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
implement-incremental
GitHub stars
536
Token cost
~1.7k tokens
SKILL.md length
852 words
Files
21
Skills in repo
27
Repo updated
First seen
Licence
MIT

At a glance

Linear phase-loop orchestrator for single-feature implementation plans.

  • Works in 7 steps: Initialize → Select Mode → Phase Loop → …
  • Medium-complexity work where transparent human-in-the-loop phase review is preferred over factory automation
  • 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 Incremental is an agent skill from rsmdt/the-startup. Linear phase-loop orchestrator for single-feature implementation plans. Use for medium-complexity work where transparent human-in-the-loop phase review is preferred over factory automation.

Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 28 other files (for example `evals/evals.json`, `evals/fixtures/eval-1-happy-path/plan/README.md` and `evals/fixtures/eval-1-happy-path/plan/phase-1.md`).

It sits in Agent Workflows, covering Human-in-the-loop approvals and Planning. 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

  • Medium-complexity work where transparent human-in-the-loop phase review is preferred over factory automation
  • Tasks that involve Human-in-the-loop approvals
  • Tasks that involve Planning

Example prompts

  • “/implement-incremental”

Workflow steps

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

  1. Initialize
  2. Select Mode
  3. Phase Loop
  4. Execute Phase
  5. Validate Phase
  6. Update Phase Status
  7. Complete

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 Incremental loads about 1.7k tokens when it runs. Until then it costs about 53 tokens; SKILL.md has 852 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~53
When it runs · the whole SKILL.md, loaded when a task matches
~1.7k

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). 852 words, ~1,734 tokens.

Download SKILL.mdSave it as .claude/skills/implement-incremental/SKILL.md (or your agent's skills folder). This skill also uses 20 other files; get the full folder from GitHub.
name
implement-incremental
description
Linear phase-loop orchestrator for single-feature implementation plans. Use for medium-complexity work where transparent human-in-the-loop phase review is preferred over factory automation.
user-invocable
false
argument-hint
spec ID to implement (e.g., 002), or file path

Persona

Act as an implementation orchestrator that executes specification plans by delegating all coding tasks to specialist agents. You are the human-in-the-loop pipeline — phase boundaries are confirmation gates, drift detection runs after every phase, and the user can pause-and-resume at will.

Implementation Target: $ARGUMENTS

Interface

Phase { number: number title: string file: string // path to phase-N.md status: pending | in_progress | completed }

PhaseResult { phase: number tasksCompleted: number totalTasks: number filesChanged: string[] testStatus: string // All passing | X failing | Pending blockers?: string[] }

State { target = $ARGUMENTS spec: string // resolved spec directory path planDirectory: string // path to plan/ directory manifest: string // plan/README.md contents phases: Phase[] // discovered from manifest, with status from frontmatter mode: Standard | Agent Team currentPhase: number results: PhaseResult[] }

Constraints

Always:

  • Delegate ALL implementation tasks to specialist subagents or teammates.
  • Summarize agent results — extract files, summary, tests, blockers for user visibility.
  • Load only the current phase file — one phase at a time for context efficiency.
  • Wait for user confirmation at phase boundaries.
  • Use the validate skill in drift mode at each phase checkpoint.
  • Use the validate skill in constitution mode if a CONSTITUTION.md exists at the project root.
  • Pass accumulated context between phases — only relevant prior outputs + specs.
  • Update phase file frontmatter AND plan/README.md checkbox on phase completion.
  • Skip already-completed phases when resuming an interrupted plan.

Never:

  • Implement code directly — you are an orchestrator ONLY.
  • Display full agent responses — extract key outputs only.
  • Skip phase boundary checkpoints.
  • Proceed past a blocking constitution violation (L1/L2).

Reference Materials

  • Output Format — Task result guidelines, phase summary, completion summary
  • Output Example — Concrete example of expected output format
  • Perspectives — Implementation perspectives and work stream mapping

Workflow

1. Initialize

Use the specify-meta skill to read the spec.

Discover the plan structure:

Read plan/README.md (the manifest). Parse phase checklist lines matching: - [x] [Phase N: Title](phase-N.md) or - [ ] [Phase N: Title](phase-N.md) For each discovered phase file: Read YAML frontmatter to get status (pending | in_progress | completed). Populate phases[] with number, title, file path, and status.

If plan/README.md does not exist, report an error: this skill requires a plan/ directory. Refer the user to the specify-incremental skill to create one, or to the implement skill (which auto-detects tier).

Present discovered phases with their statuses. Highlight completed phases (will be skipped) and in_progress phases (will be resumed).

Task metadata found in plan files uses: [activity: areas], [parallel: true], [ref: solution/Section X.Y]

Offer optional git setup:

match (git repository) { exists => ask the user to choose between Create feature branch and Skip git integration none => proceed without version control }

2. Select Mode

Ask the user to choose:

  • Standard (default) — parallel fire-and-forget subagents with progress tracked on the task list
  • Agent Team — persistent teammates with shared task list and coordination

Recommend Agent Team when: phases >= 3 | cross-phase dependencies | parallel tasks >= 5 | shared state across tasks

3. Phase Loop

For each phase in phases where phase.status != completed:

  1. Mark phase status as in_progress (call step 6).
  2. Execute the phase (step 4).
  3. Validate the phase (step 5).
  4. After validation, ask the user how to proceed:

match (user choice) { "Continue to next phase" => continue loop "Pause" => break loop (plan is resumable) "Review output" => present details, then re-ask "Address issues" => fix, then re-validate current phase }

After the loop:

match (all phases completed) { true => run step 7 (Complete) false => report progress, plan is resumable from next pending phase }

Show full SKILL.md (307 more words)Show less
4. Execute Phase

Read plan/phase-{phase.number}.md for current phase tasks. Read the Phase Context section: GATE, spec references, key decisions, dependencies.

match (mode) { Standard => { Load ONLY current phase tasks onto the task list. Parallel tasks (marked [parallel: true]): launch ALL in a single response. Sequential tasks: launch one, await result, then next. Update task list status after each task. } Agent Team => { Create tasks for the team with phase/task metadata and dependency chains. Spawn teammates by work stream — only roles needed for current phase. Assign tasks. Monitor via automatic messages and the shared task list. } }

As tasks complete, update task checkboxes in phase-N.md: - [ ] → - [x]

Review handling: APPROVED → next task | Spec violation → must fix | Revision needed → max 3 cycles | After 3 → escalate to user

5. Validate Phase
  1. Use the validate skill in drift mode for spec alignment.
  2. Use the validate skill in constitution mode if a CONSTITUTION.md exists at the project root.
  3. Verify all phase tasks are complete.
  4. Mark phase status as completed (call step 6).

Drift types: Scope Creep, Missing, Contradicts, Extra. When drift is detected: ask the user to choose between Acknowledge, Update impl, Update spec, or Defer.

Read reference/output-format.md and present the phase summary accordingly. Ask the user to choose between Continue to next phase, Review output, Pause, or Address issues.

6. Update Phase Status
  1. Edit phase file frontmatter: status: {old} → status: {new}
  2. If status is completed, edit plan/README.md: - [ ] [Phase {N}: {Title}](phase-{N}.md) → - [x] [Phase {N}: {Title}](phase-{N}.md)
7. Complete
  1. Use the validate skill in comparison mode for final validation.
  2. Read reference/output-format.md and present completion summary accordingly.

match (git integration) { active => ask the user to choose between Commit + PR, Commit only, or Skip none => ask the user to choose between Run tests, Deploy to staging, or Manual review }

In Agent Team: send sequential shutdown_request to each teammate, then disband the team.

© rsmdt, 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 20 other files in plugins/start/skills/implement-incremental of rsmdt/the-startup.

  • SKILL.md
  • evals/evals.json
  • evals/fixtures/eval-1-happy-path/plan/README.md
  • evals/fixtures/eval-1-happy-path/plan/phase-1.md
  • evals/fixtures/eval-1-happy-path/plan/phase-2.md
  • evals/fixtures/eval-1-happy-path/plan/phase-3.md
  • evals/fixtures/eval-2-resume/plan/README.md
  • evals/fixtures/eval-2-resume/plan/phase-1.md
  • evals/fixtures/eval-2-resume/plan/phase-2.md
  • evals/fixtures/eval-2-resume/plan/phase-3.md
  • evals/fixtures/eval-3-parallel-tasks/plan/README.md
  • evals/fixtures/eval-3-parallel-tasks/plan/phase-1.md
  • evals/fixtures/eval-3-parallel-tasks/plan/phase-2.md
  • … and 8 more

Open the folder on GitHubat commit 88d447c

Compare with similar skills

Implement Incremental 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 Incremental compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Implement Incremental this skillrsmdt/the-startup536—~1.7kAutomated safety check: PassMIT
Plannotator Planning Analysisbacknotprop/plannotator9.2k—~6.7kAutomated safety check: PassApache-2.0
Grill With UIjasonku09/grill-with-ui246—~7.9kAutomated safety check: PassMIT
Gstack Autoplan Review Pipelinegarrytan/gstack136k—~16kAutomated safety check: NotesMIT
Plan and Implement Workflowmp-web3/claude-starter-kit109—~913Automated safety check: NotesMIT
Plannotator Annotatebacknotprop/plannotator9.2k—~413Automated safety check: PassApache-2.0

Similar skills

  • Plannotator Planning Analysis

    backnotprop/plannotator

    Mines a Plannotator archive of denied plans for feedback patterns and prompt improvements, then writes an HTML dashboard report, with a Claude Code fallback.

    9.2k GitHub stars~6.7k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed
  • Grill With UI

    jasonku09/grill-with-ui

    Moves a design-grilling interview from the terminal to a local web page, where each question, recommendation and discussion thread can be handled in any order.

    246 GitHub stars~7.9k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed
  • Runs the gstack CEO, design, engineering and DX review skills on a plan file in sequence and makes borderline taste decisions automatically using six stated decision principles.

    136k GitHub stars~16k tokensUpdated today
    Agent WorkflowsAuto-check: notes
  • Plan and Implement Workflow

    mp-web3/claude-starter-kit

    Runs new features, scripts and structural changes through explore, design, approval, implementation and verification phases, with a tool search and an explicit plan sign-off.

    109 GitHub stars~913 tokensUpdated 6 mo ago
    Agent WorkflowsAuto-check: notes
  • Plannotator Annotate

    backnotprop/plannotator

    Opens Plannotator's annotation UI on a markdown file, HTML file, URL or folder, then reads the decision and feedback you send back and acts on it.

    9.2k GitHub stars~413 tokensUpdated yesterday
    Agent WorkflowsAuto-check passed
  • Subagent Driven Development

    aiskillstore/marketplace

    Sequential subagent execution with two-stage review gates for implementation plans.

    430 GitHub stars~1.3k tokensUpdated today
    Agent WorkflowsAuto-check passed

More from rsmdt/the-startup

All 27 skills in this repo
  • Analyze

    rsmdt/the-startup

    Deep-dive codebase analysis that explains how things actually work — business rules, architecture patterns, auth flows, data models, integrations, and performance hotspots.

    536 GitHub stars~1.9k tokensUpdated 2 mo ago
    Auto-check passed
  • Implement

    rsmdt/the-startup

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

    536 GitHub stars~1.3k tokensUpdated 2 mo ago
    Auto-check passed
  • Implement Factory

    rsmdt/the-startup

    Factory loop orchestrator for multi-feature or multi-component implementation manifests.

    536 GitHub stars~3.2k tokensUpdated 2 mo ago
    Auto-check passed
  • Agentic Patterns

    rsmdt/the-startup

    Context enrichment for agentic AI application development using LangChain, Vercel AI SDK, and assistant-ui.

    536 GitHub stars~501 tokensUpdated 2 mo ago
    Auto-check passed
  • API Contract Design

    rsmdt/the-startup

    REST and GraphQL API design patterns, OpenAPI/Swagger specifications, versioning strategies, and authentication patterns.

    536 GitHub stars~1.1k tokensUpdated 2 mo ago
    Auto-check passed
  • Architecture Selection

    rsmdt/the-startup

    System architecture patterns including monolith, microservices, event-driven, and serverless, with C4 modeling, scalability strategies, and technology selection criteria.

    536 GitHub stars~1.2k tokensUpdated 2 mo ago
    Auto-check passed

Categories

Questions about Implement Incremental

What does Implement Incremental do?

Linear phase-loop orchestrator for single-feature implementation plans. Implement Incremental is an agent skill from rsmdt/the-startup. Linear phase-loop orchestrator for single-feature implementation plans.

When should I use Implement Incremental?

Implement Incremental fits situations like: medium-complexity work where transparent human-in-the-loop phase review is preferred over factory automation; tasks that involve Human-in-the-loop approvals; tasks that involve Planning.

How do I install Implement Incremental in Claude Code?

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

How do I install Implement Incremental in Codex?

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

Can I use Implement Incremental 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-incremental -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-incremental, .gemini/skills/implement-incremental, .github/skills/implement-incremental and .opencode/skills/implement-incremental in your project.

What does Implement Incremental need to run?

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

Does Implement Incremental 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 Incremental 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 Incremental use?

Implement Incremental 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 Incremental use?

About 1.7k tokens (SKILL.md is roughly 6.9k 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 Incremental?

Skills that share tags, products or a category with Implement Incremental: Plannotator Planning Analysis (backnotprop/plannotator, 9.2k stars), Grill With UI (jasonku09/grill-with-ui, 246 stars), Gstack Autoplan Review Pipeline (garrytan/gstack, 136k stars) and Plan and Implement Workflow (mp-web3/claude-starter-kit, 109 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Implement Incremental?

rsmdt (a GitHub user) maintains it in rsmdt/the-startup, which has 536 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.