Agent skill

Implementation Plan Creator

by tailcallhq in tailcallhq/forgecode

Writes a structured Markdown implementation plan with checkbox tasks, verification criteria and risks, then checks it with a validation script; no code changes.

Apache-2.0Auto-check passedAgent Workflows

Install Implementation Plan Creator

skills CLI
$ npx skills add tailcallhq/forgecode --skill create-plan -a claude-code

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

GitHub CLI
$ gh skill install tailcallhq/forgecode create-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/tailcallhq/forgecode.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.forge/skills/create-plan .claude/skills/create-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
create-plan
GitHub stars
7.6k
Used in
1 other repo
Token cost
~1.1k tokens
SKILL.md length
359 words
Files
6 (incl. references)
Skills in repo
14
Repo updated
First seen
Licence
Apache-2.0

At a glance

Writes a structured Markdown implementation plan with checkbox tasks, verification criteria and risks, then checks it with a validation script; no code changes.

  • Works in 4 steps: Initial Assessment → Create Strategic Plan → Validate Plan → …
  • Being asked for a plan, roadmap or implementation strategy before coding starts
  • SKILL.md covers When to Use, Planning Process, Critical Requirements and Best Practices, plus 1 more section
  • Runs Shell scripts from its folder

What it does

The agent first researches the codebase: its structure, the relevant files read in full, existing conventions, risks and data flows, citing sources as `filepath:line`. It then writes a plan into the `plans/` directory, named by date, task and version, for example `plans/2025-11-24-add-auth-v1.md`.

Every plan must pass `validate-plan.sh`, which the agent re-runs until errors and warnings are gone; a second script, `validate-all-plans.sh`, is also included. Implementation tasks have to use checkbox format rather than numbered lists or plain bullets, each with what, why, affected files and integration points, and the plan carries an objective, verification criteria, risks and alternative approaches. The skill is strictly about planning: no code, snippets or examples go into the plan, and nothing in the repository changes beyond the plan file. A plan template and an example plan sit in `references/`.

When your agent uses it

  • Being asked for a plan, roadmap or implementation strategy before coding starts
  • Breaking a complex feature into trackable checkbox tasks
  • Assessing risks and alternative approaches before an architectural change

Example prompts

  • “Create a plan for adding OAuth login to the API, with no code changes yet.”
  • “Write an implementation roadmap for migrating our job queue, including risks and alternatives.”
  • “Plan the refactor of the billing module and validate the plan file.”

Requirements

  • Bash to run the bundled validation script

Workflow steps

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

  1. Initial Assessment
  2. Create Strategic Plan
  3. Validate Plan
  4. Plan Structure

What it can do on your machine

Read from SKILL.md and the folder at commit 92a5699. 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

Implementation Plan Creator loads about 1.1k tokens when it runs, and up to ~3.6k if it reads all its reference files. Until then it costs about 149 tokens; SKILL.md has 359 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~149
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~3.6k

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 tailcallhq/forgecode at commit 92a5699, republished under its Apache-2.0 licence (© tailcallhq). 359 words, ~1,095 tokens.

Download SKILL.mdSave it as .claude/skills/create-plan/SKILL.md (or your agent's skills folder). This skill also uses 5 other files; get the full folder from GitHub.
name
create-plan
description
Generate detailed implementation plans for complex tasks. Creates comprehensive strategic plans in Markdown format with objectives, step-by-step implementation tasks using checkbox format, verification criteria, risk assessments, and alternative approaches. All plans MUST be validated using the included validation script. Use when users need thorough analysis and structured planning before implementation, when breaking down complex features into actionable steps, or when they explicitly ask for a plan, roadmap, or strategy. Strictly planning-focused with no code modifications.

Create Implementation Plan

Generate comprehensive implementation plans that provide strategic guidance without making actual code changes.

When to Use

  • User explicitly requests a plan, roadmap, or implementation strategy
  • Complex tasks requiring structured breakdown before implementation
  • Need for risk assessment and alternative approach analysis
  • Pre-implementation analysis of architectural decisions

Planning Process

1. Initial Assessment

Research the codebase to understand:

  • Project structure and organization
  • Relevant files and components - read thoroughly to understand complete flows
  • Existing patterns and conventions
  • Potential challenges and risks
  • Data flows from entry points to final usage

Use search, sem_search, and read tools to examine the codebase. Use sage if deeper research is required for the use-case. Explicitly cite sources using filepath:line format in your plan.

2. Create Strategic Plan

Generate a Markdown plan file in plans/ directory with naming: plans/{YYYY-MM-DD}-{task-name}-v{N}.md

Example: plans/2025-11-24-add-auth-v1.md

3. Validate Plan

MANDATORY: Run the validation script to ensure the plan meets all requirements:

bash
./.forge/skills/create-plan/validate-plan.sh plans/{YYYY-MM-DD}-{task-name}-v{N}.md

Fix any errors or warnings and re-validate until the plan passes all checks.

4. Plan Structure
markdown
# [Task Name]

## Objective

[Clear statement of goal and expected outcomes]

## Implementation Plan

- [ ] 1. [First task with detailed description and rationale]
- [ ] 2. [Second task with detailed description and rationale]
- [ ] 3. [Third task with detailed description and rationale]

## Verification Criteria

- [Criterion 1: Specific, measurable outcome]
- [Criterion 2: Specific, measurable outcome]

## Potential Risks and Mitigations

1. **[Risk Description]**
   Mitigation: [Specific mitigation strategy]

2. **[Risk Description]**
   Mitigation: [Specific mitigation strategy]

## Alternative Approaches

1. [Alternative 1]: [Brief description and trade-offs]
2. [Alternative 2]: [Brief description and trade-offs]

Critical Requirements

  • ALWAYS validate the plan using ./.forge/skills/create-plan/validate-plan.sh after creation
  • ALWAYS use checkbox format (- [ ]) for ALL implementation tasks
  • NEVER use numbered lists or plain bullet points in Implementation Plan section
  • NEVER write code, code snippets, or code examples in the plan
  • Write comprehensive tasks including what, why, affected files, and integration points
  • Use filepath:line format for file references (e.g., crates/forge_repo/src/provider.rs:45)
  • Include clear rationale for each task
  • Provide specific, measurable verification criteria
  • Document assumptions made for ambiguous requirements
  • Focus on strategic "what" and "why", not tactical "how"
  • Describe what needs to be done using natural language, not code
Show full SKILL.md (97 more words)Show less

Best Practices

  • Make reasonable assumptions when requirements are ambiguous
  • Use codebase patterns to infer best practices
  • Provide multiple solution paths for complex challenges
  • Balance thoroughness with actionability
  • Create plans that can be executed step-by-step by implementation agents

Boundaries

This is a planning-only skill:

  • ✅ Research codebase and analyze structure
  • ✅ Create strategic plans and documentation
  • ✅ Assess risks and propose alternatives
  • ✅ Describe implementations using natural language
  • ❌ Make actual code changes
  • ❌ Modify files or create implementations
  • ❌ Run tests or build commands
  • ❌ Write code, code snippets, or code examples in plans

If user requests implementation work, suggest switching to an implementation agent.

© tailcallhq, 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 5 other files (references) in .forge/skills/create-plan of tailcallhq/forgecode.

  • SKILL.md
  • README.md
  • references/example-plan.md
  • references/plan-template.md
  • validate-all-plans.sh
  • validate-plan.sh

Open the folder on GitHubat commit 92a5699

Used in 1 other repository

We found 8 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in tailcallhq/forgecode, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Implementation Plan Creator 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.

Implementation Plan Creator compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Implementation Plan Creator this skilltailcallhq/forgecode7.6k1 repos~1.1kAutomated safety check: PassApache-2.0
Implementation Plan Writerimbue-ai/bouncer400—~2.1kAutomated safety check: PassAGPL-3.0
Auditable Playbook Designercursor/plugins10k8 repos~1kAutomated safety check: PassNone
Vibe Workflow RouterKhazP/vibe-coding-prompt-template3.1k—~544Automated safety check: NotesMIT
Launch Delivery PipelineYeachan-Heo/oh-my-claudecode40k—~7.3kAutomated safety check: PassMIT
Planning And Task Breakdownabashev/vfs-s31068 repos~1.9kAutomated safety check: PassApache-2.0

Similar skills

  • Turns a feature's goals, requirements and architecture documents into a set of self-contained task files that a developer with no project context can follow.

    400 GitHub stars~2.1k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Official

    Designs a step-by-step playbook for large or unfamiliar work, runs it as a loop of hypotheses and measurements, and logs decisions so a human can review them later.

    10k GitHub starsUsed in 8 repos~1k tokens
    Agent WorkflowsAuto-check passed
  • Vibe Workflow Router

    KhazP/vibe-coding-prompt-template

    Picks the next useful step for an app project, whether planning a new product, changing an existing app, fixing a bug or writing a handoff, loading only the context needed.

    3.1k GitHub stars~544 tokensUpdated 2 days ago
    Agent WorkflowsAuto-check: notes
  • Launch Delivery Pipeline

    Yeachan-Heo/oh-my-claudecode

    Delivery pipeline from mission brief to verified change: writes a spec, splits it into tickets, runs them in parallel, verifies and reports a decision log after a repo audit gate.

    40k GitHub stars~7.3k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Breaks work into ordered tasks. An agent skill from abashev/vfs-s3.

    106 GitHub starsUsed in 8 repos~1.9k tokens
    Agent WorkflowsAuto-check passed
  • ULW Plan Workflow

    code-yeongyu/oh-my-openagent

    Explore-first planning that turns a vague or large request into one decision-complete work plan, written only after your approval and executed by a separate worker.

    70k GitHub stars~3.9k tokensUpdated today
    Agent WorkflowsAuto-check passed

More from tailcallhq/forgecode

All 14 skills in this repo
  • Git Merge Conflict Resolver

    tailcallhq/forgecode

    Resolves Git merge conflicts with a plan-first workflow that keeps both sides' intent, regenerates lock files and backs up deleted-but-modified files.

    7.6k GitHub starsUsed in 1 repo~4.5k tokens
    Auto-check passed
  • Forge CLI Debug Workflow

    tailcallhq/forgecode

    Gives a systematic process for debugging the forge CLI: build in debug mode, check the latest help output, test with the non-interactive -p flag, and clone conversations before reproducing bugs.

    7.6k GitHub starsUsed in 1 repo~1.6k tokens
    Auto-check passed
  • FIXME Resolver

    tailcallhq/forgecode

    Finds every FIXME comment in a codebase, groups related ones across files into one task, implements the work they describe and removes the comments once it is done.

    7.6k GitHub stars~1.1k tokensUpdated today
    Auto-check passed
  • Reasoning Serialization Tests

    tailcallhq/forgecode

    Checks that ReasoningConfig fields are serialized into the right provider-specific JSON for OpenRouter, Anthropic, GitHub Copilot and Codex requests.

    7.6k GitHub stars~1k tokensUpdated today
    Auto-check passed
  • Release Notes Writer

    tailcallhq/forgecode

    Pulls a GitHub release and every linked pull request, then writes polished, factual release notes from the combined set of changes.

    7.6k GitHub stars~1.4k tokensUpdated today
    Auto-check passed
  • Skill Creation Guide

    tailcallhq/forgecode

    Guidance for creating and updating agent skills: what skills provide, keeping context lean, choosing how specific to be, and how SKILL.md and bundled resources are laid out.

    7.6k GitHub starsUsed in 1 repo~4.6k tokens
    Auto-check passed

Questions about Implementation Plan Creator

What does Implementation Plan Creator do?

Writes a structured Markdown implementation plan with checkbox tasks, verification criteria and risks, then checks it with a validation script; no code changes. The agent first researches the codebase: its structure, the relevant files read in full, existing conventions, risks and data flows, citing sources as `filepath:line`.md`.

When should I use Implementation Plan Creator?

Implementation Plan Creator fits situations like: being asked for a plan, roadmap or implementation strategy before coding starts; breaking a complex feature into trackable checkbox tasks; assessing risks and alternative approaches before an architectural change.

How do I install Implementation Plan Creator in Claude Code?

Run `npx skills add tailcallhq/forgecode --skill create-plan -a claude-code`. Or copy the skill folder (.forge/skills/create-plan in tailcallhq/forgecode) into .claude/skills/create-plan in your project. Claude Code loads it when a task matches its description.

How do I install Implementation Plan Creator in Codex?

Run `npx skills add tailcallhq/forgecode --skill create-plan -a codex`. Or copy the skill folder (.forge/skills/create-plan in tailcallhq/forgecode) into .agents/skills/create-plan in your project. Codex loads it when a task matches its description.

Can I use Implementation Plan Creator 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 tailcallhq/forgecode --skill create-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/create-plan, .gemini/skills/create-plan, .github/skills/create-plan and .opencode/skills/create-plan in your project.

What does Implementation Plan Creator need to run?

Going by SKILL.md and its folder, Implementation Plan Creator needs a shell for the scripts in its folder. Our summary lists: Bash to run the bundled validation script.

Does Implementation Plan Creator 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 Implementation Plan Creator 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 Implementation Plan Creator use?

Implementation Plan Creator 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 Implementation Plan Creator use?

About 1.1k tokens (SKILL.md is roughly 4.4k 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 2.5k tokens, read only when the agent opens those files.

What are the alternatives to Implementation Plan Creator?

Skills that share tags, products or a category with Implementation Plan Creator: Implementation Plan Writer (imbue-ai/bouncer, 400 stars), Auditable Playbook Designer (cursor/plugins, 10k stars), Vibe Workflow Router (KhazP/vibe-coding-prompt-template, 3.1k stars) and Launch Delivery Pipeline (Yeachan-Heo/oh-my-claudecode, 40k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Implementation Plan Creator?

tailcallhq (a GitHub organization) maintains it in tailcallhq/forgecode, which has 7,642 GitHub stars. The repository holds 14 skills in this directory. The repository was last updated on October 7, 2026.

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