Inline Plan Execution
jnMetaCode/superpowers-zh
Executes a written implementation plan task by task in the current session, with a progress ledger, test-first gates and one fresh-context review at the end.
Builds a two-phase implementation plan from a spec issue, analysis or concept, writing a detailed test plan first and the implementation outline second.
Install Test-First Implementation Plan
$ npx skills add gittower/git-flow-next --skill create-plan -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install gittower/git-flow-next create-plan --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/gittower/git-flow-next.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/create-plan .claude/skills/create-plan && rm -rf skills-srcUse ~/.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/
Install the "create-plan" agent skill from https://github.com/gittower/git-flow-next/tree/main/.claude/skills/create-plan into .claude/skills/create-plan/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "create-plan", 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 install https://github.com/gittower/git-flow-next/tree/main/.claude/skills/create-planType 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.
$ npx skills add gittower/git-flow-next --skill create-plan -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install gittower/git-flow-next create-plan --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/gittower/git-flow-next.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/create-plan .agents/skills/create-plan && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "create-plan" agent skill from https://github.com/gittower/git-flow-next/tree/main/.claude/skills/create-plan into .agents/skills/create-plan/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "create-plan", 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.
$ npx skills add gittower/git-flow-next --skill create-plan -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install gittower/git-flow-next create-plan --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/gittower/git-flow-next.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/create-plan .cursor/skills/create-plan && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "create-plan" agent skill from https://github.com/gittower/git-flow-next/tree/main/.claude/skills/create-plan into .cursor/skills/create-plan/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "create-plan", 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 https://github.com/gittower/git-flow-next.git --path .claude/skills/create-plan--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add gittower/git-flow-next --skill create-plan -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install gittower/git-flow-next create-plan --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/gittower/git-flow-next.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/create-plan .gemini/skills/create-plan && rm -rf skills-srcUse ~/.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/
Install the "create-plan" agent skill from https://github.com/gittower/git-flow-next/tree/main/.claude/skills/create-plan into .gemini/skills/create-plan/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "create-plan", 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.
$ gh skill install gittower/git-flow-next create-planInstalls 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).
$ npx skills add gittower/git-flow-next --skill create-plan -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/gittower/git-flow-next.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/create-plan .github/skills/create-plan && rm -rf skills-srcUse ~/.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/
Install the "create-plan" agent skill from https://github.com/gittower/git-flow-next/tree/main/.claude/skills/create-plan into .github/skills/create-plan/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "create-plan", 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.
$ npx skills add gittower/git-flow-next --skill create-plan -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install gittower/git-flow-next create-plan --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/gittower/git-flow-next.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/create-plan .opencode/skills/create-plan && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "create-plan" agent skill from https://github.com/gittower/git-flow-next/tree/main/.claude/skills/create-plan into .opencode/skills/create-plan/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "create-plan", 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
create-plan- GitHub stars
- 458
- Token cost
- ~1.3k tokens
- SKILL.md length
- 397 words
- Files
- 1
- Skills in repo
- 25
- Repo updated
- First seen
- Licence
- Custom licence
At a glance
Builds a two-phase implementation plan from a spec issue, analysis or concept, writing a detailed test plan first and the implementation outline second.
- Works in 6 steps: Detect Current Context → Find the Source of Truth → Read Project Guidelines → …
- Planning a feature or bug fix from a spec issue before writing any code
- SKILL.md covers Instructions and Plan Template
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
This skill produces a plan in the spirit of test-driven development: the test plan comes first and gets most of the effort, because that is where design questions and edge cases get settled, and the implementation outline follows to serve those tests. It begins by reading the current git branch to find the matching workflow folder under .ai, for example an issue folder for a numbered feature branch.
The source of truth is, in order of preference, a spec issue fetched from GitHub (one labeled spec or containing Test Scenarios or Expected Behavior sections), then analysis.md produced by /analyze-issue, or concept.md for features. If none exists, the agent asks you to run /analyze-issue or supply context. It also reads the project's testing, coding and commit guidelines, such as TESTING_GUIDELINES.md and COMMIT_GUIDELINES.md.
In the test plan phase it starts from the source's scenarios, hunts for missed ones such as error conditions, edge cases, interactions with config options and merge strategies, and conflicting state, and writes each as setup, action, expected outcome, test name and test file without weakening outcomes to match current behavior. The second phase derives specific tasks with file paths, ordered so tests can be written and fail first, and notes dependencies between them.
When your agent uses it
- Planning a feature or bug fix from a spec issue before writing any code
- Turning an issue analysis into concrete test scenarios and an ordered task list
- Checking a spec for missed edge cases and error conditions
- Preparing work that will be implemented test-first on a feature branch
Example prompts
- “Create an implementation plan for the spec issue linked to this branch, tests first.”
- “Turn analysis.md into a test plan and an ordered list of implementation tasks.”
- “Review the spec for this feature and add test scenarios for the error conditions it missed.”
- “Plan this feature from concept.md, listing test files and tasks with their file paths.”
Requirements
- A git branch following the project's feature naming, with a matching folder under .ai
- GitHub issue access through an MCP tool, for spec issues
- Pre-approved tools (allowed-tools): Read, Grep, Glob, Write, Bash, mcp__github__get_issue
Workflow steps
6 steps, taken from the first numbered list in SKILL.md.
- Detect Current Context
- Find the Source of Truth
- Read Project Guidelines
- Phase 1: Build the Test Plan
- Phase 2: Outline the Implementation
- Write the Plan
What it can do on your machine
Read from SKILL.md and the folder at commit 00d1b4b. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves these tools, so the agent can use them without asking each time:
ReadGrepGlobWriteBashmcp__github__get_issue
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).
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
Test-First Implementation Plan loads about 1.3k tokens when it runs. Until then it costs about 23 tokens; SKILL.md has 397 words of instructions outside code blocks.
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: notes
The automated check noted patterns worth knowing about, such as sudo or a known installer.
- NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
allowed-tools: Read, Grep, Glob, Write, Bash, mcp__github__get_issue
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
Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 397 words (~1,303 tokens).
“Generate a test-first implementation plan. The plan is built in two phases, in the spirit of TDD: the test plan comes first — detailed scenarios exercising code that does not yet exist or will change — and the implementation outline…”
- name
- create-plan
- allowed-tools
- Read, Grep, Glob, Write, Bash, mcp__github__get_issue
Files
Just SKILL.md in .claude/skills/create-plan of gittower/git-flow-next.
Open the folder on GitHubat commit 00d1b4b
Compare with similar skills
Test-First Implementation 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Test-First Implementation Plan this skillgittower/git-flow-next | 458 | — | ~1.3k | Automated safety check: Notes | Custom licence | |
| Inline Plan ExecutionjnMetaCode/superpowers-zh | 8.3k | — | ~2.5k | Automated safety check: Pass | MIT | |
| Setup Matt Pocock Skillsywwynm/EverythingDone | 144 | 9 repos | ~1.7k | Automated safety check: Pass | GPL-3.0 | |
| Blueprint Construction Planneraffaan-m/ECC | 274k | 5 repos | ~1.3k | Automated safety check: Pass | MIT | |
| Deliveradamayoung/TMDb | 178 | — | ~12k | Automated safety check: Pass | Apache-2.0 | |
| TiXL Ticket Processortixl3d/tixl | 5.1k | — | ~2.6k | Automated safety check: Pass | MIT |
Similar skills
Setup Matt Pocock Skills
ywwynm/EverythingDone
Sets up an Agent skills block in AGENTS.md/CLAUDE.md and docs/agents/ so the engineering skills know this repo's issue tracker (GitHub or local markdown), triage label vocabulary, and domain doc…
Blueprint Construction Planner
affaan-m/ECC
Turns a one-line objective into a multi-step plan file with PR-sized steps, context briefs, a dependency graph, parallel-step detection and an adversarial review.
Deliver
adamayoung/TMDb
Take a plan all the way to a ready-to-merge pull request — review the plan (scaled to risk), implement it test-first, code-review and fix, run the CI gate, open the PR, and watch it green.
TiXL Ticket Processor
tixl3d/tixl
Works through the In progress column of the TiXL road-map board unattended, turning simple tickets into git stashes and writing plans for the rest under .agentic/Plans.
Deep Plan
piercelamb/deep-plan
Creates detailed, sectionized, TDD-oriented implementation plans through research, stakeholder interviews, and multi-LLM review.
More from gittower/git-flow-next
All 25 skills in this repoGitHub Issue Analysis
gittower/git-flow-next
Analyzes a GitHub issue for the git-flow-next project and writes an analysis document under .ai/ that covers the affected code and proposes TODO comments.
PR Review Feedback Handler
gittower/git-flow-next
Fetches review comments on a pull request, judges each one, writes the evaluation to a plan file and implements accepted changes, waiting for approval before anything public.
Stale PR Review Check
gittower/git-flow-next
Scans open pull requests against the project's review response window and reports which ones need action, read-only unless you approve a reminder.
Local Code Review
gittower/git-flow-next
Reviews local commits, branch diffs or pull requests against project guidelines and writes the result to local files, never posting it to GitHub.
Commit with Project Guidelines
gittower/git-flow-next
Creates a commit that follows the project's COMMIT_GUIDELINES.md, choosing the type by what the change does and verifying the result.
Create Spec
gittower/git-flow-next
Create a Codex-gated spec issue from a triaged report, concept, or idea
Related
Categories
Questions about Test-First Implementation Plan
What does Test-First Implementation Plan do?
Builds a two-phase implementation plan from a spec issue, analysis or concept, writing a detailed test plan first and the implementation outline second. This skill produces a plan in the spirit of test-driven development: the test plan comes first and gets most of the effort, because that is where design questions and edge cases get settled, and the implementation outline follows to serve those tests.ai, for example an issue folder for a numbered feature branch.
When should I use Test-First Implementation Plan?
Test-First Implementation Plan fits situations like: planning a feature or bug fix from a spec issue before writing any code; turning an issue analysis into concrete test scenarios and an ordered task list; checking a spec for missed edge cases and error conditions; preparing work that will be implemented test-first on a feature branch.
How do I install Test-First Implementation Plan in Claude Code?
Run `npx skills add gittower/git-flow-next --skill create-plan -a claude-code`. Or copy the skill folder (.claude/skills/create-plan in gittower/git-flow-next) into .claude/skills/create-plan in your project. Claude Code loads it when a task matches its description.
How do I install Test-First Implementation Plan in Codex?
Run `npx skills add gittower/git-flow-next --skill create-plan -a codex`. Or copy the skill folder (.claude/skills/create-plan in gittower/git-flow-next) into .agents/skills/create-plan in your project. Codex loads it when a task matches its description.
Can I use Test-First Implementation 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 gittower/git-flow-next --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 Test-First Implementation Plan need to run?
SKILL.md names no scripts, command-line tools or credentials: Test-First Implementation Plan is instructions for the agent only. Our summary lists: A git branch following the project's feature naming, with a matching folder under .ai; GitHub issue access through an MCP tool, for spec issues. Its frontmatter pre-approves these tools: Read, Grep, Glob, Write, Bash, mcp__github__get_issue.
Does Test-First Implementation 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 Test-First Implementation Plan safe to install?
Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.
What licence does Test-First Implementation Plan use?
Test-First Implementation Plan has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.
How many tokens does Test-First Implementation Plan use?
About 1.3k tokens (SKILL.md is roughly 5.2k 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 Test-First Implementation Plan?
Skills that share tags, products or a category with Test-First Implementation Plan: Inline Plan Execution (jnMetaCode/superpowers-zh, 8.3k stars), Setup Matt Pocock Skills (ywwynm/EverythingDone, 144 stars), Blueprint Construction Planner (affaan-m/ECC, 274k stars) and Deliver (adamayoung/TMDb, 178 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Test-First Implementation Plan?
gittower (a GitHub organization) maintains it in gittower/git-flow-next, which has 458 GitHub stars. The repository holds 25 skills in this directory. The repository was last updated on September 8, 2026.
Source: gittower/git-flow-next on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.