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.
Turn a task description and repository into a structured implementation plan (files to create, files to modify, tests to add, risks).
Install Code Plan
$ npx skills add initializ/forge --skill code-plan -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install initializ/forge code-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/initializ/forge.git skills-src && mkdir -p .claude/skills && cp -r skills-src/forge-skills/local/embedded/code-plan .claude/skills/code-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 "code-plan" agent skill from https://github.com/initializ/forge/tree/main/forge-skills/local/embedded/code-plan into .claude/skills/code-plan/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "code-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/initializ/forge/tree/main/forge-skills/local/embedded/code-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 initializ/forge --skill code-plan -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install initializ/forge code-plan --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/initializ/forge.git skills-src && mkdir -p .agents/skills && cp -r skills-src/forge-skills/local/embedded/code-plan .agents/skills/code-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 "code-plan" agent skill from https://github.com/initializ/forge/tree/main/forge-skills/local/embedded/code-plan into .agents/skills/code-plan/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "code-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 initializ/forge --skill code-plan -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install initializ/forge code-plan --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/initializ/forge.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/forge-skills/local/embedded/code-plan .cursor/skills/code-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 "code-plan" agent skill from https://github.com/initializ/forge/tree/main/forge-skills/local/embedded/code-plan into .cursor/skills/code-plan/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "code-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/initializ/forge.git --path forge-skills/local/embedded/code-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 initializ/forge --skill code-plan -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install initializ/forge code-plan --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/initializ/forge.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/forge-skills/local/embedded/code-plan .gemini/skills/code-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 "code-plan" agent skill from https://github.com/initializ/forge/tree/main/forge-skills/local/embedded/code-plan into .gemini/skills/code-plan/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "code-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 initializ/forge code-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 initializ/forge --skill code-plan -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/initializ/forge.git skills-src && mkdir -p .github/skills && cp -r skills-src/forge-skills/local/embedded/code-plan .github/skills/code-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 "code-plan" agent skill from https://github.com/initializ/forge/tree/main/forge-skills/local/embedded/code-plan into .github/skills/code-plan/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "code-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 initializ/forge --skill code-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 initializ/forge code-plan --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/initializ/forge.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/forge-skills/local/embedded/code-plan .opencode/skills/code-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 "code-plan" agent skill from https://github.com/initializ/forge/tree/main/forge-skills/local/embedded/code-plan into .opencode/skills/code-plan/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "code-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
code-plan- GitHub stars
- 223
- Token cost
- ~1.9k tokens
- SKILL.md length
- 675 words
- Files
- 4 (incl. scripts)
- Skills in repo
- 15
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Turn a task description and repository into a structured implementation plan (files to create, files to modify, tests to add, risks).
- Works in 3 steps: The top entries of git ls-files (the… → The contents of detected manifest files:… → The first ~4 KB of README.md if present.
- Tasks that involve Planning
- SKILL.md covers When to use this skill, When NOT to use this skill, Plan-then-execute discipline and Workflow integration, plus 4 more sections
- Runs Shell scripts from its folder; calls git
What it does
Code Plan is an agent skill from initializ/forge. Turn a task description and repository into a structured implementation plan (files to create, files to modify, tests to add, risks).
Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including scripts (for example `scripts/code-plan-create.sh`, `scripts/code-plan-validate.sh` and `scripts/common.sh`).
It sits in Agent Workflows, covering Planning. The repository describes itself as: Forge is the open-source runtime for Anthropic's Agent Skills standard — built for the agent that runs next to a service, in your environment, on infrastructure you already… The licence is Apache-2.0.
When your agent uses it
- Tasks that involve Planning
Example prompts
- “/code-plan”
Requirements
- A Bash shell
- A credential in ANTHROPIC_API_KEY
- A credential in OPENAI_API_KEY
Workflow steps
3 steps, taken from the first numbered list in SKILL.md.
- The top entries of git ls-files (the repo tree).
- The contents of detected manifest files: package.json, go.mod, pyproject.toml, Cargo.toml, pom.xml, build.gradle*.
- The first ~4 KB of README.md if present.
What it can do on your machine
Read from SKILL.md and the folder at commit 3c608d8. 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 3 files in scripts/ (Shell), which the agent can run.
Shell commands in SKILL.md call:
git
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.
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
Code Plan loads about 1.9k tokens when it runs. Until then it costs about 36 tokens; SKILL.md has 675 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 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); the scripts in this folder are not scanned.
SKILL.md
The full file from initializ/forge at commit 3c608d8, republished under its Apache-2.0 licence (© initializ). 675 words, ~1,866 tokens.
Download SKILL.mdSave it as
.claude/skills/code-plan/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.- name
- code-plan
- description
- Turn a task description and repository into a structured implementation plan (files to create, files to modify, tests to add, risks).
- icon
- 🗺️
- category
- developer
- tags
- planning, code-generation, ticket-to-pr, llm-powered
Code Plan Skill
Generate a structured plan for implementing a task in a specific repository. The plan is the bridge between "I have a ticket" and "let me start writing code" — it lists files to create, files to modify, tests to add, and risks before any code is written.
This skill produces JSON. It does not write code; that is code_agent_*'s job.
When to use this skill
- The user provides a Linear ticket, GitHub issue, or free-form task description and asks you to implement it.
- Before any
code_agent_write,code_agent_edit, orgithub_committool call. - When the user explicitly asks for a plan.
When NOT to use this skill
- Tiny single-file edits (1–3 lines). Just edit directly.
- Pure exploration tasks. Use
grep_search/directory_treeinstead. - Pure scaffolding tasks (e.g. "create a new React app"). Use
code_agent_scaffoldinstead.
Plan-then-execute discipline
Once a plan is generated, present its summary and files_to_modify / files_to_create lists to the user before writing code. Do NOT proceed to implementation if the plan returns complexity: "high" or non-empty risks without acknowledging them to the user. The plan is a contract: subsequent code-writing tool calls should match files listed in the plan. If the plan turns out to be wrong, regenerate it rather than silently drifting from it.
Workflow integration
Canonical sequence for a ticket-to-PR flow:
linear_get_issue
→ code_plan_create [present summary + risks to user]
→ code_agent_write / code_agent_edit
→ code_plan_validate [optional sanity check before commit]
→ github_commit
→ github_create_prRepo signal extraction (informational)
code_plan_create automatically samples the repository so the LLM has enough context to plan without you pre-reading files. It collects:
- The top entries of
git ls-files(the repo tree). - The contents of detected manifest files:
package.json,go.mod,pyproject.toml,Cargo.toml,pom.xml,build.gradle*. - The first ~4 KB of
README.mdif present.
The total signal is size-bounded (default 256 KB, override via PLAN_MAX_REPO_SIGNAL_BYTES). If the repo is too large to fit, the tool returns status: "repo_too_large" rather than truncating silently — pass context_files to scope the plan to the relevant files, or call from a subdirectory.
Just pass repo_path. Do not pre-read the repo with grep_search before calling this tool.
Show full SKILL.md (349 more words)Show less
Tool: code_plan_create
Generate a structured implementation plan for a task in a repository. One LLM call, one plan.
Input:
| Parameter | Type | Required | Description |
|---|---|---|---|
| repo_path | string | yes | Absolute or ~-prefixed path to the repo. Required because scripts run in the agent's working directory, not the user's project. |
| task | string | yes | Task description — Linear ticket body verbatim, or a free-form ask. Markdown ok. |
| context_files | string[] | no | Repo-relative paths to include in full as additional context (e.g. ["src/auth/login.go"]). Capped at 5 files, 50 KB total. |
| target_branch | string | no | Branch name being worked on (informational, helps the LLM pick consistent naming). |
| ticket_id | string | no | Linear identifier or GitHub issue number. Echoed back in the output for traceability. |
Output — success:
{
"status": "ok",
"ticket_id": "ENG-123",
"stack_detected": "go",
"summary": "One-paragraph plain-English description of the planned change.",
"approach": "Higher-level reasoning: why this approach, what alternatives were considered.",
"files_to_create": [
{ "path": "src/billing/invoice.go", "purpose": "New domain type and constructor for Invoice." }
],
"files_to_modify": [
{ "path": "src/api/routes.go", "change": "Register /invoices route group, wire to handler." }
],
"tests_to_add": [
{ "path": "src/billing/invoice_test.go", "covers": "Construction, validation, JSON round-trip." }
],
"risks": [
{ "severity": "medium", "risk": "Existing customers will see a 422 on legacy payloads.", "mitigation": "Add a feature flag and default to the new behavior only for accounts created after launch date." }
],
"complexity": "medium",
"estimated_file_count": 3,
"open_questions": [
"Should invoice numbers be globally unique or per-customer?"
]
}complexity is one of low, medium, high. risks[].severity is one of low, medium, high.
Output — repo too large:
{
"status": "repo_too_large",
"tree_bytes": 524288,
"limit_bytes": 262144,
"suggestion": "Pass context_files explicitly to scope the plan, or run from a subdirectory."
}Output — no recognizable stack:
If no manifest (package.json, go.mod, etc.) is found, the plan is still attempted but stack_detected: "unknown" is set and an explicit risk is added noting that the stack could not be inferred.
Tool: code_plan_validate
Filesystem-only audit of a previously-generated plan against the current repo state. No LLM call. Cheap and idempotent — call it any time a plan was generated more than a few minutes ago, after pulling from remote, or before committing.
Input:
| Parameter | Type | Required | Description |
|---|---|---|---|
| repo_path | string | yes | Path to the repo. |
| plan | object | yes | A previously-generated plan object (or its files_to_create / files_to_modify subset). |
Output:
{
"status": "ok",
"files_to_modify_exist": [
{ "path": "src/api/routes.go", "exists": true }
],
"files_to_create_collisions": [
{ "path": "src/billing/invoice.go", "exists": false }
],
"warnings": [
"files_to_modify[2] (src/legacy/old.go) does not exist in the repo; the plan may be stale."
]
}A files_to_modify entry whose path does not exist becomes a warning. A files_to_create entry whose path already exists becomes a warning too — the plan would clobber existing code. Empty warnings means the plan still matches the repo.
Safety constraints
- This skill never writes to the filesystem (
writes_files: false). It returns JSON; downstream skills consume it. - Repo content is sent to the configured LLM provider; egress is restricted to
api.anthropic.comandapi.openai.com. - API keys are read from env vars, never logged.
guardrails.deny_outputredacts any key that leaks through an error payload. - Repo signal is size-bounded. Over budget →
repo_too_large, never silent truncation. - One LLM call per
code_plan_createinvocation (plus one retry if the response fails schema validation).
© initializ, 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 3 other files (scripts) in forge-skills/local/embedded/code-plan of initializ/forge.
- SKILL.md
- scripts/code-plan-create.sh
- scripts/code-plan-validate.sh
- scripts/common.sh
Open the folder on GitHubat commit 3c608d8
Compare with similar skills
Code 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 |
|---|---|---|---|---|---|---|
| Code Plan this skillinitializ/forge | 223 | — | ~1.9k | Automated safety check: Pass | Apache-2.0 | |
| Executing Plans Inlineobra/superpowers | 296k | 2 repos | ~5.1k | Automated safety check: Pass | MIT | |
| Interview Meaddyosmani/agent-skills | 102k | 6 repos | ~3.8k | Automated safety check: Pass | MIT | |
| OpenSpec Guided OnboardingFission-AI/OpenSpec | 71k | 1 repos | ~4.5k | Automated safety check: Pass | MIT | |
| Writing Plansgeeksblabla/stateofdev.ma | 163 | 56 repos | ~661 | Automated safety check: Pass | None | |
| Subagent Driven DevelopmentAsvarox/allkaraoke | 261 | 37 repos | ~1.2k | Automated safety check: Pass | None |
Similar skills
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.
OpenSpec Guided Onboarding
Fission-AI/OpenSpec
Walks you through a complete OpenSpec workflow cycle with narration while doing real work in your codebase.
Writing Plans
geeksblabla/stateofdev.ma
A skill your agent uses when design is complete and you need detailed implementation tasks for engineers with zero codebase context - creates comprehensive implementation plans with exact file…
Subagent Driven Development
Asvarox/allkaraoke
A skill your agent uses when executing implementation plans with independent tasks in the current session
Planning With Files
jd-opensource/JoySafeter
Implements Manus-style file-based planning for complex tasks.
More from initializ/forge
All 15 skills in this repoCode Review
initializ/forge
AI-powered code review for diffs and individual files using LLM analysis
Codegen HTML
initializ/forge
Scaffold and iterate on standalone Preact + HTM applications with zero build dependencies
Code Agent
initializ/forge
General-purpose coding agent that reads, writes, and edits code, and searches codebases.
Codegen React
initializ/forge
Scaffold and iterate on Vite + React applications. An agent skill from initializ/forge.
K8s Cost Visibility
initializ/forge
Estimate Kubernetes infrastructure costs by querying cluster node, pod, PVC/PV, and LoadBalancer data, applying cloud pricing models, and producing cost attribution reports with storage and…
K8s Pod Rightsizer
initializ/forge
Analyze Kubernetes workload metrics and produce policy-constrained CPU/memory rightsizing recommendations with optional patch generation and rollback-safe apply.
Related
Categories
Questions about Code Plan
What does Code Plan do?
Turn a task description and repository into a structured implementation plan (files to create, files to modify, tests to add, risks). Code Plan is an agent skill from initializ/forge. Turn a task description and repository into a structured implementation plan (files to create, files to modify, tests to add, risks).
When should I use Code Plan?
Code Plan fits situations like: tasks that involve Planning.
How do I install Code Plan in Claude Code?
Run `npx skills add initializ/forge --skill code-plan -a claude-code`. Or copy the skill folder (forge-skills/local/embedded/code-plan in initializ/forge) into .claude/skills/code-plan in your project. Claude Code loads it when a task matches its description.
How do I install Code Plan in Codex?
Run `npx skills add initializ/forge --skill code-plan -a codex`. Or copy the skill folder (forge-skills/local/embedded/code-plan in initializ/forge) into .agents/skills/code-plan in your project. Codex loads it when a task matches its description.
Can I use Code 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 initializ/forge --skill code-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/code-plan, .gemini/skills/code-plan, .github/skills/code-plan and .opencode/skills/code-plan in your project.
What does Code Plan need to run?
Going by SKILL.md and its folder, Code Plan needs a shell for the scripts in its folder and the command-line tools its instructions call (git). Our summary lists: A Bash shell; A credential in ANTHROPIC_API_KEY; A credential in OPENAI_API_KEY.
Does Code Plan access the network?
SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Code 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Code Plan use?
Code Plan 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 Code Plan use?
About 1.9k tokens (SKILL.md is roughly 7.5k 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 Code Plan?
Skills that share tags, products or a category with Code Plan: Executing Plans Inline (obra/superpowers, 296k stars), Interview Me (addyosmani/agent-skills, 102k stars), OpenSpec Guided Onboarding (Fission-AI/OpenSpec, 71k stars) and Writing Plans (geeksblabla/stateofdev.ma, 163 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Code Plan?
initializ (a GitHub organization) maintains it in initializ/forge, which has 223 GitHub stars. The repository holds 15 skills in this directory. The repository was last updated on October 1, 2026.
Source: initializ/forge on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.