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.
Conventions for editing plan.json implementation plans including task format, structured arrays, and plan structure rules.
Install Plan Editing Conventions
$ npx skills add closedloop-ai/claude-plugins --skill plan-editing-conventions -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install closedloop-ai/claude-plugins plan-editing-conventions --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/closedloop-ai/claude-plugins.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/code/skills/plan-editing-conventions .claude/skills/plan-editing-conventions && 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 "plan-editing-conventions" agent skill from https://github.com/closedloop-ai/claude-plugins/tree/main/plugins/code/skills/plan-editing-conventions into .claude/skills/plan-editing-conventions/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "plan-editing-conventions", 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/closedloop-ai/claude-plugins/tree/main/plugins/code/skills/plan-editing-conventionsType 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 closedloop-ai/claude-plugins --skill plan-editing-conventions -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install closedloop-ai/claude-plugins plan-editing-conventions --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/closedloop-ai/claude-plugins.git skills-src && mkdir -p .agents/skills && cp -r skills-src/plugins/code/skills/plan-editing-conventions .agents/skills/plan-editing-conventions && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "plan-editing-conventions" agent skill from https://github.com/closedloop-ai/claude-plugins/tree/main/plugins/code/skills/plan-editing-conventions into .agents/skills/plan-editing-conventions/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "plan-editing-conventions", 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 closedloop-ai/claude-plugins --skill plan-editing-conventions -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install closedloop-ai/claude-plugins plan-editing-conventions --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/closedloop-ai/claude-plugins.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/plugins/code/skills/plan-editing-conventions .cursor/skills/plan-editing-conventions && 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 "plan-editing-conventions" agent skill from https://github.com/closedloop-ai/claude-plugins/tree/main/plugins/code/skills/plan-editing-conventions into .cursor/skills/plan-editing-conventions/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "plan-editing-conventions", 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/closedloop-ai/claude-plugins.git --path plugins/code/skills/plan-editing-conventions--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 closedloop-ai/claude-plugins --skill plan-editing-conventions -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install closedloop-ai/claude-plugins plan-editing-conventions --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/closedloop-ai/claude-plugins.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/plugins/code/skills/plan-editing-conventions .gemini/skills/plan-editing-conventions && 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 "plan-editing-conventions" agent skill from https://github.com/closedloop-ai/claude-plugins/tree/main/plugins/code/skills/plan-editing-conventions into .gemini/skills/plan-editing-conventions/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "plan-editing-conventions", 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 closedloop-ai/claude-plugins plan-editing-conventionsInstalls 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 closedloop-ai/claude-plugins --skill plan-editing-conventions -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/closedloop-ai/claude-plugins.git skills-src && mkdir -p .github/skills && cp -r skills-src/plugins/code/skills/plan-editing-conventions .github/skills/plan-editing-conventions && 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 "plan-editing-conventions" agent skill from https://github.com/closedloop-ai/claude-plugins/tree/main/plugins/code/skills/plan-editing-conventions into .github/skills/plan-editing-conventions/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "plan-editing-conventions", 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 closedloop-ai/claude-plugins --skill plan-editing-conventions -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install closedloop-ai/claude-plugins plan-editing-conventions --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/closedloop-ai/claude-plugins.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/plugins/code/skills/plan-editing-conventions .opencode/skills/plan-editing-conventions && 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 "plan-editing-conventions" agent skill from https://github.com/closedloop-ai/claude-plugins/tree/main/plugins/code/skills/plan-editing-conventions into .opencode/skills/plan-editing-conventions/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "plan-editing-conventions", 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
plan-editing-conventions- GitHub stars
- 122
- Token cost
- ~1.2k tokens
- SKILL.md length
- 363 words
- Files
- 1
- Skills in repo
- 41
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Conventions for editing plan.json implementation plans including task format, structured arrays, and plan structure rules.
- Works in 6 steps: Edit plan.json - Update the content… → Keep arrays in sync - If a task moves… → Preserve existing structure - Don't… → …
- Modifying plan.json files
- SKILL.md covers Plan Structure Rules, plan.json Format, Editing plan.json Content Field and Task Format, plus 2 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Plan Editing Conventions is an agent skill from closedloop-ai/claude-plugins. Conventions for editing plan.json implementation plans including task format, structured arrays, and plan structure rules. Use when creating or modifying plan.json files.
Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Agent Workflows, covering Planning. The repository describes itself as: Open-source Claude Code plugins for multi-agent software delivery. Plan-first SDLC workflow, code review, LLM quality judges, and self-learning — grounded in your codebase… The licence is Apache-2.0.
When your agent uses it
- Modifying plan.json files
- Tasks that involve Planning
Example prompts
- “Use the plan-editing-conventions skill to convention for editing plan.json implementation plans including task format, structured arrays, and plan…”
- “/plan-editing-conventions”
Requirements
- Python 3
Workflow steps
6 steps, taken from the first numbered list in SKILL.md.
- Edit plan.json - Update the content field and structured arrays as needed
- Keep arrays in sync - If a task moves from pending to completed, update both pendingTasks and completedTasks arrays
- Preserve existing structure - Don't reorganize unless necessary
- Update affected sections only - Minimize changes to unaffected tasks
- Keep complexity accurate - Reassess if scope changes significantly
- Sync plan.md - Always regenerate plan.md via code:extract-plan-md after edits
What it can do on your machine
Read from SKILL.md and the folder at commit 476b54c. 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 (its code samples are json, markdown and python).
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
Plan Editing Conventions loads about 1.2k tokens when it runs. Until then it costs about 49 tokens; SKILL.md has 363 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); files beside SKILL.md are not scanned.
SKILL.md
The full file from closedloop-ai/claude-plugins at commit 476b54c, republished under its Apache-2.0 licence (© closedloop-ai). 363 words, ~1,198 tokens.
Download SKILL.mdSave it as
.claude/skills/plan-editing-conventions/SKILL.md (or your agent's skills folder).- name
- plan-editing-conventions
- description
- Conventions for editing plan.json implementation plans including task format, structured arrays, and plan structure rules. Use when creating or modifying plan.json files.
Plan Editing Conventions
Conventions for creating and modifying implementation plans stored as plan.json.
Plan Structure Rules
- Keep prose concise and actionable; include concrete file paths (
relative/path.ts) - Never include time estimates. Use qualitative Complexity per task: S (≤ ~120 LOC), M (~120–300 LOC), L (> ~300 LOC)
- Do not hardcode colors or tokens; reference semantic tokens when citing UI work
plan.json Format
The plan is stored as plan.json with these key fields:
{
"content": "# Implementation Plan\n\n## Stage 1: ...\n\n### T-1.1: Task Title\n...",
"acceptanceCriteria": [...],
"pendingTasks": [...],
"completedTasks": [...],
"manualTasks": [...],
"openQuestions": [...],
"answeredQuestions": [...],
"gaps": [...],
"amendments": [...]
}content: The full markdown plan as a JSON string with escaped newlines (\n). This is the human-readable plan text.- Structured arrays: Mirror the plan content for programmatic access (pendingTasks, completedTasks, etc.)
Editing plan.json Content Field
CRITICAL: The content field is a JSON string. When editing:
- Use
\nescape sequences for newlines, NOT literal line breaks - Ensure proper JSON escaping of quotes and special characters
- After editing, always sync
plan.mdvia thecode:extract-plan-mdskill
Task Format
Tasks use the T-X.Y ID convention where X is the stage number and Y is the task number within that stage.
Each task in the plan content should follow this structure:
### T-X.Y: [Task Title]
**Files:** `path/to/file.ext`
**Complexity:** S | M | L
**AC Refs:** AC-001, AC-002
**Description:** Brief description of what this task accomplishes.
**Implementation Details:**
[Include one or more of the following as appropriate:]
**Mapping Table:** (for distribution/transformation tasks)
| Source | Target | Notes |
|--------|--------|-------|
| category_a | target_file_a.md | Section: XYZ |
| category_b | target_file_b.md | Section: ABC |
**Algorithm:** (for logic-heavy tasks)
1. Load input from `source_path`
2. Parse using `specific_method()`
3. For each item:
a. Transform using pattern X
b. Validate against schema Y
4. Write output to `target_path`
**Code Template:** (for new file creation)
```python
# Actual code structure to be created
from typing import TypedDict
class ConfigType(TypedDict):
field_a: str
field_b: int
def main_function(config: ConfigType) -> Result:
"""Docstring explaining purpose."""
passBefore/After Example: (for modification tasks)
# BEFORE (current code)
def old_approach():
pass
# AFTER (with changes)
def new_approach():
# Added: explanation of change
pass
## Structured Array Format
### pendingTasks / completedTasks
```json
{
"id": "T-1.1",
"description": "Task description",
"acceptanceCriteria": ["AC-001", "AC-002"]
}amendments
{
"timestamp": "2024-01-01T00:00:00",
"changes": ["Description of change 1", "Description of change 2"],
"conversation": [...]
}Show full SKILL.md (182 more words)Show less
Implementation Details Guidance
Extract implementation details for tasks that involve:
- Pattern extraction from existing code (algorithms, templates, mappings)
- Creating new files based on existing patterns
- Distributing/transforming content across multiple targets
- Complex logic that benefits from step-by-step documentation
Detail extraction checklist:
- Every task with Complexity M or L has implementation details
- Tasks referencing source files include extracted content
- Mapping/distribution tasks have explicit tables
- Algorithm tasks have step-by-step logic
- New file tasks have templates showing structure
- Code snippets use correct syntax highlighting
Skip detail extraction for:
- Simple file moves or renames (Complexity S, obvious path)
- Documentation-only tasks with no code
- Tasks that are pure analysis with no deliverable
Editing Existing Plans
When amending an existing plan:
- Edit plan.json - Update the
contentfield and structured arrays as needed - Keep arrays in sync - If a task moves from pending to completed, update both
pendingTasksandcompletedTasksarrays - Preserve existing structure - Don't reorganize unless necessary
- Update affected sections only - Minimize changes to unaffected tasks
- Keep complexity accurate - Reassess if scope changes significantly
- Sync plan.md - Always regenerate
plan.mdviacode:extract-plan-mdafter edits
© closedloop-ai, 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
Just SKILL.md in plugins/code/skills/plan-editing-conventions of closedloop-ai/claude-plugins.
Open the folder on GitHubat commit 476b54c
Compare with similar skills
Plan Editing Conventions 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 |
|---|---|---|---|---|---|---|
| Plan Editing Conventions this skillclosedloop-ai/claude-plugins | 122 | — | ~1.2k | 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 | 103k | 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 | 57 repos | ~661 | Automated safety check: Pass | None | |
| Subagent Driven DevelopmentAsvarox/allkaraoke | 261 | 38 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 closedloop-ai/claude-plugins
All 41 skills in this repoCodex Review
closedloop-ai/claude-plugins
Run Codex to review a plan file and return structured feedback with a verdict.
Critic Cache
closedloop-ai/claude-plugins
Check if critic reviews are still valid before re-running Phase 2.5 critics.
Cross Repo Cache
closedloop-ai/claude-plugins
Check if cross-repo coordinator results can be reused, avoiding redundant Sonnet agent launches.
Eval Cache
closedloop-ai/claude-plugins
Check for a cached plan-evaluation.json result before launching the plan-evaluator agent.
Find Plugin File
closedloop-ai/claude-plugins
This skill should be used when needing to locate files within the Claude Code plugins cache directory (~/.claude/plugins/cache).
Gh Monitor PR
closedloop-ai/claude-plugins
Start a detached GitHub pull-request monitor that wakes the exact launching Codex Desktop or CLI root through the managed Codex App Server when review, CI, conflict, merge-queue, closure, readiness…
Related
Categories
Questions about Plan Editing Conventions
What does Plan Editing Conventions do?
Conventions for editing plan.json implementation plans including task format, structured arrays, and plan structure rules. Plan Editing Conventions is an agent skill from closedloop-ai/claude-plugins.json implementation plans including task format, structured arrays, and plan structure rules.
When should I use Plan Editing Conventions?
Plan Editing Conventions fits situations like: modifying plan.json files; tasks that involve Planning.
How do I install Plan Editing Conventions in Claude Code?
Run `npx skills add closedloop-ai/claude-plugins --skill plan-editing-conventions -a claude-code`. Or copy the skill folder (plugins/code/skills/plan-editing-conventions in closedloop-ai/claude-plugins) into .claude/skills/plan-editing-conventions in your project. Claude Code loads it when a task matches its description.
How do I install Plan Editing Conventions in Codex?
Run `npx skills add closedloop-ai/claude-plugins --skill plan-editing-conventions -a codex`. Or copy the skill folder (plugins/code/skills/plan-editing-conventions in closedloop-ai/claude-plugins) into .agents/skills/plan-editing-conventions in your project. Codex loads it when a task matches its description.
Can I use Plan Editing Conventions 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 closedloop-ai/claude-plugins --skill plan-editing-conventions -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/plan-editing-conventions, .gemini/skills/plan-editing-conventions, .github/skills/plan-editing-conventions and .opencode/skills/plan-editing-conventions in your project.
What does Plan Editing Conventions need to run?
SKILL.md names no scripts, command-line tools or credentials: Plan Editing Conventions is instructions for the agent only. Our summary lists: Python 3.
Does Plan Editing Conventions 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 Plan Editing Conventions 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 Plan Editing Conventions use?
Plan Editing Conventions 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 Plan Editing Conventions use?
About 1.2k tokens (SKILL.md is roughly 4.8k 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 Plan Editing Conventions?
Skills that share tags, products or a category with Plan Editing Conventions: Executing Plans Inline (obra/superpowers, 296k stars), Interview Me (addyosmani/agent-skills, 103k 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 Plan Editing Conventions?
closedloop-ai (a GitHub organization) maintains it in closedloop-ai/claude-plugins, which has 122 GitHub stars. The repository holds 41 skills in this directory. The repository was last updated on October 7, 2026.
Source: closedloop-ai/claude-plugins on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.