Subagent Driven Development
Asvarox/allkaraoke
A skill your agent uses when executing implementation plans with independent tasks in the current session
Executes implementation plans directly with a verification gate and conditional code review.
Install Executing Plans
$ npx skills add rileyhilliard/claude-essentials --skill executing-plans -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install rileyhilliard/claude-essentials executing-plans --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/rileyhilliard/claude-essentials.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/ce/skills/executing-plans .claude/skills/executing-plans && 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 "executing-plans" agent skill from https://github.com/rileyhilliard/claude-essentials/tree/main/plugins/ce/skills/executing-plans into .claude/skills/executing-plans/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "executing-plans", 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/rileyhilliard/claude-essentials/tree/main/plugins/ce/skills/executing-plansType 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 rileyhilliard/claude-essentials --skill executing-plans -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install rileyhilliard/claude-essentials executing-plans --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/rileyhilliard/claude-essentials.git skills-src && mkdir -p .agents/skills && cp -r skills-src/plugins/ce/skills/executing-plans .agents/skills/executing-plans && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "executing-plans" agent skill from https://github.com/rileyhilliard/claude-essentials/tree/main/plugins/ce/skills/executing-plans into .agents/skills/executing-plans/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "executing-plans", 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 rileyhilliard/claude-essentials --skill executing-plans -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install rileyhilliard/claude-essentials executing-plans --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/rileyhilliard/claude-essentials.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/plugins/ce/skills/executing-plans .cursor/skills/executing-plans && 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 "executing-plans" agent skill from https://github.com/rileyhilliard/claude-essentials/tree/main/plugins/ce/skills/executing-plans into .cursor/skills/executing-plans/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "executing-plans", 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/rileyhilliard/claude-essentials.git --path plugins/ce/skills/executing-plans--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 rileyhilliard/claude-essentials --skill executing-plans -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install rileyhilliard/claude-essentials executing-plans --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/rileyhilliard/claude-essentials.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/plugins/ce/skills/executing-plans .gemini/skills/executing-plans && 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 "executing-plans" agent skill from https://github.com/rileyhilliard/claude-essentials/tree/main/plugins/ce/skills/executing-plans into .gemini/skills/executing-plans/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "executing-plans", 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 rileyhilliard/claude-essentials executing-plansInstalls 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 rileyhilliard/claude-essentials --skill executing-plans -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/rileyhilliard/claude-essentials.git skills-src && mkdir -p .github/skills && cp -r skills-src/plugins/ce/skills/executing-plans .github/skills/executing-plans && 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 "executing-plans" agent skill from https://github.com/rileyhilliard/claude-essentials/tree/main/plugins/ce/skills/executing-plans into .github/skills/executing-plans/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "executing-plans", 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 rileyhilliard/claude-essentials --skill executing-plans -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install rileyhilliard/claude-essentials executing-plans --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/rileyhilliard/claude-essentials.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/plugins/ce/skills/executing-plans .opencode/skills/executing-plans && 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 "executing-plans" agent skill from https://github.com/rileyhilliard/claude-essentials/tree/main/plugins/ce/skills/executing-plans into .opencode/skills/executing-plans/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "executing-plans", 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
executing-plans- GitHub stars
- 130
- Token cost
- ~1.2k tokens
- SKILL.md length
- 616 words
- Files
- 1
- Skills in repo
- 17
- Repo updated
- First seen
- Licence
- MIT
At a glance
Executes implementation plans directly with a verification gate and conditional code review.
- Works in 4 steps: Setup → Execute → Verify → …
- Carrying out a written plan step by step
- SKILL.md covers 1. Setup, 2. Execute, 3. Verify and 4. Complete
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Executing Plans is an agent skill from rileyhilliard/claude-essentials. Executes implementation plans directly with a verification gate and conditional code review. Use when carrying out a written plan step by step; delegates to subagents only for large, genuinely independent, parallelizable work.
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 and Subagents. The licence is MIT.
When your agent uses it
- Carrying out a written plan step by step
- Delegates to subagents only for large
- Genuinely independent
- Parallelizable work
Example prompts
- “Use the executing-plans skill to execute implementation plans directly with a verification gate and conditional code review”
- “/executing-plans”
Workflow steps
4 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 3a67a01. 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
Executing Plans loads about 1.2k tokens when it runs. Until then it costs about 61 tokens; SKILL.md has 616 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 rileyhilliard/claude-essentials at commit 3a67a01, republished under its MIT licence (© rileyhilliard). 616 words, ~1,158 tokens.
Download SKILL.mdSave it as
.claude/skills/executing-plans/SKILL.md (or your agent's skills folder).- name
- executing-plans
- description
- Executes implementation plans directly with a verification gate and conditional code review. Use when carrying out a written plan step by step; delegates to subagents only for large, genuinely independent, parallelizable work.
Executing Plans
Default to implementing directly. Delegation is the exception, not the default. Delegate to a subagent only for large tasks that are genuinely independent and parallelizable, such as a wide multi-file investigation. Do not delegate work you can finish yourself in a handful of tool calls, and do not use subagents to verify or double-check your own work. If one subagent can complete the task, use one rather than several, and keep spawn counts low.
1. Setup
Create a worktree using EnterWorktree before starting any work. This isolates changes from the main branch and makes cleanup safe. Skip only for trivial single-file changes that don't warrant isolation.
Clarify ambiguity upfront. If the plan has unclear requirements or meaningful tradeoffs, ask before starting. Don't guess when the user can clarify in 10 seconds.
Track progress with tasks. Create tasks for each major work item from the plan. Set up dependency chains between tasks using addBlocks/addBlockedBy so blocked tasks don't start prematurely. Update task status as work progresses. This keeps execution visible to the user and persists across context compactions.
2. Execute
Work through the plan's tasks directly, in order, updating task status as you go.
If delegation is warranted (large, independent, parallelizable work identified in step 1), group related tasks by subsystem rather than spawning per-task, since each agent re-investigates the codebase.
| Signal | Group together |
|---|---|
| Same directory prefix | src/auth/* tasks |
| Same domain/feature | Auth tasks, billing tasks |
| Plan sections | Tasks under same ## heading |
Keep concurrent agents to a small handful. Claude Code hard-fails above 20 concurrent subagents, but that's not a target, stay well under it.
Parallel vs sequential: Groups that touch different subsystems run in parallel. Groups with dependencies run sequentially (e.g., create shared types before using them). When parallel agents may touch overlapping files, use isolation: "worktree" on the Agent call.
Recovery: Fix failures inline yourself. If the same error recurs after a second attempt, stop and ask the user rather than keep retrying.
Show full SKILL.md (291 more words)Show less
3. Verify
Verification is a gate, not a checklist. Nothing proceeds to merge until all checks pass.
Automated tests. Run the full test suite. All tests must pass.
Manual verification. Automated tests aren't sufficient. Actually exercise the changes:
- API changes: Curl endpoints with realistic payloads
- External integrations: Test against real services to catch rate limiting, format drift, bot detection
- CLI changes: Run actual commands, verify output
- UI changes: Start the dev server and use the feature in a browser
- Parser changes: Feed real data, not just fixtures
Watch for DX friction during manual testing: confusing error messages, noisy output, inconsistent behavior, rough edges that technically work but feel bad. Fix inline or document for follow-up. Don't ship friction.
Code review (conditional). For large or risky diffs, dispatch the ce:code-reviewer agent to review the full diff against the base branch after tests pass and manual verification is done. Skip it for small or simple changes.
Load relevant domain skills into the reviewer based on what was implemented. Evaluate which apply and include them in the agent prompt:
Skill(architecting-systems)- system design, module boundariesSkill(managing-databases)- database workSkill(handling-errors)- error handlingSkill(writing-tests)- test qualitySkill(optimizing-performance)- performance work
Handle the review verdict:
- Must fix: Fix all Critical and Important issues
- Suggestions: Fix these too unless there's a clear reason not to
4. Complete
Once verification passes:
- Commit the work with a message summarizing what was implemented
- Merge to main from the worktree branch
- Exit worktree using
ExitWorktreewithaction: "remove"to clean up - Mark plan as COMPLETED and move to
./plans/done/if applicable
Match the length of written documents (commit messages, failure reports) to what the task needs: cover the substance, but do not pad with filler sections, redundant summaries, or boilerplate.
© rileyhilliard, MIT. 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/ce/skills/executing-plans of rileyhilliard/claude-essentials.
Open the folder on GitHubat commit 3a67a01
Compare with similar skills
Executing Plans 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 |
|---|---|---|---|---|---|---|
| Executing Plans this skillrileyhilliard/claude-essentials | 130 | — | ~1.2k | Automated safety check: Pass | MIT | |
| Subagent Driven DevelopmentAsvarox/allkaraoke | 261 | 37 repos | ~1.2k | Automated safety check: Pass | None | |
| Executing PlansGanyuanRan/Aegis | 1.3k | 1 repos | ~2.3k | Automated safety check: Pass | MIT | |
| Execumputun/cc-thingz | 483 | — | ~8k | Automated safety check: Pass | MIT | |
| Autopilot End-to-End Buildernick-vels/skills | 403 | — | ~2.5k | Automated safety check: Notes | MIT | |
| Workflow Orchestrationvxcozy/workflow-orchestration | 115 | — | ~1k | Automated safety check: Pass | MIT |
Similar skills
Executing Plans
GanyuanRan/Aegis
A skill your agent uses when executing a written implementation plan across sessions or with review checkpoints.
Exec
umputun/cc-thingz
Execute plan tasks sequentially using subagents. An agent skill from umputun/cc-thingz.
Autopilot End-to-End Builder
nick-vels/skills
Builds an app, site, bot or feature from a spoken idea through requirements, spec, tickets, subagent work, review and acceptance, with a live progress dashboard.
Workflow Orchestration
vxcozy/workflow-orchestration
Disciplined task execution with planning, verification, and self-improvement loops.
Blueprint
byungjunjang/jangpm-meta-skills
Agentic system design blueprint generator. An agent skill from byungjunjang/jangpm-meta-skills.
More from rileyhilliard/claude-essentials
All 17 skills in this repoHandling Errors
rileyhilliard/claude-essentials
Prevents silent failures and context loss in error handling.
Planning Products
rileyhilliard/claude-essentials
Defines product features from a PM perspective (JTBD, competitive research, scope negotiation) before technical planning.
Writing Tests
rileyhilliard/claude-essentials
Writes behavior-focused tests using Testing Trophy model with real dependencies.
Optimizing Performance
rileyhilliard/claude-essentials
Measure-first performance optimization that balances gains against complexity.
Architecting Systems
rileyhilliard/claude-essentials
Guides clean, scalable system architecture during the build phase.
Design
rileyhilliard/claude-essentials
Enforces precise, minimal design for dashboards and admin interfaces.
Related
Categories
Questions about Executing Plans
What does Executing Plans do?
Executes implementation plans directly with a verification gate and conditional code review. Executing Plans is an agent skill from rileyhilliard/claude-essentials. Executes implementation plans directly with a verification gate and conditional code review.
When should I use Executing Plans?
Executing Plans fits situations like: carrying out a written plan step by step; delegates to subagents only for large; genuinely independent; parallelizable work.
How do I install Executing Plans in Claude Code?
Run `npx skills add rileyhilliard/claude-essentials --skill executing-plans -a claude-code`. Or copy the skill folder (plugins/ce/skills/executing-plans in rileyhilliard/claude-essentials) into .claude/skills/executing-plans in your project. Claude Code loads it when a task matches its description.
How do I install Executing Plans in Codex?
Run `npx skills add rileyhilliard/claude-essentials --skill executing-plans -a codex`. Or copy the skill folder (plugins/ce/skills/executing-plans in rileyhilliard/claude-essentials) into .agents/skills/executing-plans in your project. Codex loads it when a task matches its description.
Can I use Executing Plans 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 rileyhilliard/claude-essentials --skill executing-plans -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/executing-plans, .gemini/skills/executing-plans, .github/skills/executing-plans and .opencode/skills/executing-plans in your project.
What does Executing Plans need to run?
SKILL.md names no scripts, command-line tools or credentials: Executing Plans is instructions for the agent only.
Does Executing Plans 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 Executing Plans 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 Executing Plans use?
Executing Plans 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 Executing Plans use?
About 1.2k tokens (SKILL.md is roughly 4.6k 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 Executing Plans?
Skills that share tags, products or a category with Executing Plans: Subagent Driven Development (Asvarox/allkaraoke, 261 stars), Executing Plans (GanyuanRan/Aegis, 1.3k stars), Exec (umputun/cc-thingz, 483 stars) and Autopilot End-to-End Builder (nick-vels/skills, 403 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Executing Plans?
rileyhilliard (a GitHub user) maintains it in rileyhilliard/claude-essentials, which has 130 GitHub stars. The repository holds 17 skills in this directory. The repository was last updated on August 18, 2026.
Source: rileyhilliard/claude-essentials on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.