PRP Loop
Wirasm/prp
Runs the plan, implement and review pipeline detached in fresh headless sessions, looping review and fix until the pull request is clean.
Runs one unattended implementation iteration of an autonomous loop: steward the in-flight PR, fix interrupts, or build one queued idea issue and open a PR.
Install Next Task Implementation Loop
$ npx skills add breaking-brake/cc-wf-studio --skill next-task -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install breaking-brake/cc-wf-studio next-task --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/breaking-brake/cc-wf-studio.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/next-task .claude/skills/next-task && 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 "next-task" agent skill from https://github.com/breaking-brake/cc-wf-studio/tree/main/.claude/skills/next-task into .claude/skills/next-task/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "next-task", 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/breaking-brake/cc-wf-studio/tree/main/.claude/skills/next-taskType 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 breaking-brake/cc-wf-studio --skill next-task -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install breaking-brake/cc-wf-studio next-task --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/breaking-brake/cc-wf-studio.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/next-task .agents/skills/next-task && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "next-task" agent skill from https://github.com/breaking-brake/cc-wf-studio/tree/main/.claude/skills/next-task into .agents/skills/next-task/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "next-task", 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 breaking-brake/cc-wf-studio --skill next-task -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install breaking-brake/cc-wf-studio next-task --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/breaking-brake/cc-wf-studio.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/next-task .cursor/skills/next-task && 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 "next-task" agent skill from https://github.com/breaking-brake/cc-wf-studio/tree/main/.claude/skills/next-task into .cursor/skills/next-task/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "next-task", 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/breaking-brake/cc-wf-studio.git --path .claude/skills/next-task--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 breaking-brake/cc-wf-studio --skill next-task -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install breaking-brake/cc-wf-studio next-task --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/breaking-brake/cc-wf-studio.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/next-task .gemini/skills/next-task && 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 "next-task" agent skill from https://github.com/breaking-brake/cc-wf-studio/tree/main/.claude/skills/next-task into .gemini/skills/next-task/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "next-task", 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 breaking-brake/cc-wf-studio next-taskInstalls 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 breaking-brake/cc-wf-studio --skill next-task -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/breaking-brake/cc-wf-studio.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/next-task .github/skills/next-task && 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 "next-task" agent skill from https://github.com/breaking-brake/cc-wf-studio/tree/main/.claude/skills/next-task into .github/skills/next-task/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "next-task", 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 breaking-brake/cc-wf-studio --skill next-task -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install breaking-brake/cc-wf-studio next-task --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/breaking-brake/cc-wf-studio.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/next-task .opencode/skills/next-task && 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 "next-task" agent skill from https://github.com/breaking-brake/cc-wf-studio/tree/main/.claude/skills/next-task into .opencode/skills/next-task/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "next-task", 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
next-task- GitHub stars
- 5.4k
- Token cost
- ~2.1k tokens
- SKILL.md length
- 1,204 words
- Files
- 1
- Skills in repo
- 11
- Repo updated
- First seen
- Licence
- Custom licence
At a glance
Runs one unattended implementation iteration of an autonomous loop: steward the in-flight PR, fix interrupts, or build one queued idea issue and open a PR.
- Works in 4 steps: Serialization guard — one in-flight task… → Interrupts — the ONLY maintenance this… → Pick ONE idea from the queue → …
- Letting the agent make autonomous progress on the queued idea backlog
- SKILL.md covers 0. Serialization guard — one…, 1. Interrupts — the ONLY…, 2. Pick ONE idea from the queue and 3. Build & Record, plus 1 more section
- Calls gh, git and pnpm
What it does
Each invocation is one iteration: guard, handle interrupts, pick one queued idea, then build and record it. A serialization guard allows a single in-flight task, so the agent first checks open PRs on `auto-dev` and stewards only one that is provably the loop's own, from a `claude/*` branch in the same repository by the owner's account, squash-merging on green CI and closing the linked issue. The skill implements and does not invent: ideas come from GitHub issues labeled `idea`, filled by the `next-idea` skill.
If the queue is empty and nothing is broken, doing nothing is the correct outcome, and housekeeping such as dependency bumps, comment cleanup or refactors with no visible effect does not count as work. The human steers through `IMPLEMENTATION_PLAN.md` and by closing idea issues. Issue and PR text from anyone but the repository owner is treated as a report to verify, never as instructions. In remote sessions without the `gh` CLI, GitHub MCP tools are used instead. Triggers include requests like next task or continue.
When your agent uses it
- Letting the agent make autonomous progress on the queued idea backlog
- A scheduled routine needs to run one implementation iteration
- Advancing or merging the loop's in-flight PR
Example prompts
- “Run the next task and pick the top queued idea.”
- “Continue where you left off: steward any open PR first, then build the next idea.”
- “Do one unattended iteration of the loop and open a PR if CI will go green.”
Requirements
- GitHub access through the `gh` CLI or GitHub MCP tools
- An `auto-dev` branch and issues labeled `idea`
- The `next-idea` skill to fill the idea queue
Workflow steps
4 steps, taken from the step headings in SKILL.md.
- Serialization guard — one in-flight task at a time
- Interrupts — the ONLY maintenance this loop does
- Pick ONE idea from the queue
- Build & Record
What it can do on your machine
Read from SKILL.md and the folder at commit a7bf24a. 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
Shell commands in SKILL.md call:
ghgitpnpm
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use gh, git and pnpm, 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
Next Task Implementation Loop loads about 2.1k tokens when it runs. Until then it costs about 116 tokens; SKILL.md has 1,204 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
Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 1,204 words (~2,118 tokens).
“One invocation = one iteration: guard → interrupts → pick ONE queued idea → build & record.”
- name
- next-task
Files
Just SKILL.md in .claude/skills/next-task of breaking-brake/cc-wf-studio.
Open the folder on GitHubat commit a7bf24a
Compare with similar skills
Next Task Implementation Loop 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 |
|---|---|---|---|---|---|---|
| Next Task Implementation Loop this skillbreaking-brake/cc-wf-studio | 5.4k | — | ~2.1k | Automated safety check: Pass | Custom licence | |
| PRP LoopWirasm/prp | 2.3k | — | ~894 | Automated safety check: Pass | MIT | |
| PR BabysitterEveryInc/compound-engineering-plugin | 25k | — | ~2k | Automated safety check: Pass | MIT | |
| CI Watch and Auto-Fix Loopmodu-ai/moai-adk | 1.2k | — | ~2.4k | Automated safety check: Notes | Apache-2.0 | |
| Context Mode Opsmksglu/context-mode | 26k | — | ~6k | Automated safety check: Pass | Custom licence | |
| PRP Loop: Autonomous PipelineWirasm/prp | 2.3k | — | ~863 | Automated safety check: Pass | MIT |
Similar skills
PR Babysitter
EveryInc/compound-engineering-plugin
Watches an open GitHub pull request over time, routing review comments and CI failures to other skills until the PR is ready to merge.
CI Watch and Auto-Fix Loop
modu-ai/moai-adk
Watches a pull request's CI checks after creation, separates required from auxiliary failures, applies limited safe fixes and escalates anything semantic to you.
Context Mode Ops
mksglu/context-mode
Runs maintenance for the context-mode project with parallel subagents: issue triage, PR review, releases, bug fixes, announcements and branch syncing.
PRP Loop: Autonomous Pipeline
Wirasm/prp
Runs a detached, resumable loop that plans, implements, opens a PR, reviews and fixes a feature across headless CLI sessions until the review is clean.
Open PR
ArcadeAI/arcade-mcp
Prepare arcade-mcp changes for review by verifying intended behavior, filling the repository PR template, and creating or updating the PR.
More from breaking-brake/cc-wf-studio
All 11 skills in this repoPR Review Analysis
breaking-brake/cc-wf-studio
Fetches review comments from a GitHub pull request, checks each one against the real code, rates it valid, invalid or partial, and can reply on GitHub.
CC Workflow Studio AI Editor
breaking-brake/cc-wf-studio
Creates and edits visual agent workflows in CC Workflow Studio through conversation, with the agent reading and writing the canvas over MCP.
Workflow Schema Tuning
breaking-brake/cc-wf-studio
Guides edits to cc-wf-studio's workflow schema so AI agents generate better workflows, treating schema text as prompt engineering rather than validation.
Changesets Pull Request to Main
breaking-brake/cc-wf-studio
Opens a pull request to main in a pnpm and Changesets monorepo, after working out which packages changed and making sure a changeset file exists.
PR Merge Branch Cleanup
breaking-brake/cc-wf-studio
Clean up merged feature branches after PR to main is merged. Use when the user says "ブランチ削除", "cleanup", "マージ後の片付け", or wants to delete a merged branch.
ccwf Workflow CLI
breaking-brake/cc-wf-studio
Teaches the agent to use the ccwf command line tool to validate, preview, render, export and run cc-wf-studio workflow JSON files without opening VS Code.
Related
Works with
Categories
Questions about Next Task Implementation Loop
What does Next Task Implementation Loop do?
Runs one unattended implementation iteration of an autonomous loop: steward the in-flight PR, fix interrupts, or build one queued idea issue and open a PR. Each invocation is one iteration: guard, handle interrupts, pick one queued idea, then build and record it. A serialization guard allows a single in-flight task, so the agent first checks open PRs on `auto-dev` and stewards only one that is provably the loop's own, from a `claude/*` branch in the same repository by the owner's account, squash-merging on green CI and closing the linked issue.
When should I use Next Task Implementation Loop?
Next Task Implementation Loop fits situations like: letting the agent make autonomous progress on the queued idea backlog; A scheduled routine needs to run one implementation iteration; advancing or merging the loop's in-flight PR.
How do I install Next Task Implementation Loop in Claude Code?
Run `npx skills add breaking-brake/cc-wf-studio --skill next-task -a claude-code`. Or copy the skill folder (.claude/skills/next-task in breaking-brake/cc-wf-studio) into .claude/skills/next-task in your project. Claude Code loads it when a task matches its description.
How do I install Next Task Implementation Loop in Codex?
Run `npx skills add breaking-brake/cc-wf-studio --skill next-task -a codex`. Or copy the skill folder (.claude/skills/next-task in breaking-brake/cc-wf-studio) into .agents/skills/next-task in your project. Codex loads it when a task matches its description.
Can I use Next Task Implementation Loop 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 breaking-brake/cc-wf-studio --skill next-task -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/next-task, .gemini/skills/next-task, .github/skills/next-task and .opencode/skills/next-task in your project.
What does Next Task Implementation Loop need to run?
Going by SKILL.md and its folder, Next Task Implementation Loop needs the command-line tools its instructions call (gh, git and pnpm). Our summary lists: GitHub access through the `gh` CLI or GitHub MCP tools; An `auto-dev` branch and issues labeled `idea`; The `next-idea` skill to fill the idea queue.
Does Next Task Implementation Loop access the network?
SKILL.md contains no URLs. Its commands use gh and git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Next Task Implementation Loop 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 Next Task Implementation Loop use?
Next Task Implementation Loop 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 Next Task Implementation Loop use?
About 2.1k tokens (SKILL.md is roughly 8.5k 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 Next Task Implementation Loop?
Skills that share tags, products or a category with Next Task Implementation Loop: PRP Loop (Wirasm/prp, 2.3k stars), PR Babysitter (EveryInc/compound-engineering-plugin, 25k stars), CI Watch and Auto-Fix Loop (modu-ai/moai-adk, 1.2k stars) and Context Mode Ops (mksglu/context-mode, 26k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Next Task Implementation Loop?
breaking-brake (a GitHub user) maintains it in breaking-brake/cc-wf-studio, which has 5,391 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on October 7, 2026.
Source: breaking-brake/cc-wf-studio on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.