Finishing a Development Branch
obra/superpowers
Walks the last step of a branch: confirm tests pass, detect the git environment, ask how to integrate, carry out your choice and clean up the worktree.
A skill your agent uses when the user asks to run or continue an autonomous build: turn a goal into an approved plan, dispatch implementation and review agents, and finish with one pull request.
Install Lead
$ npx skills add tamdogood/builder-essential-skills --skill lead -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install tamdogood/builder-essential-skills lead --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/tamdogood/builder-essential-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/lead .claude/skills/lead && 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 "lead" agent skill from https://github.com/tamdogood/builder-essential-skills/tree/main/skills/lead into .claude/skills/lead/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "lead", 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/tamdogood/builder-essential-skills/tree/main/skills/leadType 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 tamdogood/builder-essential-skills --skill lead -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install tamdogood/builder-essential-skills lead --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/tamdogood/builder-essential-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/lead .agents/skills/lead && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "lead" agent skill from https://github.com/tamdogood/builder-essential-skills/tree/main/skills/lead into .agents/skills/lead/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "lead", 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 tamdogood/builder-essential-skills --skill lead -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install tamdogood/builder-essential-skills lead --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/tamdogood/builder-essential-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/lead .cursor/skills/lead && 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 "lead" agent skill from https://github.com/tamdogood/builder-essential-skills/tree/main/skills/lead into .cursor/skills/lead/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "lead", 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/tamdogood/builder-essential-skills.git --path skills/lead--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 tamdogood/builder-essential-skills --skill lead -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install tamdogood/builder-essential-skills lead --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/tamdogood/builder-essential-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/lead .gemini/skills/lead && 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 "lead" agent skill from https://github.com/tamdogood/builder-essential-skills/tree/main/skills/lead into .gemini/skills/lead/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "lead", 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 tamdogood/builder-essential-skills leadInstalls 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 tamdogood/builder-essential-skills --skill lead -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/tamdogood/builder-essential-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/lead .github/skills/lead && 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 "lead" agent skill from https://github.com/tamdogood/builder-essential-skills/tree/main/skills/lead into .github/skills/lead/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "lead", 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 tamdogood/builder-essential-skills --skill lead -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install tamdogood/builder-essential-skills lead --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/tamdogood/builder-essential-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/lead .opencode/skills/lead && 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 "lead" agent skill from https://github.com/tamdogood/builder-essential-skills/tree/main/skills/lead into .opencode/skills/lead/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "lead", 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
lead- GitHub stars
- 218
- Token cost
- ~2.4k tokens
- SKILL.md length
- 1,346 words
- Files
- 5
- Skills in repo
- 18
- Repo updated
- First seen
- Licence
- MIT
At a glance
A skill your agent uses when the user asks to run or continue an autonomous build: turn a goal into an approved plan, dispatch implementation and review agents, and finish with one pull request.
- Works in 5 steps: Ground and preflight → Intake and approval → Decompose and freeze → …
- The user asks to run
- SKILL.md covers Zero-direct-execution contract, Provider-neutral dispatch, Roles and Invariants, plus 3 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Lead is an agent skill from tamdogood/builder-essential-skills. Use when the user asks to run or continue an autonomous build: turn a goal into an approved plan, dispatch implementation and review agents, and finish with one pull request. The Lead is a provider-neutral orchestrator that makes decisions but never writes code, edits files, runs commands, or reviews its own work.
Its SKILL.md is about 2.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files (for example `README.md`, `dispatch.md` and `loop.md`).
It sits in Development, covering Pull requests. The repository describes itself as: A repository for skills that are essential to my daily work. The licence is MIT.
When your agent uses it
- The user asks to run
- Continue an autonomous build: turn a goal into an approved plan
- Dispatch implementation and review agents
- Finish with one pull request
Example prompts
- “/lead”
Workflow steps
5 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 1be9984. 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
Lead loads about 2.4k tokens when it runs. Until then it costs about 80 tokens; SKILL.md has 1,346 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 tamdogood/builder-essential-skills at commit 1be9984, republished under its MIT licence (© tamdogood). 1,346 words, ~2,431 tokens.
Download SKILL.mdSave it as
.claude/skills/lead/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.- name
- lead
- description
- Use when the user asks to run or continue an autonomous build: turn a goal into an approved plan, dispatch implementation and review agents, and finish with one pull request. The Lead is a provider-neutral orchestrator that makes decisions but never writes code, edits files, runs commands, or reviews its own work.
- metadata.effort
- high
Lead
You are the Lead. You own the goal, user communication, trade-offs, task boundaries, and final decisions. Agents do every executable action.
Zero-direct-execution contract
The Lead may only:
- ask the user material questions and report decisions;
- spawn, message, wait for, or stop agents with the runtime's native delegation tools;
- read compact agent handoffs and choose APPROVE, REVISE, CONTINUE, or STOP.
The Lead must never:
- write or edit code, tests, specs, checks, reports, documentation, or config;
- run shell, git, GitHub, browser, search, test, build, or deployment commands;
- commit, merge, push, open a pull request, or post tracker updates;
- inspect a large diff or turn a failed review into a pass;
- take over a task because an agent is unavailable or blocked.
Delegate each forbidden action to an agent with an explicit role, ownership boundary, and evidence contract. If the runtime cannot spawn agents, stop and tell the user that this skill requires native subagent delegation. Never fall back to doing the work yourself.
Provider-neutral dispatch
Use the current runtime's native agent tools. Do not invoke another provider's CLI, require a provider-specific model name, or ask the user to rewrite config when moving between runtimes.
At the start of a run, spawn one canary agent. It must report its available
tools, inspect one harmless repository fact, and return CANARY: READY or
CANARY: DEGRADED <missing capability>. Its handoff is the capability record:
- maximum useful concurrency;
- background execution and completion notifications;
- agent messaging, cancellation, and nested delegation;
- workspace or worktree isolation;
- shell, file-write, network, and web-search access.
Use only capabilities the canary proves. If the runtime exposes model or effort selection, choose by relative role need: strongest available independent agent for planning, criticism, and review; economical agents for scouting and mechanical work. If it exposes no selector, inherit the runtime default. Exact provider and model identifiers never belong in the workflow.
Keep one slot for the Lead. Fill the remaining slots with ready independent jobs; never assume a fixed concurrency limit. Prefer runtime-managed isolated worktrees. If the runtime shares a checkout, dispatch an Integrator to create one explicit worktree per job at the freeze commit and pass its root to every agent for that job. If agents cannot reliably stay inside an assigned worktree, serialize all writers and reviewers.
Roles
Use fresh agents for distinct trust boundaries:
| Role | Owns | Must not do |
|---|---|---|
| Grounder | Read repo, tracker, instructions, stops, and current state; return a compact evidence map | Edit or decide scope |
| Planner | Draft the spec and vertical slices from the approved goal | Implement or approve its own plan |
| Check author | Write falsifiable acceptance checks before builders start | Build against those checks |
| Critic | Attack the plan, paths, assumptions, and checks | Repair what it finds |
| Builder | Implement one bounded slice and leave raw check evidence | Commit, merge, or grade itself |
| Reviewer | Re-run frozen checks and review intent from a fresh context | Edit or fix the slice |
| Integrator | Create worktrees and perform tracker, git, branch, commit, merge, push, and PR operations authorized by the Lead | Change implementation to make integration pass |
| Docs writer | Update docs and reusable notes after implementation settles | Reinterpret product behavior |
| Researcher | Gather one narrow evidence set using research.md | Recommend or implement |
| Operator | Reconcile status and inspect process/worktree evidence | Judge anomalies |
Agents may delegate bounded independent subtasks when the runtime supports it, but the parent remains responsible for its role contract. Nobody grades their own work.
Exact job envelopes, portable role prompts, isolation rules, and blocker
recovery live in dispatch.md. The event loop lives in loop.md. Slice-scale
fact finding lives in research.md.
Invariants
- The Lead writes zero implementation. Prompts and user-facing decisions are orchestration; every repository or external-system mutation belongs to an agent.
- Not in the tracker means it did not happen. A tracker/integrator agent mirrors job state and evidence at event boundaries.
- Checks freeze before any builder exists. A check-author writes them and
an integrator commits the freeze. Builders treat
docs/checks/as read-only. - Nobody grades their own work. A fresh reviewer reruns checks and reads the diff for intent. A reviewer FAIL cannot be overruled into a merge.
- Fresh builder per attempt. A blocker or failed attempt gets a new agent with the durable answer and surviving worktree evidence.
- Builders never commit. An integrator commits only after an independent PASS and clean touch-set evidence.
- No silent fallback. Missing capabilities, absent tools, sandbox limits, and blockers are explicit evidence. The Lead never becomes the fallback.
- Parallel writers are isolated. Each job uses runtime isolation or an Integrator-created worktree and still owns disjoint files, migrations, lockfiles, schemas, generated artifacts, databases, and dev servers.
- The user's checkout is read-only to the factory. An Integrator prepares a clean run workspace before the first artifact writer; every writing agent receives that root or a child job worktree.
Procedure
Show full SKILL.md (548 more words)Show less
0. Ground and preflight
Spawn the canary and a Grounder. The Grounder reads authority docs, architecture,
active specs, notes, open issues and comments, job reports, frozen checks,
branches, and worktrees; reconciles tracker state with git; checks docs/STOP
and docs/PAUSE; and verifies the GitHub remote and authenticated tracker tools.
The Lead performs none of those probes directly.
Done when the Lead has a compact evidence map, runtime capability record, active stops, and explicit preflight failures.
1. Intake and approval
Ask at most five questions whose answers would materially change the build or
validation. Have an Integrator prepare a clean planning workspace, then send its
root, the answers, and Grounder map to a Planner. The Planner drafts
docs/spec/<project>.md there with goal, non-goals, assumptions, validation
strategy, domain terms, and open decisions. A tracker agent creates the tracking
issue and records the spec pointer.
Only explicit in-session authorization or an exact tracker APPROVE comment
authorizes implementation. Send the authorization verbatim to an Integrator,
which records it and creates the run branch. Rejection stops the run.
2. Decompose and freeze
Spawn a Planner for vertical slices and a Check author for each slice. Each slice has acceptance criteria, may-touch and must-not-touch sets, check and report paths, interface contracts, and dependency edges. Separate structural work from behavioral work. Concurrent slices must have disjoint mutable state.
Spawn one fresh Critic over the full plan. On findings, send the evidence to a new Planner or Check author; the Lead chooses which proposal to accept but edits nothing. After a clean critic verdict, an Integrator commits and pushes the frozen checks and, when needed, creates one worktree per job. Verify through the Integrator's evidence that every builder starts from that freeze in its assigned workspace root.
3. Factory loop
Follow loop.md:
- ask an Operator for the ready set, then spawn as many independent Builders as proven concurrency allows;
- wait for completion notifications instead of polling;
- send every completed slice to a fresh Reviewer immediately;
- on PASS, dispatch an Integrator to commit, merge, rerun checks, update the tracker, and close the slice;
- on FAIL, dispatch a diagnostic Planner or Researcher from the review evidence, then respawn a fresh Builder at the same role strength;
- on BLOCKED, record the Lead's ruling through a tracker agent and pass it to a fresh Builder;
- on conflict, discard the integration attempt and re-plan the slice; the Lead never resolves code conflicts.
For status questions, spawn an Operator to reconcile the tracker, reports, git, and live agent state into an evidence-backed tree. Do not hand-compose status.
4. Finish
Spawn one Docs writer, then an independent Reviewer for its changes. After PASS, send an Integrator the exact PR and digest contract: one PR, tracking-issue closure, shipped issue numbers, skipped work, residual risks, and verification evidence. The Lead presents the final digest after the Integrator proves the PR state.
Hard stops
Stop and ask the user when docs/STOP exists, docs/PAUSE forbids new work, an
irreversible action is required, two consecutive attempts are killed, a blocker
contradicts an approved assumption, scope exceeds the approved spec, tracker
preflight fails, or the runtime cannot preserve the zero-direct-execution
contract.
Maintenance
Keep role prompts provider-neutral and delete instructions that the current agent runtimes perform reliably without prompting. Preserve the trust boundaries: the Lead decides, agents execute, and fresh reviewers judge.
© tamdogood, MIT. 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 4 other files in skills/lead of tamdogood/builder-essential-skills.
- SKILL.md
- README.md
- dispatch.md
- loop.md
- research.md
Open the folder on GitHubat commit 1be9984
Compare with similar skills
Lead 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 |
|---|---|---|---|---|---|---|
| Lead this skilltamdogood/builder-essential-skills | 218 | — | ~2.4k | Automated safety check: Pass | MIT | |
| Finishing a Development Branchobra/superpowers | 296k | 5 repos | ~1.9k | Automated safety check: Pass | MIT | |
| PR Babysitteropeninterpreter/openinterpreter | 69k | 3 repos | ~4.2k | Automated safety check: Pass | Apache-2.0 | |
| Check PRonyx-dot-app/onyx | 32k | 2 repos | ~2.3k | Automated safety check: Pass | MIT | |
| Understand Diff AnalysisEgonex-AI/Understand-Anything | 85k | 1 repos | ~1.4k | Automated safety check: Pass | MIT | |
| PR Design DocOpenHands/OpenHands | 90k | — | ~2.4k | Automated safety check: Pass | MIT |
Similar skills
PR Babysitter
openinterpreter/openinterpreter
Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.
Check PR
onyx-dot-app/onyx
Checks a GitHub, GitLab, or Perforce (p4) pull request (or merge request, or shelved changelist) for unresolved review comments, failing status checks, and incomplete PR descriptions.
Understand Diff Analysis
Egonex-AI/Understand-Anything
Reads your git changes or a pull request against a prebuilt knowledge graph of the project to explain what changed, which components are affected and what is risky.
PR Design Doc
OpenHands/OpenHands
For a non-trivial pull request, write a self-contained HTML design doc under the temporary .pr/ directory and link a visibility-appropriate preview in the PR description, so maintainers grasp the…
WooCommerce Code Review
woocommerce/woocommerce
Reviews WooCommerce code changes against the project's standards, flagging backend PHP architecture, naming, documentation, data integrity and testing violations.
More from tamdogood/builder-essential-skills
All 18 skills in this repoCreate Marketing Kit
tamdogood/builder-essential-skills
Create truthful, human-centered marketing campaigns for an app or product, including positioning, channel copy, original artwork, editable layouts, README banners, and selective website integration.
Name Your Business
tamdogood/builder-essential-skills
Generate, refine, compare, and when needed validate distinctive names for startups, AI products, developer tools, protocols, open-source projects, apps, product families, local businesses, services…
Session Profiler
tamdogood/builder-essential-skills
Profile and debug Hermes sessions from their JSONL transcripts.
Build Scenario Tests
tamdogood/builder-essential-skills
Inspect an unfamiliar repository, turn a focused Markdown behavior scenario into a deterministic test in the repository's native test stack, run it, and preserve traceability between intent and code.
Create Skill
tamdogood/builder-essential-skills
Create or update a complete repository skill from a user's idea, including the workflow instructions, references, scripts or assets, agent metadata, skill-card artwork, cinematic banner artwork…
Paper Opportunity Radar
tamdogood/builder-essential-skills
Run a cumulative daily or retrospective sweep of research papers on a chosen topic, audit their claims, methods, integrity signals, and independent support, then identify overlooked but feasible…
Related
Categories
Questions about Lead
What does Lead do?
A skill your agent uses when the user asks to run or continue an autonomous build: turn a goal into an approved plan, dispatch implementation and review agents, and finish with one pull request. Lead is an agent skill from tamdogood/builder-essential-skills. Use when the user asks to run or continue an autonomous build: turn a goal into an approved plan, dispatch implementation and review agents, and finish with one pull request.
When should I use Lead?
Lead fits situations like: the user asks to run; continue an autonomous build: turn a goal into an approved plan; dispatch implementation and review agents; finish with one pull request.
How do I install Lead in Claude Code?
Run `npx skills add tamdogood/builder-essential-skills --skill lead -a claude-code`. Or copy the skill folder (skills/lead in tamdogood/builder-essential-skills) into .claude/skills/lead in your project. Claude Code loads it when a task matches its description.
How do I install Lead in Codex?
Run `npx skills add tamdogood/builder-essential-skills --skill lead -a codex`. Or copy the skill folder (skills/lead in tamdogood/builder-essential-skills) into .agents/skills/lead in your project. Codex loads it when a task matches its description.
Can I use Lead 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 tamdogood/builder-essential-skills --skill lead -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/lead, .gemini/skills/lead, .github/skills/lead and .opencode/skills/lead in your project.
What does Lead need to run?
SKILL.md names no scripts, command-line tools or credentials: Lead is instructions for the agent only.
Does Lead 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 Lead 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 Lead use?
Lead 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 Lead use?
About 2.4k tokens (SKILL.md is roughly 9.7k 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 Lead?
Skills that share tags, products or a category with Lead: Finishing a Development Branch (obra/superpowers, 296k stars), PR Babysitter (openinterpreter/openinterpreter, 69k stars), Check PR (onyx-dot-app/onyx, 32k stars) and Understand Diff Analysis (Egonex-AI/Understand-Anything, 85k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Lead?
tamdogood (a GitHub user) maintains it in tamdogood/builder-essential-skills, which has 218 GitHub stars. The repository holds 18 skills in this directory. The repository was last updated on August 16, 2026.
Source: tamdogood/builder-essential-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.