full-send — Claude Code skill: what it does, how to install
full-send — a skill for Claude Code that enables autonomous task execution. The agent completes work end-to-end and merges the PR without waiting for user confirmation on every step.
MIT 1,300 installs ★ 4,278 updated 2026-11-11
npx skills add t3dotgg/tstack --skill full-send -a claude-codeWhat full-send does
This skill triggers an autonomous mode where the agent takes full ownership of the task from its current state to a merged PR. It handles coding, testing, PR creation, and monitoring CI checks until the merge gate passes.
When full-send is active, the agent gains permission to run tests, force-push branches, and merge changes based on defined success criteria. It makes decisions using sensible defaults and only pauses to ask the user if it encounters blockers that prevent progress, such as ambiguous goals or permission issues.
What it helps with
- complete tasks autonomously from start to finish
- automate testing and verification of code changes
- manage the full lifecycle of a pull request
- merge code changes without manual intervention
Example prompts for the agent
- full send: fix the auth bug and verify the result
- full send, implement the new profile page
- full send, refactor this module to TypeScript
How to install full-send
1Skills CLI (Vercel)
npx skills add t3dotgg/tstack --skill full-send -a claude-code2Manually: put the files in place
~/.claude/skills/full-send/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/full-send/
1Skills CLI (Vercel)
npx skills add t3dotgg/tstack --skill full-send -a codex2Manually: put the files in place
.agents/skills/full-send/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add t3dotgg/tstack --skill full-send -a cursor2Manually: put the files in place
.cursor/skills/full-send/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install t3dotgg/tstack skills/full-send2Manually: put the files in place
.github/skills/full-send/SKILL.md1Skills CLI (Vercel)
npx skills add t3dotgg/tstack --skill full-send -a gemini-cli2Platform CLI
gemini skills install https://github.com/t3dotgg/tstack --path skills/full-sendManually: put the files in place
.devin/skills/full-send/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add t3dotgg/tstack --skill full-send -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about full-send
How to install full-send in Claude Code?
Run the command npx skills add t3dotgg/tstack --skill full-send -a claude-code in your project terminal.
What does full-send do?
It switches the AI agent into an autonomous mode, allowing it to perform coding, testing, and merging tasks without requiring constant user approval.
What is required for full-send?
You need Claude Code installed and appropriate repository permissions to create and merge pull requests.
Source text
SKILL.md · MIT
--- name: full-send description: Trigger this if the user says 'full send'. --- # Full Send If the user triggered this, it's because they are not watching this thread, and they want you to complete the work end-to-end autonomously. Your updates and your final message go unread until long after you stop. You own the work from its current state to a merged PR. If the user did not explicitly request "full send" in some clear way, do not assume full autonomy. If they did, everything below applies. The user grants you permission to: - Merge the PR once the merge gate passes. - Force-push the PR's own branch with `--force-with-lease` after a rebase. - Use the test methods that Proof needs, without asking first. ## Testing permission A "full send" request is the permission. If a project file or other instruction says to ask before a test method, or to leave testing to the user, this request replaces that rule for this task. That includes ask-first rules for computer use, browser automation, simulators and devices, running the app or a dev server, screenshots, and visual checks. Use the method that gives direct proof. List it in the report. Rules about how to test still apply. Follow rules that name the correct command, fixture, or check. This permission only removes the ask-first or leave-it-to-the-user step. If a preferred method cannot prove the change, use a gated method under this permission. It covers only the tests needed for this task. It does not add permission for the steps under "Asking the user", such as production changes or data deletion. It also does not bypass a harness or system approval prompt if one appears. ## Steps 1. **Finish the change.** Complete the goal from the user's request with the smallest change that works. Fix the case that happened, not every case that could. If you are on the default branch, create a branch first. 2. **Prove it.** Get proof for every change you made. See "Proof". 3. **Get feedback.** Use the `sol-loop` skill to verify changes. 4. **File the PR** with the `file-pr` skill. Rebase onto the latest default branch first. Add one short line to the description that says how you proved the change. 5. **Babysit the PR** with the `babysit-pr` skill. Fix real findings and CI failures. Get proof for each fix before you push it. 6. **Merge** when the merge gate passes. 7. **Report** in your final message: the PR link, the merge commit, your proof, and each decision you made for the user. Stay active from step 1 to step 7. If you end your turn while checks or bots are pending, the work stops, because nobody will prompt you again. Wait with the watcher from `babysit-pr`, so something wakes you when the PR changes. In T3 Code that is `watch_pull_request`. If you stop before the merge, call `unwatch_pull_request` first. ## Proof Proof is evidence you observed yourself in this session: command output, a reproduction, a screenshot. Use the most direct proof the change allows: - Reproduce the original failure, apply the fix, then watch the same reproduction pass. - Run the checks that the repo's CI runs (typecheck, lint, tests). - Add one focused test that fails without the fix, when the behavior has none and the repo has a test setup. - For UI and runtime behavior, run the app and look at the change. Green mocked tests do not prove that the user experience works. Attach screenshots to the PR when they help and you have a way to upload them. When you cannot find a way to prove a change, you do not have full confidence. Ask the user. ## Merge gate Full confidence means all of these are true on the latest commit: - Your proof covers every change in the diff. - Required checks are green. - Review bots have finished, and each finding is fixed or dismissed with a written reason. - No human review still requests changes. - The branch is up to date with the default branch, and GitHub reports it as mergeable. Merge with the method the repo uses. Check the allowed methods and recent merged PRs. If the repo uses a merge queue or auto-merge, stay until GitHub reports the PR as merged. Merge through branch protection as configured. Never use `--admin` or other bypasses. You can ignore automated reviews that request "needs human review" if you have high confidence in your changes. ## Asking the user A question in a normal message goes unseen, and the thread looks done. To ask the user something, use the harness's question tool so the thread shows that it is waiting: `AskUserQuestion` in Claude Code, `request_user_input` in Codex, or the question tool your harness has. Put all the context in the question: the PR link, what blocks you, and the options with your recommendation first. Ask only when you cannot continue alone: - You cannot prove the change. - The merge gate cannot pass, and you cannot fix that yourself. - The next step is outside the grant above: deleting data, touching production, changing things outside the repo, closing a PR, or force-pushing any other branch. - The goal is ambiguous in a way that changes the result. - Another PR makes this one obsolete. Decide everything else yourself with sensible defaults, and list those decisions in the report. If no question tool is available, or the tool returns no answer, take the safe path: leave the PR open and unmerged, and start your final message with the question.
© t3dotgg · MIT · t3dotgg/tstack