full-send
Skill1 starsChanged 3 days agoMITView on GitHub
Use when the user invokes `$full-send` to finish work end-to-end and merge.
- Commits and pushes
20 other projects use a version of this, 11 of them edited.
Adopted by
Most recently taken up by
- cogine-ai/cogine-dev-skillsetedited, first seen Nov 16, 2026
- mjeffrey18/skillstheir own version, first seen Nov 15, 2026
- lihbr/skillsedited, first seen Nov 15, 2026
- jameswyse/skillstheir own version, first seen Nov 15, 2026
- adelrodriguez/skillstheir own version, first seen Nov 15, 2026
- syanga/astacktheir own version, first seen Nov 8, 2026
Used with
Projects with it also use leaving-pr-comments, sol-loop and 7 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
scottwaterSkillleaving-pr-comments
Format comments an agent posts on GitHub on the user's behalf. Use whenever leaving a PR comment, review comment, or reply.
Also in 8 projects that use this
scottwaterSkillsol-loop
Review a change with GPT Sol in a loop until both agents agree. Use when the user says sol loop, or when another skill asks for a Sol review.
Also in 8 projects that use this
assisjpSkillfile-pr
Prepare and open or update an authorized pull request with a concise problem-first description and verifiable evidence. Use when the user asks to create, file, open, or update a PR. Do not use merely to review a diff or when publication is not authorized.
Also in 8 projects that use this
assisjpSkilltakeover
Take over an existing branch, pull request, worktree, or agent handoff while preserving the original goal, contributor credit, and concurrent work. Use when the user asks to take over, finish, rescue, or continue someone else's implementation. Do not use to replace a clear request to start new work.
Also in 3 projects that use this
owidSkillbabysit-pr
Spawn a background agent that babysits an open PR — triggers a Codex review, watches CI, judges and fixes valid findings, replies to and resolves review threads, and loops to a cap. Never merges. Trigger when the user asks to "babysit the PR", "ask for codex review(s) and watch CI", or after pushing a substantial chunk to a PR branch.
Also in 8 projects that use this
jaydubya818Skillno-comments
Use when code comments need structural review, root-cause fixes, and constraint encoding.
Also in 3 projects that use this
- +1 more from scottwater
Other versions20 projects use a version of this.
Word for word · 0
None found.
Edited · 11
- t3dotgg/tstack★ 3.8k70% same
- cogine-ai/cogine-dev-skillset★ 370% same
- Dhruv2mars/skills★ 325% same
- connorch/skills★ 269% same
- scottwater/skills★ 267% same
- johnnygreco/skills★ 153% same
- salasebas/skills★ 166% same
- lbussell/agent-skills★ 066% same
- lihbr/skills★ 068% same
- luisgui1757/sentinel★ 069% same
1 more not listed
Wrote their own version · 9
- malinskibeniamin/skills★ 4same name
- shhac/skills★ 4same name
- adelrodriguez/skills★ 1same name
- jameswyse/skills★ 1same name
- JeffreyFerreiras/ai-skills★ 1same name
- ptrandev/claude-skills★ 1same name
- ayv4zyan/skills★ 0same name
- mjeffrey18/skills★ 0same name
- syanga/astack★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository22 other files it gives its agents.
- analyze-logsSkill
- architectSkill
- build-audit-logsSkill
- cloudflareSkill
- code-reviewSkill
- design-engineeringSkill
- diagnosing-bugsSkill
- full-stopSkill
- ghSkill
- grillingSkill
- impeccableSkill
- improve-animationsSkill
- interrogateSkill
- no-use-effectSkill
- prSkill
- retroSkill
- t3-toolsSkill
- triageSkill
- unslopSkill
- vitestSkill
- wait-whatSkill
- writing-for-agentsSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
27 rules. 1 is common, 14 are distinctive, and 12 are very specific to this project.
1
Common
Most of the 20 edited versions we read keep these.
14
Distinctive
This author's own choices. Worth a look.
12
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- could be automatic: a setting could enforce it
- Very specific: line 14
If the user did not explicitly invoke $full-send or clearly ask for full send, do not assume full autonomy.
- Distinctive: line 25
Use the test methods that Proof needs, without asking first.
- Distinctive: line 48
Look up the repo's rules before you open a PR:
- Very specific: line 50
If .agents/skills/pr/SKILL.md exists, use it to open the PR.
- Distinctive: line 54
Use the repo's documented CI command.
- Very specific: line 58
Run every stage in order. The user names only $full-stop or $full-send.
- Distinctive: line 80
Use what this session already shows.
- Very specific: line 92
If a spec or tickets exist, or an agreed $architect design does, skip the stages they already cover.
- Very specific: line 109
Every sub-agent model comes from the tiers in the t3-tools skill ("Choosing a model").
- Very specific: line 132
If the repo has no tracker docs, use the local ticket form in to-tickets.
- Distinctive: line 153
Run the repo's documented CI command.
- Distinctive: line 154
Add one focused test that fails without the fix, when the behavior has none and the repo has a test setup.
- Distinctive: line 160
When you cannot find a way to prove a change, you do not have full confidence.
- Very specific: line 165
Before stage 8's last pass, read /Users/home/.agents/skills/full-send/references/review-loop.md and follow it.
- Distinctive: line 170
Only act on checks and comments newer than the latest push.
- Very specific: line 177
If the repo has .macroscope/check-run-agents/*.md, read those rules before you reply to a Macroscope finding.
- Distinctive: line 181
Keep the PR at the size the goal needs.
- Distinctive: line 186
If nothing has changed, stay quiet rather than posting filler comments.
- Distinctive: line 187
If an overlapping PR makes this one obsolete, stop, report it to the user, and ask before closing the PR.
- Very specific: line 192
Use one watcher per PR. Never write your own polling loop or sleep loop, and never run two watchers on the same PR.
- Very specific: line 200
Only the thread that owns the PR watches it.
- Very specific: line 211
If remaining is near 0, wait for reset with one background command, then watch again.
- Distinctive: line 213
Before a merge, run git fetch and check the PR again.
- Common: line 228
No human review still requests changes.
- Very specific: line 238
Before you post any comment on the user's behalf, read /Users/home/.agents/skills/full-send/references/comment-format.md and follow it.
- Distinctive: line 249
Ask only when you cannot continue alone:
- Distinctive: line 262
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 …
“Common” is measured: kept by at least 6 in 10 of the 20 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Full Send
The user invoked $full-send, so they are not watching this thread and want the
work completed end-to-end without them. 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 invoke $full-send or clearly ask for full send,
do not assume full autonomy. If they did, everything below applies.
Grant
The user grants you permission to:
- Merge the PR once the merge gate passes. This is the only agent merge authority. It overrides any repo PR skill rule that says "mark ready, then stop." Sub-agents never merge.
- Force-push the PR's own branch with
--force-with-leaseafter 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.
Repo rules
Look up the repo's rules before you open a PR:
- If
.agents/skills/pr/SKILL.mdexists, use it to open the PR. Its "mark ready, then stop" rule does not apply here. Full send's merge grant does. - Otherwise open the PR directly with
gh pr createas a draft, followingAGENTS.mdandCONTRIBUTING.md. - Use the repo's documented CI command. Do not substitute a generic one.
Stages
Run every stage in order. The user names only $full-stop or $full-send; picking
the skills is your job. Record each stage as run or skipped, with the reason, and
put that ledger in the report. A stage marked "may skip" needs a stated reason.
| # | Stage | Do |
| 1 | Frame | Write the goal, the done condition, what is out of scope, and how you will prove it, before any code |
| 2 | Size | Pick Direct, Design, or Split. See "Routes" |
| 3 | Impact | Use the Blast radius mode of interrogate: who and what this touches, and the one fact it is safe because of. May skip only for a local change with no shared code, schema, API, auth, or data |
| 4 | Design | Design and Split routes, when the shape is open: run architect |
| 5 | Plan | Split route: run to-tickets |
| 6 | Build | Read the implement guide. Direct and Design use its TDD loop when there is a cheap test target. Split uses "Fan out a spec". If you are on the default branch, create a branch first. Use the smallest change that works, and fix the case that happened, not every case that could |
| 7 | Prove | Run the proof from stage 1, plus anything impact flagged. See "Proof" |
| 8 | Review | Run each pass in "Review passes". Fix or decline every finding before the next pass |
| 9 | Open the PR | Rebase onto origin/<base>, then open the PR with the repo rules above. Write the body through unslop, with one short line on how you proved the change unless the template covers it. Use t3-tools for the T3 steps. Right after gh pr create, call link_pull_request with the URL if T3 tools are present |
| 10 | Push and gate | Push the tested commit, run the repo CI command, and wait for the required check to succeed on the head SHA before gh pr ready. Then start the watcher. See "Watching" |
| 11 | Babysit | Fix real findings and CI failures. Get proof for each fix before you push it. See "Review rules" |
| 12 | Merge | When the merge gate passes. If the repo uses a merge queue or auto-merge, stay until GitHub reports the PR as merged |
| 13 | Report | The route and why, the stage ledger, the PR link, the merge commit, your proof, the reviewer model used (and any substitution), and each decision you made for the user |
Routes
Use what this session already shows. If that does not settle it, start one read-only scout sub-agent on the cheapest capable model. It reports the files and modules involved, any new or changed public interface or schema, how many slices could ship independently, and any existing spec, tickets, or ADRs. It does not edit. The route is your decision, not the scout's.
| Route | Use when |
| Direct | One concern, the shape is obvious, and it fits one session |
| Design | It fits one session, but the shape is open: a new module, interface, or data model, or more than one reasonable design |
| Split | It is too big for one session, or it holds several slices that ship independently |
If a spec or tickets exist, or an agreed $architect design does, skip the stages
they already cover. Take the lightest route that fits. If the work proves bigger
than the route, move up one and say so. All routes end in one PR.
Review passes
| Pass | Runs |
code-review | Every behavior change: repo standards and the spec |
interrogate, review mode | Split route, a real risk from impact, or anything touching auth, permissions, payments, data loss, or concurrency |
| Review loop | Every behavior change. See "Review loop" |
Comment, doc, or format-only changes run the last pass only. interrogate findings
count only when a run proves them.
Models
Every sub-agent model comes from the tiers in the t3-tools skill ("Choosing a
model"). That skill also says how to set one and what to do when one fails.
| Work | Tier |
Scout, build, merge work, code-review | Fast. Move a job up to Balanced if a Fast model gets it wrong twice |
architect runners | Strong: Opus plus one OpenCode model, so two families |
interrogate reviewers | Strong: all three models, one per family |
| Review loop | Cheap strong, first model (see references/review-loop.md) |
Loading
code-review, interrogate, unslop, and t3-tools are normal skills. Load
architect from /Users/home/.agents/skills/architect/SKILL.md. Load the others
from /Users/home/.agents/skills/full-send/routes/<name>/GUIDE.md: to-tickets
and implement.
Nobody is watching, so these rules override those skills and guides on this task:
- Where they say to check with the user (seams, the ticket breakdown, which candidate to pursue, unclear intent), decide yourself and list the decision in the report.
grillingneeds the user, so do not run it here.- If the repo has no tracker docs, use the local ticket form in
to-tickets. - Replace the final review and "mark ready" steps in
implementwith stages 7 to 13, run on the integration branch. - Merger sub-agents may merge worktree branches into the integration branch. Only this thread merges the PR.
- A missing decision about how to build it is yours. A missing decision about
what to build falls under "Asking the user". If several are missing, stop and
tell the user to run
$architectfirst.
Stay active from stage 1 to stage 13. If you end your turn while checks or reviews
are pending, the work stops, because nobody will prompt you again. Wait with the
watcher so something wakes you when the PR changes. 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 repo's documented CI command.
- 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.
Review loop
Before stage 8's last pass, read /Users/home/.agents/skills/full-send/references/review-loop.md and follow it. It holds the
reviewer model, budget, round brief, and stop rules.
Review rules
Only act on checks and comments newer than the latest push. Verify every review finding against the source before you change code. Fix real findings and CI failures. Distinguish repository failures from infrastructure flakes. When you dismiss a false positive, reply with a written reason and resolve the comment.
- Any auto-review on the head has finished, and each finding is fixed or dismissed with a written reason.
- If the repo has
.macroscope/check-run-agents/*.md, read those rules before you reply to a Macroscope finding. Its findings cite them. - CodeRabbit is advisory. Treat its findings like any other finding, but never wait for it and never hold a merge for it.
- Keep the PR at the size the goal needs. Review loops tend to grow a PR one cheap-looking fix at a time. Fix real bugs in the intended case. Decline the rest with a written reason and list them as follow-ups: unneeded tests, guards for edge cases that do not matter, extra integration or compatibility, and small performance costs. Prefer the fix that deletes or narrows code.
- If nothing has changed, stay quiet rather than posting filler comments.
- If an overlapping PR makes this one obsolete, stop, report it to the user, and ask before closing the PR.
Watching
Use one watcher per PR. Never write your own polling loop or sleep loop, and
never run two watchers on the same PR.
- In T3 Code, handle the existing checks and comments first. Then call
watch_pull_requestand end your turn. T3 Code wakes you when a check fails, the required checks pass, someone comments or reviews, or the branch conflicts. - Outside T3 Code, poll the head check-runs with
gh apiin one background command at a modest interval. Never run a tight loop. - Only the thread that owns the PR watches it. If you are a delegated child task
(a reviewer or any
delegate_taskchild), never callwatch_pull_request. - A wake is news, not a merge decision. Check the merge gate yourself.
- Unwatch when you hand off. Call
unwatch_pull_requestbefore you stop, whether the PR is ready, blocked, or you are asking the user. A merge or close ends the watch on its own. - Use
gh api repos/<owner>/<repo>/pulls/<n>andgh api repos/<owner>/<repo>/commits/<sha>/check-runsto read the PR and its checks.gh pr viewandgh pr checksuse GraphQL, which runs out first. - "Stopped watching, could not read it" usually means the GitHub rate limit is
used up. Run
gh api rate_limit --jq .resources.graphqlbefore you watch again. Ifremainingis near 0, wait forresetwith one background command, then watch again. Never watch again in a tight loop. - Before a merge, run
git fetchand check the PR again. Never merge when it is BEHIND or DIRTY, or when base commits that landed after the last green run touch this PR's files. Rebase, push, and wait for green again.
Merge gate
Full confidence means all of these are true on the latest commit:
- Your proof covers every change in the diff.
- Trust the forge's verdict, not a green check list. Ready means the forge agrees the PR can merge: read the status of the current head SHA and require the required check to be success. After any amend, rebase, or base update, rerun CI. Exit 0 is not the gate.
- Any auto-review on the head has 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 its base, and GitHub reports it as mergeable.
Merge with the method the repo allows. If its docs do not say, read
allow_squash_merge, allow_merge_commit, and allow_rebase_merge from
gh api repos/<owner>/<repo>. Never use --admin or other bypasses. Merge only through
branch protection as configured.
Comment format
Before you post any comment on the user's behalf, read
/Users/home/.agents/skills/full-send/references/comment-format.md and follow it.
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.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

