post-merge-cleanup
Bring the project's knowledge files up to date from merged pull requests, or from an agent run's pull request before it merges.
Skill by openagt
Chalk Labs
Need help deploying post-merge-cleanup?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/openagt-post-merge-cleanup-7f6b0e
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions: not checked yet.
What's inside
- Skill name
post-merge-cleanup- Description
- Bring the project's knowledge files up to date from merged pull requests, or from an agent run's pull request before it merges.
- License
- MIT
- Instructions
- 9 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
Write what merged work decided and taught into the project's knowledge files. Nobody will answer you: never ask, decide yourself. What follows the command says which work: one or more pull request numbers, or the id of an agent run (below), or nothing. When nothing follows it, the work is every pull request merged since the start of the last run of this same command that had nothing after it and ended done, as the project's record of agent runs shows, or in the last 24 hours when there is no such run, less every pull request whose body has the line `Post-merge cleanup done.`. If the pull requests cannot be read, show an error to the user saying why and stop. If there is none, say so and stop. Read each pull request: its changes and its discussion. The knowledge files, each created when missing: `knowledge-base/DECISIONS.md`, the decisions taken and why; `knowledge-base/FACTS.md`, the non-obvious facts; `knowledge-base/INSIGHTS.md`, the insights. Write only what a future agent would need and cannot get from the code itself, and nothing the files already say. If nothing is worth writing, publish nothing. Otherwise commit, and publish the work as far as whoever started you said; when they said nothing, publish nothing. A pull request's body names the pull requests it covers and ends with the line `Post-merge cleanup done.`. Your last message names each pull request covered and what you wrote. When the id of an agent run follows the command, you are on that run's branch, and the run's pull request waits to merge until you are done: that pull request is the work. Read the run in the project's record of agent runs, what it was asked and what its agent said, and read the pull request's changes and its discussion. If the run cannot be read, show an error to the user saying why and stop. Open no other pull request and arm no merge: it is merged for you once you are done. If nothing is worth writing, commit nothing; otherwise commit on the branch you are on and push it. Either way, then add the line `Post-merge cleanup done.` at the end of the pull request's body, keeping the rest as it is. Your last message says what you wrote.
From openagt/openagent, MIT.
More from openagt/openagent
- 0.629score
branches
openagt
Where your work goes (a branch named agent-<name>), how to name it, what must be true before you finish, and how to push it when you are asked to.
SkillAFreshness: A★ 11Claude Code +9 - 0.629score
tickets
openagt
Where the project's tickets live, how to read and change them, how to claim a ticket so no two agents work the same one, how to queue one, and the formats.
SkillAFreshness: A★ 11Claude Code +9 - 0.629score
browser
openagt
A real browser you drive from the shell, to see or act on a web page (open it, read it, click, type, take a screenshot), such as checking that the app you…
SkillAFreshness: A★ 11Claude Code +9 - 0.629score
orchestration
openagt
Split your task across subagents: plan it, get the person's yes, start other agents on the parts, each in its own checkout on a branch started from yours, and…
SkillAFreshness: A★ 11Claude Code +9 - 0.629score
scheduler
openagt
Start and stop the project's scheduler, switch the commands it starts on a schedule on or off, set their pace, or start one now, when the person asks you to.
SkillAFreshness: A★ 11Claude Code +9 - 0.629score
github
openagt
The project's git host is GitHub: how to open your pull request when you are asked to, how to land it, and how to read and close the project's issues.
SkillAFreshness: A★ 11Claude Code +9 - 0.629score
logs
openagt
The record of every run agents made on this project — what was asked, where the work went, how it ended, what the agent said — where it lives, how to read it…
SkillAFreshness: A★ 11Claude Code +9 - 0.626score
queue
openagt
Where the project's agent queue lives, how to read it and change it, and its format.
SkillAFreshness: A★ 11Claude Code +9 - 0.626score
discord
openagt
Post a message to the team's Discord channel from the shell, when a task asks you to tell people something there.
SkillAFreshness: A★ 11Claude Code +9 - 0.624score
reply
openagt
Answer where a maintainer calls you with /agent, on an issue or a pull request; and on your own pull request, checks that turned red and a conflict with its…
SkillAFreshness: A★ 11Claude Code +9 - 0.624score
readability
openagt
Refactor a part of the code to make it as easy as possible for humans to read, rating every file and function before and after.
SkillAFreshness: A★ 11Claude Code +9 - 0.624score
post-merge-cleanup
openagt
Bring the project's knowledge files up to date from merged pull requests, or from an agent run's pull request before it merges.
SkillAFreshness: A★ 11Claude Code +9
Signals
- Stars
- 11
- Forks
- 1
- Open issues
- 12
- Last commit (this folder)
- Oct 21, 2026 (10 days ago)
- Last release
- Aug 19, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/openagt/openagent
- Website
- openagent.build
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
Same skill elsewhere
Copies of this SKILL.md published by others; search shows only one of them.
More from openagt
- 0.629score
scheduler
openagt
Start and stop the project's scheduler, switch the commands it starts on a schedule on or off, set their pace, or start one now, when the person asks you to.
SkillAFreshness: A★ 11Claude Code +9 - 0.629score
github
openagt
The project's git host is GitHub: how to open your pull request when you are asked to, how to land it, and how to read and close the project's issues.
SkillAFreshness: A★ 11Claude Code +9 - 0.629score
logs
openagt
The record of every run agents made on this project — what was asked, where the work went, how it ended, what the agent said — where it lives, how to read it…
SkillAFreshness: A★ 11Claude Code +9 - 0.629score
browser
openagt
A real browser you drive from the shell, to see or act on a web page (open it, read it, click, type, take a screenshot), such as checking that the app you…
SkillAFreshness: A★ 11Claude Code +9 - 0.629score
orchestration
openagt
Split your task across subagents: plan it, get the person's yes, start other agents on the parts, each in its own checkout on a branch started from yours, and…
SkillAFreshness: A★ 11Claude Code +9 - 0.629score
tickets
openagt
Where the project's tickets live, how to read and change them, how to claim a ticket so no two agents work the same one, how to queue one, and the formats.
SkillAFreshness: A★ 11Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get post-merge-cleanup running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
post-merge-cleanup skill. Agent Mart. https://agentmart.dev/skills/openagt-post-merge-cleanup-7f6b0e (last updated 2026-10-24)