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.
Cross-repo + mesh communication: file tracked GitHub issues on sibling repos, comment on existing issues, fetch issues with body + comments to inline current state into briefs, and send live…
$ npx skills add agentculture/culture --skill communicate -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install agentculture/culture communicate --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/agentculture/culture.git skills-src && mkdir -p .claude/skills && cp -r skills-src/culture_core/skills/communicate .claude/skills/communicate && 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 "communicate" agent skill from https://github.com/agentculture/culture/tree/main/culture_core/skills/communicate into .claude/skills/communicate/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "communicate", 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/agentculture/culture/tree/main/culture_core/skills/communicateType 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 agentculture/culture --skill communicate -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install agentculture/culture communicate --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/agentculture/culture.git skills-src && mkdir -p .agents/skills && cp -r skills-src/culture_core/skills/communicate .agents/skills/communicate && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "communicate" agent skill from https://github.com/agentculture/culture/tree/main/culture_core/skills/communicate into .agents/skills/communicate/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "communicate", 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 agentculture/culture --skill communicate -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install agentculture/culture communicate --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/agentculture/culture.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/culture_core/skills/communicate .cursor/skills/communicate && 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 "communicate" agent skill from https://github.com/agentculture/culture/tree/main/culture_core/skills/communicate into .cursor/skills/communicate/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "communicate", 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/agentculture/culture.git --path culture_core/skills/communicate--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 agentculture/culture --skill communicate -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install agentculture/culture communicate --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/agentculture/culture.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/culture_core/skills/communicate .gemini/skills/communicate && 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 "communicate" agent skill from https://github.com/agentculture/culture/tree/main/culture_core/skills/communicate into .gemini/skills/communicate/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "communicate", 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 agentculture/culture communicateInstalls 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 agentculture/culture --skill communicate -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/agentculture/culture.git skills-src && mkdir -p .github/skills && cp -r skills-src/culture_core/skills/communicate .github/skills/communicate && 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 "communicate" agent skill from https://github.com/agentculture/culture/tree/main/culture_core/skills/communicate into .github/skills/communicate/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "communicate", 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 agentculture/culture --skill communicate -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install agentculture/culture communicate --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/agentculture/culture.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/culture_core/skills/communicate .opencode/skills/communicate && 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 "communicate" agent skill from https://github.com/agentculture/culture/tree/main/culture_core/skills/communicate into .opencode/skills/communicate/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "communicate", 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.
communicateCross-repo + mesh communication: file tracked GitHub issues on sibling repos, comment on existing issues, fetch issues with body + comments to inline current state into briefs, and send live…
Communicate is an agent skill from agentculture/culture. Cross-repo + mesh communication: file tracked GitHub issues on sibling repos, comment on existing issues, fetch issues with body + comments to inline current state into briefs, and send live messages to Culture mesh channels. Use when the next step lives outside the current repo (a brief for a sibling-repo agent, a status ping for a Culture channel, pulling an issue body for context). Issue I/O is backed by agtag (=0.1); agtag auto-signs from the local culture.yaml. Mesh messages are unsigned (the IRC nick is the…
Its SKILL.md is about 2.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 8 other files, including scripts (for example `scripts/fetch-issues.sh`, `scripts/mesh-message.sh` and `scripts/post-comment.sh`).
It works with GitHub. The repository describes itself as: Culture turns isolated stochastic agents into cooperative, inspectable, improvable artificial colleagues. The licence is Apache-2.0.
3 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit d5b5715. It shows what the files ask for, not the result of running them.
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.
Ships 6 files in scripts/ (Shell), which the agent can run.
Shell commands in SKILL.md call:
bashghuvFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md. Its commands use gh and uv, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Communicate loads about 2.7k tokens when it runs. Until then it costs about 136 tokens; SKILL.md has 1,184 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.
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); the scripts in this folder are not scanned.
The full file from agentculture/culture at commit d5b5715, republished under its Apache-2.0 licence (© agentculture). 1,184 words, ~2,652 tokens.
.claude/skills/communicate/SKILL.md (or your agent's skills folder). This skill also uses 6 other files; get the full folder from GitHub.<!--
Vendored from agentculture/guildmaster → .claude/skills/communicate/
(the AgentCulture skills hub, post steward→guildmaster cutover; lineage:
steward through 0.11.x). The
three GitHub verbs (post-issue.sh, post-comment.sh, fetch-issues.sh)
are thin wrappers around `agtag issue post|reply|fetch`. agtag resolves
the signing nick from the local `culture.yaml`'s first agent suffix
(falling back to repo basename), so this vendored copy needs no
hard-coded signature literal. When installed alongside the culture
repo's `culture.yaml` (suffix: culture), agtag signs as
`- culture (Claude)`. Mesh-message handling is unchanged — culture's
own CLI is already the underlying transport.
-->
Culture's role is to coordinate work across the AgentCulture mesh; that surfaces in four distinct channels:
post-issue.sh (GitHub).post-comment.sh (GitHub).fetch-issues.sh (GitHub).mesh-message.sh (Culture IRC).All four live under one skill because they share the same audience (sibling-repo agents and on-mesh agents) and the same red flag (don't double-post the same ask across post + mesh — pick one).
The three GitHub verbs (post-issue.sh, post-comment.sh,
fetch-issues.sh) are thin wrappers around the agtag CLI
(agtag issue post|reply|fetch). agtag handles auto-signature
resolution from the local culture.yaml (falling back to repo
basename), JSON output mode, and a uniform exit-code policy. Read
agtag learn for the agent-facing self-teaching prompt and
agtag explain agtag / agtag explain issue for the surface docs —
this SKILL.md does not re-document agtag's flags.
agtag is a runtime dependency of culture (agtag>=0.1,<1.0), so any
culture install carries it. If you're running outside a culture venv:
uv tool install agtag # or: pip install --user agtagmesh-message.sh stays a culture channel message wrapper for now;
agtag mesh transport is slated for v0.2.
post-issue.sh)mesh-message.sh)post-comment.sh)agtag issue post you sent earlier and
the resolution belongs on the same thread.fetch-issues.sh)gh issue view "Projects (classic) deprecated" error by
passing --json explicitly to GitHub.gh issue create directly.The receiving agent must not need culture-side context to act. Inline the relevant content; do not say "see culture's plan."
A brief that says "see culture#NN" is a bug. The receiving agent will look at it, get lost in culture-specific context that's irrelevant to them, and either ask for clarification (slow round-trip) or guess wrong (worse). Inline the ask, the rationale, and concrete acceptance criteria. Quote source-of-truth files (path + line numbers + small excerpts) when their shape matters to the ask.
| Channel | Signature | Why |
|---|---|---|
| GitHub issues / comments | - culture (Claude) — agtag resolves the nick from the local culture.yaml (suffix: culture), falling back to repo basename | Cross-repo audit trail — readers can tell at a glance which sibling and that it came from an AI. |
| Culture mesh | none — unsigned | The IRC nick already identifies the speaker. A trailing - <nick> (Claude) would be visual noise that the nick already supplies. |
Vendors do not need to edit a literal — agtag does the resolution.
--as NICK overrides if a vendor needs to sign as something other than
its culture.yaml suffix. Mesh messages stay unsigned across all
vendors.
<verb> <thing> (unblocks <consumer>) — e.g.,
Vendor portability-lint into <repo> (unblocks culture 11.1 doctor --apply).
The parenthetical tells the receiving repo's maintainers what's waiting
on them. Drop the parenthetical only when the ask isn't blocking
anything.
bash <skill-dir>/scripts/post-issue.sh \
--repo agentculture/<sibling> \
--title "Vendor portability-lint into <sibling> (unblocks culture 11.1)" \
--body-file /tmp/brief.mdOr pass the body on stdin:
bash <skill-dir>/scripts/post-issue.sh \
--repo agentculture/<sibling> \
--title "..." <<'EOF'
<brief body here, multi-paragraph, with all the inline context the receiving agent needs>
EOFThe script prints the issue URL on success — capture it for
cross-references in your spec / plan / PR description. agtag appends
the signature - culture (Claude) (resolved from culture.yaml).
bash <skill-dir>/scripts/post-comment.sh \
--repo agentculture/<sibling> \
--number 42 \
--body-file /tmp/follow-up.mdAuto-signed by agtag from culture.yaml; do not hand-author the
trailing nick.
bash <skill-dir>/scripts/mesh-message.sh \
--channel "#general" \
--body "PR #42 — all review threads addressed. Ready for merge."Body can also come from --body-file PATH or stdin. The script wraps
culture channel message <target> <text> and forwards exit codes
unchanged, so failures (no Culture server, agent not connected) surface
verbatim. No signature is appended — the IRC nick is the speaker.
The script requires culture on PATH and an active mesh agent for the
current shell (set CULTURE_NICK). If either is missing the script
fails with the underlying CLI error verbatim — fix the registration,
don't paper over it.
bash <skill-dir>/scripts/fetch-issues.sh 191 --repo agentculture/culture
bash <skill-dir>/scripts/fetch-issues.sh 191-197 --repo agentculture/culture
bash <skill-dir>/scripts/fetch-issues.sh 191 195 197Output is one JSON object per issue (separated by header bars) with
number, title, state, labels, body, and comments. Without
--repo, gh resolves the repo from the current git remote.
| Script | Purpose |
|---|---|
scripts/post-issue.sh | Create a new issue on a target repo. Wraps agtag issue post; auto-signs from culture.yaml. |
scripts/post-comment.sh | Comment on an existing issue. Wraps agtag issue reply; auto-signs from culture.yaml. |
scripts/fetch-issues.sh | Fetch one or more issues (single / range / list) with body + comments. Wraps agtag issue fetch. |
scripts/mesh-message.sh | Send a message to a Culture mesh channel. Unsigned (IRC nick is the speaker). |
scripts/templates/skill-update-brief.md | The Markdown template the steward broadcast verb consumes. Vendored for reference; culture itself does not run a broadcast verb. |
Never:
--no-signature flag.- <nick> (Claude). The nick already says
who you are.gh issue create instead.- culture (Claude) at the end of an issue or comment
body — agtag appends it. Manual typing creates double-signatures.Source: agentculture/guildmaster → .claude/skills/communicate/ (the
AgentCulture skills hub, post steward→guildmaster cutover; lineage:
steward through 0.11.x). Re-cite from there when guildmaster bumps the
skill. Scripts intentionally diverged from the upstream copy carry a
# culture-divergence: header.
© agentculture, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 6 other files (scripts) in culture_core/skills/communicate of agentculture/culture.
Open the folder on GitHubat commit d5b5715
Communicate 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 |
|---|---|---|---|---|---|---|
| Communicate this skillagentculture/culture | 113 | — | ~2.7k | Automated safety check: Pass | Apache-2.0 | |
| PR Babysitteropeninterpreter/openinterpreter | 69k | 3 repos | ~4.2k | Automated safety check: Pass | Apache-2.0 | |
| Diagnosing Superpowers Sessionsobra/superpowers | 296k | 3 repos | ~1.7k | Automated safety check: Pass | MIT | |
| GitHub Deep Researchbytedance/deer-flow | 83k | 5 repos | ~1.3k | Automated safety check: Pass | MIT | |
| Greplooponyx-dot-app/onyx | 32k | 4 repos | ~3.3k | Automated safety check: Pass | MIT | |
| Update V8 Versionopeninterpreter/openinterpreter | 69k | 2 repos | ~845 | Automated safety check: Pass | Apache-2.0 |
openinterpreter/openinterpreter
Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.
obra/superpowers
Investigates a session where Superpowers went wrong, reads the transcripts on disk and produces an evidence-cited report, optionally prepared as a bug report for the maintainers.
bytedance/deer-flow
Researches a GitHub repository over four rounds using the GitHub API and web search, then writes a structured markdown report with timeline, metrics and Mermaid diagrams.
onyx-dot-app/onyx
Iteratively improves a PR (GitHub), MR (GitLab), or shelved changelist (Perforce) until Greptile gives it a 5/5 confidence score with zero unresolved comments.
openinterpreter/openinterpreter
Bumps the pinned v8 and rusty_v8 versions in Codex, validates the release-candidate path with the v8-canary check, and traces failures to upstream build changes.
mvanhorn/last30days-skill
Research what people actually say about any topic in the last 30 days.
agentculture/culture
Show a Culture agent's full configuration in one read-only view: its system-prompt file (CLAUDE.md / AGENTS.md / GEMINI.md), the parallel culture.yaml, and the agent's local .claude/skills index.
agentculture/culture
CI/CD lane for culture: branch, commit, push, create PR, wait for automated reviewers, fetch comments, fix or pushback, reply, resolve threads.
agentculture/culture
All agent communication from culture: in-mesh chat (channels, DMs, mentions, knowledge sharing) via culture channel CLI, AND cross-repo hand-off briefs to sibling-repo agents (agentirc, steward…
agentculture/culture
Fan out a converged devague plan's dependency waves to parallel agents in isolated git worktrees, one agent per task per wave, with TDD-gated merges by the main agent.
agentculture/culture
Switch a PyPI package install between the production index, TestPyPI pre-release builds, and a local editable checkout.
agentculture/culture
Run pytest with parallel execution and coverage. An agent skill from agentculture/culture.
Works with
Cross-repo + mesh communication: file tracked GitHub issues on sibling repos, comment on existing issues, fetch issues with body + comments to inline current state into briefs, and send live…. Communicate is an agent skill from agentculture/culture. Cross-repo + mesh communication: file tracked GitHub issues on sibling repos, comment on existing issues, fetch issues with body + comments to inline current state into briefs, and send live messages to Culture mesh channels.
Communicate fits situations like: the next step lives outside the current repo (a brief for a sibling-repo agent; A status ping for a Culture channel; pulling an issue body for context).
Run `npx skills add agentculture/culture --skill communicate -a claude-code`. Or copy the skill folder (culture_core/skills/communicate in agentculture/culture) into .claude/skills/communicate in your project. Claude Code loads it when a task matches its description.
Run `npx skills add agentculture/culture --skill communicate -a codex`. Or copy the skill folder (culture_core/skills/communicate in agentculture/culture) into .agents/skills/communicate in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add agentculture/culture --skill communicate -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/communicate, .gemini/skills/communicate, .github/skills/communicate and .opencode/skills/communicate in your project.
Going by SKILL.md and its folder, Communicate needs a shell for the scripts in its folder and the command-line tools its instructions call (bash, gh and uv). Our summary lists: Python 3; A Bash shell.
SKILL.md contains no URLs. Its commands use gh and uv, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
Communicate is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.7k tokens (SKILL.md is roughly 11k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Communicate: PR Babysitter (openinterpreter/openinterpreter, 69k stars), Diagnosing Superpowers Sessions (obra/superpowers, 296k stars), GitHub Deep Research (bytedance/deer-flow, 83k stars) and Greploop (onyx-dot-app/onyx, 32k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
agentculture (a GitHub organization) maintains it in agentculture/culture, which has 113 GitHub stars. The repository holds 18 skills in this directory. The repository was last updated on August 23, 2026.
Source: agentculture/culture on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.