Official agent skill

Safe Push

by JetBrains in JetBrains/intellij-community

Push IntelliJ repository changes through the Safe Push workflow.

OfficialCustom licenceAuto-check passed

Install Safe Push

skills CLI
$ npx skills add JetBrains/intellij-community --skill safe-push -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install JetBrains/intellij-community safe-push --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/JetBrains/intellij-community.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/safe-push .claude/skills/safe-push && rm -rf skills-src

Use ~/.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/

Facts

Skill name
safe-push
GitHub stars
21k
Token cost
~1.1k tokens
SKILL.md length
465 words
Files
1
Skills in repo
38
Repo updated
First seen
Licence
Custom licence

At a glance

Push IntelliJ repository changes through the Safe Push workflow.

  • Works in 5 steps: Your changes are pushed to a temporary… → Patronus triggers required CI checks… → Tests may retry up to 4 times for flaky… → …
  • SKILL.md covers Overview, Safe Push CLI, Emergency Push and Bazel Tests and Environment…, plus 2 more sections
  • Reaches patronus.labs.jb.gg

What it does

Safe Push is an agent skill from JetBrains/intellij-community, published by the product's own GitHub organization. Push IntelliJ repository changes through the Safe Push workflow.

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It works with JetBrains IDEs. The repository describes itself as: IntelliJ IDEA & IntelliJ Platform.

Example prompts

  • “/safe-push”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Your changes are pushed to a temporary branch
  2. Patronus triggers required CI checks (tests, compilation)
  3. Tests may retry up to 4 times for flaky failures
  4. If all checks pass, changes are merged to the target branch
  5. You receive Slack/Space/Email notification of results

What it can do on your machine

Read from SKILL.md and the folder at commit 562e3a2. 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 (its code samples are bash and java).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • patronus.labs.jb.gg

    Also links to:

    • youtrack.jetbrains.com

    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

Safe Push loads about 1.1k tokens when it runs. Until then it costs about 19 tokens; SKILL.md has 465 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~19
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k

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

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 465 words (~1,072 tokens).

“This guide covers the Safe Push process for pushing changes to the IntelliJ repository.”

— opening of SKILL.md by JetBrains, Custom licence
name
safe-push

Read the full SKILL.md on GitHub

Files

Just SKILL.md in .agents/skills/safe-push of JetBrains/intellij-community.

Open the folder on GitHubat commit 562e3a2

Compare with similar skills

Safe Push 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.

Safe Push compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Safe Push this skillJetBrains/intellij-community21k—~1.1kAutomated safety check: PassCustom licence
Doc SyncJetBrains/ideavim10k2 repos~2.6kAutomated safety check: PassMIT
Evals Contextzgsm-ai/costrict4.4k1 repos~1.9kAutomated safety check: PassApache-2.0
ChangelogJetBrains/ideavim10k1 repos~2.7kAutomated safety check: PassMIT
Compose Multiplatform Patternsmonta-app/ocpp-emulator1805 repos~2kAutomated safety check: PassApache-2.0
Roo Conflict Resolutionzgsm-ai/costrict4.4k—~2.3kAutomated safety check: PassApache-2.0

Similar skills

  • Doc Sync

    JetBrains/ideavim

    Official

    Keeps IdeaVim documentation in sync with code changes. An agent skill from JetBrains/ideavim.

    10k GitHub starsUsed in 2 repos~2.6k tokens
    DevelopmentAuto-check passed
  • Evals Context

    zgsm-ai/costrict

    Provides context about the CoStrict evals system structure in this monorepo.

    4.4k GitHub starsUsed in 1 repo~1.9k tokens
    AI & LLM EngineeringAuto-check passed
  • Changelog

    JetBrains/ideavim

    Official

    Maintains the IdeaVim changelog (CHANGES.md). An agent skill from JetBrains/ideavim.

    10k GitHub starsUsed in 1 repo~2.7k tokens
    DevelopmentAuto-check passed
  • Compose Multiplatform Patterns

    monta-app/ocpp-emulator

    Compose Multiplatform and Jetpack Compose patterns for KMP projects — state management, navigation, theming, performance, and platform-specific UI.

    180 GitHub starsUsed in 5 repos~2k tokens
    MobileAuto-check passed
  • Roo Conflict Resolution

    zgsm-ai/costrict

    Provides comprehensive guidelines for resolving merge conflicts intelligently using git history and commit context.

    4.4k GitHub stars~2.3k tokensUpdated 7 days ago
    DevelopmentAuto-check passed
  • Official

    Analyze an MPS language by name — discover concepts, properties, references, children, aspects (editor/constraints/behavior), and metadata.

    1.7k GitHub stars~1.4k tokensUpdated today
    Auto-check passed

More from JetBrains/intellij-community

All 38 skills in this repo
  • Youtrack Community

    JetBrains/intellij-community

    Official

    YouTrack CLI for a community checkout; the monorepo uses youtrack.

    21k GitHub stars~3.2k tokensUpdated today
    Auto-check: notes
  • Compare Python Typecheckers

    JetBrains/intellij-community

    Official

    Compare Python type inference with ty, pyrefly, and basedpyright.

    21k GitHub stars~617 tokensUpdated today
    Auto-check passed
  • Sibling Checkout Commits

    JetBrains/intellij-community

    Official

    Take commits from a sibling checkout as patches, without a fetch.

    21k GitHub stars~753 tokensUpdated today
    Auto-check passed
  • Code Style

    JetBrains/intellij-community

    Official

    Apply IntelliJ Kotlin and Java code style when writing or reviewing.

    21k GitHub stars~795 tokensUpdated today
    Auto-check passed
  • Notebook For Experiment

    JetBrains/intellij-community

    Official

    Create reproducible Jupyter notebooks for performance experiments.

    21k GitHub stars~4.4k tokensUpdated today
    Auto-check: warnings
  • Jewel Markdown

    JetBrains/intellij-community

    Official

    Build or debug Jewel Markdown parsing, rendering, and styling.

    21k GitHub stars~4.3k tokensUpdated today
    Auto-check passed

Works with

Questions about Safe Push

What does Safe Push do?

Push IntelliJ repository changes through the Safe Push workflow. Safe Push is an agent skill from JetBrains/intellij-community, published by the product's own GitHub organization. Push IntelliJ repository changes through the Safe Push workflow.

How do I install Safe Push in Claude Code?

Run `npx skills add JetBrains/intellij-community --skill safe-push -a claude-code`. Or copy the skill folder (.agents/skills/safe-push in JetBrains/intellij-community) into .claude/skills/safe-push in your project. Claude Code loads it when a task matches its description.

How do I install Safe Push in Codex?

Run `npx skills add JetBrains/intellij-community --skill safe-push -a codex`. Or copy the skill folder (.agents/skills/safe-push in JetBrains/intellij-community) into .agents/skills/safe-push in your project. Codex loads it when a task matches its description.

Can I use Safe Push 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 JetBrains/intellij-community --skill safe-push -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/safe-push, .gemini/skills/safe-push, .github/skills/safe-push and .opencode/skills/safe-push in your project.

What does Safe Push need to run?

SKILL.md names no scripts, command-line tools or credentials: Safe Push is instructions for the agent only.

Does Safe Push access the network?

SKILL.md names 2 domains. In commands or code: patronus.labs.jb.gg; the agent is likely to contact it when it follows the instructions. As links in the text: youtrack.jetbrains.com. This is read from the text; nothing was executed.

Is Safe Push 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 Safe Push use?

Safe Push has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Safe Push use?

About 1.1k tokens (SKILL.md is roughly 4.3k 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 Safe Push?

Skills that share tags, products or a category with Safe Push: Doc Sync (JetBrains/ideavim, 10k stars), Evals Context (zgsm-ai/costrict, 4.4k stars), Changelog (JetBrains/ideavim, 10k stars) and Compose Multiplatform Patterns (monta-app/ocpp-emulator, 180 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Safe Push?

JetBrains (a GitHub organization, an official publisher) maintains it in JetBrains/intellij-community, which has 20,613 GitHub stars. The repository holds 38 skills in this directory. The repository was last updated on October 8, 2026.

Source: JetBrains/intellij-community on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.