agentleFS
Sign inStart free
amirkiarafieiamirkiarafiei/subagent-cli-skills/skills/junie-cli/SKILL.md

junie-cli

Skill14 starsChanged 10 days agoMITView on GitHub

Use Junie CLI as a subagent. Lets the main agent prompt Junie CLI from the terminal in headless mode with the `junie` command, and send the goal, the decisions and the scope with the task. Use when the user asks to delegate work to Junie CLI, when a task needs a second independent agent, or when a plan needs a fresh perspective.

  • Pipes a download into a shell
  • Reads credentials

The file

We split this skill into the rules it gives an agent

10 rules. About 0 are common, 9 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈9

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Secrets or policy-sensitive work: Do not pipe credentials into a subagent.

    line 48
  2. Distinctive:

    Low return on investment: If writing the handoff costs more than doing the edit, do the edit.

    line 50
  3. Distinctive:

    Treat every call as stateless delegation: the subagent keeps nothing between calls, so each command must carry its own state.

    line 61
  4. Distinctive:

    Write the prompt as a transfer of shared state, not as a title.

    line 71
  5. Distinctive:

    Prefer sequential delegations with explicit carry-over.

    line 82
  6. Distinctive:

    After the subagent returns:

    line 96
  7. Distinctive:

    Every vendor has its own terminal rules.

    line 104
  8. Distinctive:

    Exit code 0 is not success: If stdout is empty, treat the run as failed and read stderr.

    line 108
  9. Very specific:

    Keep all seven sub-headings, in this order, even if the answer is "none".

    line 119
  10. Distinctive:

    If the user names a model, use it.

    line 178

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Junie CLI (subagent / task delegation)

<!-- ============================================================================= GLOBAL HALF — sections 1 to 5. These sections are identical in every skill in this repository. Copy them without any change. Do not put a vendor name or a flag in them. A change here must be made in all skills at the same time. ============================================================================= -->

What is it

This skill teaches your agent to use an agent from another vendor as a subagent.

Almost every coding agent has a headless mode. Headless mode runs the agent from the terminal with one command and returns the answer to stdout. This skill gives the command pattern for one such agent, and the protocol to transfer enough context with the task.

You stay the main agent. You keep the plan, the decisions and the conversation with the user. The subagent does one bounded task and reports back.

When to delegate

  • The user asks for it. The user names another agent, or asks for a second opinion.
  • Large or multi-step work. The task covers several files, phases or checkpoints.
  • Code review with a fresh mind. Another agent reviews the work with a different lens and no memory of the decisions that produced it.
  • Planning that needs different ideas. A second agent proposes options that you did not consider.
  • An internal council. Several subagents answer the same question, and you compare the answers.
  • Deep research. The other CLI has web search, web extraction or browser automation.
  • Background investigation. A long task runs in the background while you continue in the foreground.

When not to delegate

  • Small or single-step tasks. One or two edits, or a short explanation, are faster in this thread.
  • Tight feedback loops. The user wants quick back-and-forth in one conversation.
  • Secrets or policy-sensitive work. Do not pipe credentials into a subagent. Redact first.
  • Context you already hold. Repeating the whole plan in a prompt adds no value.
  • Low return on investment. If writing the handoff costs more than doing the edit, do the edit.
  • Work that needs high precision and full judgement. A subagent without your context will break a task that depends on a detail only this session knows.

Delegation and context transfer protocol

An isolated subagent saves tokens, but it splits the story. The subagent does not see this conversation. It has no memory of the goal you agreed with the user, the decisions you already made, or the paths you agreed not to touch. A poor handoff causes misread tasks, wrong assumptions about the stack or the style, and wasted edits.

Treat every call as stateless delegation: the subagent keeps nothing between calls, so each command must carry its own state. A good handoff happens when you keep these practices in mind:

  • Shared state handoff. The prompt carries the original goal, the decisions already made, and the explicit scope, to bridge the subagent's missing session history.
  • Contextual preservation. The high-volume work stays in the isolated process, so the bulk never enters this conversation and no "split story" forms from missing history.
  • Result reconciliation. What comes back is folded into this thread afterwards, so there is a single source of truth.

Write the prompt as a transfer of shared state, not as a title. Include all six fields:

IncludeWhy
GoalThe same objective as the user, not only the immediate micro-task.
DecisionsFramework, patterns, naming, "use X not Y" — anything that would otherwise be guessed wrong.
ScopeThe absolute paths and modules to touch, and the areas to leave alone. A relative path may not resolve where you expect.
ConstraintsPerformance, accessibility, compatibility, review gates, "no new dependencies".
VerificationThe exact command the subagent must run and pass before it returns.
OutputFor example: "report only, no edits", "apply edits with a minimal diff", "list the files changed".

Prefer sequential delegations with explicit carry-over. Parallel runs diverge unless every run gets the same briefing.

Run the subagent in the mode that does the work without asking for approval. Headless mode has nobody to answer a permission prompt. Any mode that stops to ask will stall, or return an empty answer with a success exit code. Each CLI names this mode differently — take the flag from the vendor card below.

Never call a subagent in plan mode. Many CLIs have a plan or read-only mode. That mode makes the other agent write a plan for itself, which is not what you asked for: you want its work or its answer, and you keep the planning. Plan mode also waits for someone to approve that plan, so the run comes back with nothing. If you want no file changes, keep the auto-approving mode and write "report only, no edits" in the Output field. Do not use plan mode to make a run read-only.

After the subagent returns:

  • Report to the user. Give a short summary. Do not paste long logs unless the user asks.
  • Reconcile the context. Record the decisions it made, the files it changed, and the open risks, so this session stays the single source of truth.

CLI failure modes

Every vendor has its own terminal rules. A headless run fails quietly more often than it fails loudly.

  • Wrap the call in an external timeout. A headless CLI can stall before its own timeout starts.
  • Exit code 0 is not success. If stdout is empty, treat the run as failed and read stderr. A permission the CLI could not ask for, and a prompt that never arrived, both look like success.
  • Never carry a flag habit from one CLI to another. The same short flag means different things in different tools. In OpenCode, -p is --password: passing a prompt to it empties the message and the run waits on stdin forever. Confirm every flag against the CLI's own --help.
  • An unrecognized-flag error means this skill is stale, not that the task is impossible. Read --help, continue with the flags that exist, and tell the user which line in this file is wrong.
<!-- ============================================================================= VENDOR HALF — section 6. Everything below is specific to this CLI. Keep all seven sub-headings, in this order, even if the answer is "none". Take every flag from the installed binary (`<cli> --help`), not from memory and not from another skill in this repository. ============================================================================= -->

Vendor card

Binary and prompt form

  • Binary: junie
  • Install: curl -fsSL https://junie.jetbrains.com/install.sh | bash (macOS, Linux). Windows: powershell -NoProfile -Command "iex (irm 'https://junie.jetbrains.com/install.ps1')".
  • Prompt form: positional is the documented headless form: junie --auth="$JUNIE_API_KEY" "prompt text" --model <alias>. A --task <text> flag also exists as an explicit alternative to the positional argument. JetBrains' docs also describe a --prompt flag that opens an interactive session; build 888.212's --help does not list it. Neither way is the headless form — use the positional argument or --task.

Headless and output flags

NeedFlag
Non-interactive runprompt as a positional argument, or --task <text>
Output format--output-format text|json (build 888.212 accepts only these two)
Input format (piped input)--input-format text|json
Save JSON output to a file--json-output-file <path>
Project directory-p, --project <path>
Follow up a previous session--session-id <id>
Time limit in milliseconds-t, --timeout <int>
Skip the startup update check (use in CI)--skip-update-check

JetBrains' parameters page still lists --review, --merge, --rebase, --resume and --output-format json-stream, but build 888.212 does not accept them. Check junie --help before use. There are no chat/review subcommands.

Approvals and permissions

Junie's approval system is Brave Mode, three levels — Off (ask before every sensitive action not already allowlisted; the interactive default), Auto (auto-approve actions it safety-classifies as safe, still ask for risky/unrecognized ones), and On (execute everything, no prompts). It is toggled interactively with /brave or Ctrl+B, and there is a --brave CLI flag — but the docs state it is "Interactive mode only." It cannot be used to force On in a headless/scripted invocation.

This does not leave headless runs blocked. JetBrains' own docs state that non-interactive sessions (a positional prompt, --task, piped input, ACP, or Gateway) "cannot ask for a trust decision, so they are trusted by design" — they load project config (MCP servers, hooks, agents, skills, guidelines) and execute sensitive actions without ever prompting. There is no TTY block and no hang; the documented caveat is simply "only run Junie non-interactively in projects you trust." Fine-grained control below that still exists via the persistent Action Allowlist at ~/.junie/allowlist.json (rules of prefix/pattern + action: allow|ask across fileEditing, executables, mcpTools, readOutsideProject, readSecretFile) — how an ask entry resolves in a non-interactive run specifically is not spelled out verbatim in the docs; treat it as most likely resolving the same "trusted by design" way, but unconfirmed. The /sandbox slash command is documented for development/nightly builds only. Build 888.212 has no --sandbox flag in its help — do not rely on sandboxing.

Models and how to list them

Selection is --model [alias]; aliases are short vendor-neutral tags. There is no separate junie models subcommand — list them with junie --help or the interactive /model slash command.

If the user names a model, use it. Otherwise ask the binary first. For capability and price comparisons, check Artificial Analysis and the vendor's own documentation.

Command pattern

junie --auth="$JUNIE_API_KEY" "GOAL: [goal] | DECISIONS: [decisions] | SCOPE: [paths] | CONSTRAINTS: [constraints] | VERIFICATION: [test_command] | OUTPUT: [format]" \
  --model <alias> --output-format text --skip-update-check 2>&1

Prompt examples

  • Implement: junie --auth="$JUNIE_API_KEY" "GOAL: [goal] | DECISIONS: [decisions] | SCOPE: [paths] | VERIFICATION: [test_command] | OUTPUT: [format]" --model <alias>
  • Code review (report only): junie --auth="$JUNIE_API_KEY" "GOAL: Review my changes for [concerns] | SCOPE: [paths] | CONSTRAINTS: do not edit any file | OUTPUT: review report" --skip-update-check
  • Investigate with a time limit: junie --auth="$JUNIE_API_KEY" "GOAL: Map how [feature] works | SCOPE: [paths] | CONSTRAINTS: do not edit any file | OUTPUT: file:line map" --timeout 600000 --skip-update-check

Docs and reference

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free