amirkiarafieiamirkiarafiei/subagent-cli-skills/skills/kiro-cli/SKILL.md

kiro-cli

Skill14 starsChanged 10 days agoMITView on GitHub

Use Kiro CLI as a subagent. Lets the main agent prompt Kiro CLI from the terminal in headless mode with the `kiro-cli` command, and send the goal, the decisions and the scope with the task. Use when the user asks to delegate work to Kiro 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

In this repository24 other files it gives its agents.
- antigravity-cliSkill
- claude-codeSkill
- cline-cliSkill
- codex-cliSkill
- copilot-cliSkill
- cursor-cliSkill
- deepagents-codeSkill
- devin-cliSkill
- gemini-cliSkill
- goose-cliSkill
- grok-cliSkill
- hermes-agentSkill
- junie-cliSkill
- kilocode-cliSkill
- kimi-codeSkill
- mistral-vibeSkill
- oh-my-piSkill
- openclaw-cliSkill
- opencode-cliSkill
- openhands-cliSkill
- pi-cliSkill
- qoder-cliSkill
- qwen-codeSkill
- <skill-name>Skill

The file

We split this skill into the rules it gives an agent

11 rules. About 0 are common, 8 are distinctive, and 3 are very specific to this project.

≈0
Common · estimate
Many files like this have a rule of this kind.
≈8
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Distinctive:
Secrets or policy-sensitive work: Do not pipe credentials into a subagent.
line 48
Distinctive:
Low return on investment: If writing the handoff costs more than doing the edit, do the edit.
line 50
Distinctive:
Treat every call as stateless delegation: the subagent keeps nothing between calls, so each command must carry its own state.
line 61
Distinctive:
Write the prompt as a transfer of shared state, not as a title.
line 71
Distinctive:
Prefer sequential delegations with explicit carry-over.
line 82
Distinctive:
After the subagent returns:
line 96
Distinctive:
Every vendor has its own terminal rules.
line 104
Distinctive:
Exit code 0 is not success: If stdout is empty, treat the run as failed and read stderr.
line 108
Very specific:
Keep all seven sub-headings, in this order, even if the answer is "none".
line 119
Very specific:
Run kiro-cli chat --list-models (add --format json for machine-readable output).
line 167
Very specific:
If the user names a model, use it.
line 171

≈ “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

Kiro 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:

Include	Why
Goal	The same objective as the user, not only the immediate micro-task.
Decisions	Framework, patterns, naming, "use X not Y" — anything that would otherwise be guessed wrong.
Scope	The absolute paths and modules to touch, and the areas to leave alone. A relative path may not resolve where you expect.
Constraints	Performance, accessibility, compatibility, review gates, "no new dependencies".
Verification	The exact command the subagent must run and pass before it returns.
Output	For 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

Note: AWS has moved Kiro CLI's authoritative docs to kiro.dev/docs; docs.aws.amazon.com now mostly hosts a migration notice pointing there (the Amazon Q Developer CLI → Kiro CLI rename took effect 2025-11-17).

Binary and prompt form

Binary: kiro-cli
Install: curl -fsSL https://cli.kiro.dev/install | bash. The docs list no Homebrew or npm option.
Auth for headless runs: set the KIRO_API_KEY environment variable. The docs say headless mode requires it. API keys need a paid tier.
Prompt form: positional, on the chat --no-interactive subcommand: kiro-cli chat --no-interactive "prompt". Reference a file directly with @path — no space after the @ (e.g. @src/auth.rs, @./relative/path, @"path with spaces.txt", @dir/ for a directory tree). Tab-completion is supported; the content is expanded inline before sending, not fetched via a tool call.

Headless and output flags

Need	Flag
Run once and exit	`chat --no-interactive "prompt"`
List available models	`chat --list-models` (supports `--format json`)
Pick the agent harness	`--v2`, `--v3`, or `--agent-engine <v1\|v2\|v3>`. CLI 3.0.0 and later start V3 by default when no harness is named.
Machine-readable output	`--output-format stream-json` (JSON Lines on stdout). Needs V2 or V3, so add `--v3`. Plain text is the default.
Fail if MCP servers don't come up	`--require-mcp-startup` — exits with code 3 if MCP servers don't start or report status within a 30-second window; without the flag, startup problems are only logged and execution continues

Example from the docs: kiro-cli chat --v3 --no-interactive --trust-all-tools --output-format stream-json "...".

Approvals and permissions

--trust-all-tools auto-approves all tool calls without prompting — the docs explicitly flag that this includes arbitrary shell execution ("use with caution"). --trust-tools=<comma-list> grants granular auto-approval instead, and the docs recommend it in headless V3. Non-interactive V3 matches exact internal tool IDs; the docs example is --trust-tools=read_file,grep_search. CLI 2.x accepts its own tool names. --trust-tools cannot approve a Hook request.

Without a trust flag, the docs say a V3 sub-agent's tool call is denied with "[denied] tool permission approval is not supported in non-interactive mode. Use --trust-all-tools to auto-approve." A Hook confirmation is also denied without --trust-all-tools. The docs do not spell out the general case for the main agent, so pass an explicit trust flag rather than rely on it.

Models and how to list them

Run kiro-cli chat --list-models (add --format json for machine-readable output). Selection is --model <alias> on chat. A chat.defaultModel setting is mentioned in the docs only as a value --model overrides; setting it with kiro-cli settings chat.defaultModel <alias> is unverified.

If the user names a model, use it. Otherwise ask the binary first. Kiro bills by a credit-based subscription (Free/Pro/Pro+/Pro Max/Power tiers, each with a monthly credit allotment; add-on credits and overage both bill at a flat per-credit rate) and gates newer/premium models behind a paid tier — the Free tier gets a baseline model plus open-weight models only. Check Artificial Analysis and the vendor's own pricing docs before assuming availability or cost for a given model.

Built-in agents, selectable via --agent "<name>" (list with kiro-cli agent list): Default (general-purpose, all tools — the one to use for delegation), Spec (structured feature development with approval gates), Quick Spec (auto-generates all phases, no gates), Bug Fix (structured bug investigation/resolution). Do not select Plan (explores and produces a plan; cannot write files or execute commands — read-only by design) or Guide/Help (CLI-only, documentation-grounded Q&A over an indexed-docs tool, not general coding agents) for headless delegation — none of the three can do real work. Users can also define custom agents (kiro-cli agent create|edit|validate|migrate|set-default).

Command pattern

kiro-cli chat --no-interactive "GOAL: [goal] | DECISIONS: [decisions] | SCOPE: [paths] | CONSTRAINTS: [constraints] | VERIFICATION: [test_command] | OUTPUT: [format]" \
  --trust-all-tools --v3 --model <alias> 2>&1

Prompt examples

Implement: kiro-cli chat --no-interactive "GOAL: [goal] | DECISIONS: [decisions] | SCOPE: [paths] | VERIFICATION: [test_command] | OUTPUT: [format]" --trust-all-tools
Investigate: kiro-cli chat --no-interactive "GOAL: Map how [feature] works | SCOPE: [paths] | OUTPUT: concise file:line map" --agent "Default" --v3 --trust-tools=read_file,grep_search
Refactor: kiro-cli chat --no-interactive "GOAL: Refactor [area] for better performance | SCOPE: [paths] | VERIFICATION: [test_command] | OUTPUT: summary of edits" --trust-all-tools

Docs and reference

Delegation checklist, agent/model tables, config paths: reference.md
Vendor documentation: https://kiro.dev/docs/cli/headless/ and https://kiro.dev/docs/reference/cli-commands/
Checked against the official Kiro (kiro.dev) documentation on 2026-11-05; not run against an installed binary. The docs describe CLI 3.0.0 or later. kiro-cli is not installed here (the local kiro command is the IDE launcher). Confirm with kiro-cli --help before trusting a flag. The 30-second MCP window, the built-in agent list and the billing figures are unverified.

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