A command that sends an implementation task to the Kiro command-line tool, then reviews the changes it produces. Headless mode means the tool runs without an interactive browser or terminal session.

Use it for specification-driven coding tasks, AWS-related work, read-only code investigation, and reviewing Kiro's resulting diff.

It lets another coding agent handle a defined task while requiring a separate review of the resulting code changes. A read-only option prevents edits during the delegated run.

kiro — Command for Claude Code by pwdev-solucoes

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code

/plugin marketplace add pwdev-solucoes/pwdev-claude-marketplace

Claude Code

/plugin install pwdev-code

Made for: Claude Code.

Or install pwdev-code, the plugin that ships this one along with the rest of its 2 skills, 22 commands, 8 agents, 6 hooks.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/commands/pwdev-solucoes/pwdev-claude-marketplace/kiro/github.svg)](https://agentmods.dev/commands/pwdev-solucoes/pwdev-claude-marketplace/kiro)

Your own site

<a href="https://agentmods.dev/commands/pwdev-solucoes/pwdev-claude-marketplace/kiro"><img src="https://agentmods.dev/badge/commands/pwdev-solucoes/pwdev-claude-marketplace/kiro/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/commands/pwdev-solucoes/pwdev-claude-marketplace/kiro"><img src="https://agentmods.dev/badge/commands/pwdev-solucoes/pwdev-claude-marketplace/kiro.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,007 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00022	$0.01007
Opus 5	$0.00011	$0.00504
Sonnet 5	$0.00004	$0.00201
Haiku 4.5	$0.00002	$0.00101

Measured 9d ago against content hash d54df6c5cf2c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

kiro scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/pwdev-code/commands/kiro.md · 90 lines

How it starts

The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/pwdev-code:kiro — Delegate to Kiro CLI

Role

Orchestrator: sends the task to the external Kiro CLI (headless mode) via the standardized delegation script, then performs a MANDATORY critical review. Best for: agentic/spec-driven implementation and AWS-stack tasks. Protocol details: ${CLAUDE_PLUGIN_ROOT}/references/delegation.md

CLI notes

Binary: kiro-cli — invoked as kiro-cli chat --no-interactive "<prompt>".
In write mode the script adds --trust-all-tools (required for Kiro to edit files headlessly). In read mode it is omitted: read-only tools are trusted by default and mutations get rejected — a natural read-only guard.
Headless auth: set KIRO_API_KEY to skip the browser login flow (docs: https://kiro.dev/docs/cli/headless/).

Input

$ARGUMENTS: the task description. --read-only → MODE=read (default: write).

Flow

STEP 0 — Language

Follow ${CLAUDE_PLUGIN_ROOT}/references/language.md (resolve lang from .planning/config.json; ask only if unset).

STEP 1 — Preflight

Parse $ARGUMENTS: strip --read-only (→ MODE=read); the remainder is the task. Empty task → show usage and STOP.
git status --porcelain — if the tree is dirty in write mode, warn the user that delegation results will be hard to attribute; offer to continue or abort.
Record baseline: git rev-parse HEAD and git status --short.

STEP 2 — Human Confirmation (same rule as review.md STEP 3.5)

Show the EXACT command that will run:

"${CLAUDE_PLUGIN_ROOT}/scripts/run-agent.sh" kiro <write|read> "<task>"

If this is the FIRST external CLI run in this session → require explicit confirmation before executing. Never proceed silently.

STEP 3 — Run

Execute the command via Bash with a tool timeout ≥ the script timeout + 60s (default 600s; agentic runs are slow — consider external_models.kiro.timeout_s: 900).

exit 127 → Kiro CLI not installed (official installer at https://kiro.dev, then authenticate once or set KIRO_API_KEY); STOP.
exit 124 → report the timeout; suggest raising external_models.kiro.timeout_s.
exit 4 → another write delegation is running; wait for it.
Output copy (when .planning/ exists): .planning/delegation/<ts>-kiro.md

Read the full file on GitHub · 90 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

9d ago First seen · 90 lines · 22 tokens per session scan A d54df6c5cf2c

Subscribe to this mod's changes

kiro is a command published in the GitHub repository pwdev-solucoes/pwdev-claude-marketplace (2 stars, last pushed 3d ago), licensed Apache-2.0. It adds 22 tokens to every session and 1,007 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Building agents Code review

kiro

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

/pwdev-code:kiro — Delegate to Kiro CLI

Role

CLI notes

Input

Flow

STEP 0 — Language

STEP 1 — Preflight

STEP 2 — Human Confirmation (same rule as review.md STEP 3.5)

STEP 3 — Run

What this file has done since we first saw it

Other commands, from other repositories

sdd-init

review-branch

init

merge-conflict-analysis

repo-audit

argos