Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/kirodotdev/kirocrew/artifact-deploynpx skills add kirodotdev/KiroCrew --skill artifact-deploygit clone --depth 1 https://github.com/kirodotdev/KiroCrewWrote 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.
[](https://agentmods.dev/skills/kirodotdev/kirocrew/artifact-deploy)<a href="https://agentmods.dev/skills/kirodotdev/kirocrew/artifact-deploy"><img src="https://agentmods.dev/badge/skills/kirodotdev/kirocrew/artifact-deploy.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00074 | $0.05091 |
| Opus 5 | $0.00037 | $0.02545 |
| Sonnet 5 | $0.00015 | $0.01018 |
| Haiku 4.5 | $0.00007 | $0.00509 |
Grade A, and why
artifact-deploy scanned grade A with 1 finding 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 3d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`curl -d` without `-H application/json`). Calling `json.loads(event["body"])` How it starts
The opening of the file, as written. The whole thing — 357 lines — stays where its author put it; the contents beside it link to each section on GitHub.
KiroCrew One-Click Deploy (MVP)
Shipped by the Artifact Deploy app (
apps/builtins/deploy_web/). Installing the app activates this skill -- that's how the fullstack deploy capability is distributed. The app page (sidebar -> Artifact Deploy) owns AWS profile setup, verification, and the fleet/cost view; this skill is the deploy action.
AWS config -- resolve the profile from the app's registry, don't ask
The Artifact Deploy app owns the AWS configuration as a multi-profile
registry at ~/.kiro/crew/deploy/profiles.json
({"profiles": [{"name", "region", ...}], "default": "<name>"}). Resolve the
deploy profile in this order, before asking the user anything:
- User picked one: if the deploy request names a profile (the artifact
card's dropdown injects
Use the AWS profile "<name>".), use that entry'sname/regionfrom the registry. If the name is not in the registry, stop and send the user to the app page to register it -- never deploy with an unregistered profile name. - Registry default: otherwise use the entry named by
default. - Legacy fallback: if
profiles.jsondoesn't exist, read the old~/.kiro/crew/deploy/config.json (legacy: ~/.kiro/crew/apps/deploy-web/data/config.json)({"profile", "region"}). - Unconfigured (no registry, no legacy profile): do NOT walk the user through manual profile setup in chat -- link them to the app page (sidebar -> Artifact Deploy), which has the Profiles control plane (register / create + Verify access + IAM policy generator). Resume once a profile exists.
After a successful deploy, back-fill webapp_metadata.deploy_target.profile
with the profile NAME actually used, so the fleet table and the artifact's
control card show which identity owns the deployment.
This replaces the old "pick the AWS profile" step: profiles are managed once in
the app, then every deploy (static publish or fullstack webapp) reuses them.
Optionally confirm reachability via the app's verify endpoint
(POST /api/deploy/verify with {"profile": "<name>"} -- an STS
read, no credential access).
What ships with it
20 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- MIGRATION.md 2.5 KB
- scripts/_common.sh 7.6 KB runs code
- scripts/attach_backend.py 17 KB runs code
- scripts/cost.sh 7.8 KB runs code
- scripts/deploy-app.sh 2.2 KB runs code
- scripts/deploy-backend.sh 7.6 KB runs code
- scripts/deploy.sh 13 KB runs code
- scripts/detach_backend.py 6.0 KB runs code
- scripts/install-reaper.sh 4.0 KB runs code
- scripts/list.sh 1.8 KB runs code
- scripts/persist.sh 1.3 KB runs code
- scripts/reaper_lambda/index.py 29 KB runs code
- scripts/reaper.sh 15 KB runs code
- scripts/teardown.sh 3.0 KB runs code
- templates/app-apigw-ddb.yaml 10 KB
- templates/app-apigw.yaml 9.1 KB
- templates/app-lambda.yaml 2.7 KB
- templates/base-stack.yaml 17 KB
- templates/handler-example.py 2.2 KB runs code
- templates/reaper.yaml 11 KB
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.
- 3d ago First seen · 357 lines · 74 tokens per session scan A 816dad7a837c
artifact-deploy is a skill published in the GitHub repository kirodotdev/KiroCrew (3,532 stars, last pushed yesterday), licensed Apache-2.0. It adds 74 tokens to every session and 5,091 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
reskin
Author a NEW skin for the reskinnable-demo app. A skin is a self-contained domain plugin under src/skins/ / that implements the frozen Skin contract (src/shell/skin-contract.ts) to swap the app's entire experience — brand, theme, layout, pages, tools, data, and agent — as a live sales demo. Use when the user says "add…
setup-slack-channel
Use for the PROVIDER half of getting a locally running CopilotKit Channels agent to answer in Slack, when no Slack app exists yet — setting up a Channels bot in Slack for the first time, creating the Slack app and its tokens, attaching it to a managed Intelligence Channel, or when a Channel reports setuprequired, sits…
copilotkit-channels
Use for the CODE half of a managed Intelligence Channel with Slack or Microsoft Teams: customising the Channel a CLI-scaffolded project already ships, or — for a project the CLI did not generate — writing the Channel declaration, the long-running host, and the awaited activation call. Teams provider setup is in scope…
runtime
@copilotkit/runtime — mount a fetch-native CopilotRuntime on any JS server, wire middleware, pick an AgentRunner, instantiate BuiltInAgent (Factory Mode with TanStack AI is the preferred default) or plug in any of 12 external agent frameworks (Mastra, LangGraph, CrewAI Crews/Flows, PydanticAI, ADK, LlamaIndex, Agno…
copilotkit-integrations
Use when wiring an external agent framework (LangGraph, CrewAI, PydanticAI, Mastra, ADK, LlamaIndex, Agno, Strands, Microsoft Agent Framework, or others) into a CopilotKit application via the AG-UI protocol.
a2ui-renderer
Render A2UI (Agent-to-UI declarative surfaces) in CopilotKit v2. Enable the runtime via CopilotRuntime({ a2ui: {...} }), then enable the provider via . Auto-activates via /info — do NOT manually pass renderActivityMessages. createA2UIMessageRenderer ships from @copilotkit/react-core/v2; low-level primitives…