Kiro Crew is a persistent development workspace where agents continue multi-step software work across sessions, schedules, and connected interfaces. Developers use it locally or remotely through a desktop app, web dashboard, CLI, Slack, or Discord, with unattended tasks and recurring jobs. The catalogue contains skills and instructions for working with this workspace.
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 skills add kirodotdev/KiroCrew --skill dashboard-templategit 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/dashboard-template)<a href="https://agentmods.dev/skills/kirodotdev/kirocrew/dashboard-template"><img src="https://agentmods.dev/badge/skills/kirodotdev/kirocrew/dashboard-template/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.
<a href="https://agentmods.dev/skills/kirodotdev/kirocrew/dashboard-template"><img src="https://agentmods.dev/badge/skills/kirodotdev/kirocrew/dashboard-template.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00068 | $0.03890 |
| Opus 5.5 | $0.00027 | $0.01556 |
| Sonnet 5.5 | $0.00014 | $0.00778 |
| Haiku 4.5 | $0.00007 | $0.00389 |
Grade A, and why
dashboard-template 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 270 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dashboard Template
A dashboard page is HALF of a template. The other half is a type, and the two halves are checked by different machines, which is why they drift.
This skill is the procedure for the
kirocrew-dashboard-authorcrewmate, whose spec isagent-spec.mdbeside this file: the charter (what it is for and what it may never do) plus the narrowed toolset that makes the charter true against a tool list rather than only against prose. A human or another agent following this file gets the same procedure. The gateway installs the spec as the owned agentkirocrew-dashboard-authorat every start (OWNED_KIRO_AGENT_FILES,_install_dashboard_author_agent), so a crewmate dispatched on it starts with this procedure as its prompt; a human or another agent loads this skill directly.
The page is inert html. The host sanitizes it, renders it, and binds text into it by
data-dashboard-field. No type checker is anywhere near that binding, because one half
is markup. So a page that reads settled while its provider fills settled_count
renders an empty cell, on a status board, forever, with nothing red anywhere.
Read the host before you write a page; it is short and it is the authority on what gets
refused. src/kiro_crew/dashboard/dynamic_cards.py holds normalize_card, which decides
whether a card is accepted at all, and
website/src/pages/chat/command-center/dashboardDocument.ts is what queries
[data-dashboard-field] and writes the text in.
You are done when four files and one registration line exist, not when the page looks right. Everything here is dev time: it lands through a pull request, mypy is blocking and the parity test is a gate. At run time the gateway evaluates none of it. A publisher supplies three sentences and nothing else.
What a run produces
| # | File | What it is |
|---|---|---|
| 1 | <slug>.html |
the page: inert layout, one data-dashboard-field per value, zero controls |
| 2 | <slug>_contract.py |
the TypedDict naming exactly those fields, plus the judgment type and CONTRACT_VERSION |
| 3 | <slug>_provider.py |
build_<slug>(view, judgment, *, captured_at) whose RETURN TYPE is the contract |
| 4 | test_dashboard_template_<slug>.py |
the parity gate, both directions, plus the planted failures |
| 5 | one line in registry.py |
slug -> (contract, provider, source fold, version) |
What ships with it
4 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.
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.
- 2d ago Changed · +1 lines 77db722a2a49
- 3d ago Changed · +44 lines c84db68f74be
- 6d ago Changed · +4 lines 90bd7839e9d1
- 9d ago Changed · +5 tokens per session d3e9bc42cce6
- 12d ago First seen · 221 lines · 63 tokens per session scan A 9ec268cb5f07
dashboard-template is a skill published in the GitHub repository kirodotdev/KiroCrew (4,402 stars, last pushed today), licensed Apache-2.0. It adds 68 tokens to every session and 3,890 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-02.
Other skills, from other repositories
python-testing
Guidelines for writing and running tests in the Agent Framework Python codebase. Use this when creating, modifying, or running tests.
relay-80-100-workflow
Use when writing agent-relay workflows that must fully validate features end-to-end before merging. Covers the 80-to-100 pattern - going beyond "code compiles" to "feature works, tested E2E locally." Includes repair-before-failure validation gates, review-depth fresh-eyes review/fix loops with test hardening, PGlite…
adk-verify-snippets
Checks that every Python code block in a Markdown file actually compiles and runs, by extracting each block to a temporary file, executing it in an isolated subprocess, and writing a pass/fail report with per-snippet coverage. Use when the user asks to verify, test, or validate the code samples in a README, a guide…
browser-testing-with-screenshots
Use when testing web applications with visual verification - automates Chrome browser interactions, element selection, and screenshot capture for confirming UI functionality.
adk-setup
Sets up a local ADK Python development environment in a git clone of the open-source adk-python repository: a uv virtual environment, all dependency extras, pre-commit hooks, and a first unit-test run. Runs only when explicitly requested, never on its own. Use when asked to set up, bootstrap, or repair a development…
flutter-bloc-state-management
Implement BLoC/Cubit state, events, transitions, and async concurrency in Flutter. Use for BLoC/Cubit feature logic, debounced/cancellable events, state rendering, or bloc tests—not generic widget-only work.