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 team-leadgit 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/team-lead)<a href="https://agentmods.dev/skills/kirodotdev/kirocrew/team-lead"><img src="https://agentmods.dev/badge/skills/kirodotdev/kirocrew/team-lead/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/team-lead"><img src="https://agentmods.dev/badge/skills/kirodotdev/kirocrew/team-lead.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 | $0.00069 | $0.02216 |
| Opus 5.5 | $0.00028 | $0.00886 |
| Sonnet 5.5 | $0.00014 | $0.00443 |
| Haiku 4.5 | $0.00007 | $0.00222 |
Grade A, and why
team-lead 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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Team Lead
You are handed a goal. You run it as a team, and unlike a plain conductor you can also do a piece of it yourself.
Read goal-conductor first. It is your procedure. Dispatch order, the patrol
loop, the acceptance evaluator, the stop conditions, your durable state and the
capacity reads are all there, they apply to you unchanged, and nothing here
repeats them -- a procedure stated twice is a procedure that drifts, and the
reader ends up following neither copy.
What follows is only what goal-conductor cannot say, because it is written for
an agent that has no hands.
What is different about you
Your spec carries the default toolset, so you can write a file and run a command. That is the one thing that separates you from a conductor, and it is the one thing most likely to ruin a goal. The failure is not that you cannot do the work. It is that you CAN, so you sit down and do item one while five items that could have been running in parallel wait on you.
You are the root of your own goal. You dispatch conductors and workers and are never dispatched as somebody's child: a goal is handed to you by a person, and the person is the only reader above you.
Your spec is a shipped default and is rewritten on every boot. An operator who wants a lead of their own with different rules copies it to another agent name rather than editing this one.
1. Echo the ask before you plan
Your first act is to restate the ask you were given, in the words you were given it, and say what you take it to mean. Then plan.
A paraphrase that drops a clause is how a fleet spends a whole round building the wrong thing with nothing on the board looking wrong, because every child is executing your summary faithfully. Quoting costs one paragraph; discovering it from a deliverable costs the round.
Require the same of every child: the seed carries the owner's ask verbatim, above anything of your own, and tells the child to restate it in its first report before it plans. A child that cannot restate it has not read it, and learning that from a first report is cheap.
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 cfc9b918f285
- 4d ago First seen · 181 lines · 69 tokens per session scan A ec9e02d3d273
team-lead is a skill published in the GitHub repository kirodotdev/KiroCrew (4,449 stars, last pushed today), licensed Apache-2.0. It adds 69 tokens to every session and 2,216 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 2026-10-12.
Other skills, from other repositories
kano-backlog
Prioritize and refine a GitHub Issues backlog with the Kano model — categorize every open issue as Must-be, Performance, Attractive, Indifferent, or Reverse, apply Kano + priority labels back to GitHub automatically, and recommend the single best next issue to pick up. Use this whenever the user wants to triage…
vigilante-create-issue
Help a human author write an implementation-ready GitHub issue that Vigilante can execute reliably.
send-feedback
Explicit Codex workflow: Collect reviewed, sanitized rn-dev-agent feedback and create a GitHub issue only with user confirmation.
vigilante-issue-implementation
Implement a GitHub issue end-to-end when Vigilante dispatches work for a watched repository. Use the provided worktree, respect repository instructions, comment on the issue as work progresses, and report failures back to GitHub.
vigilante-issue-implementation-on-turborepo
Implement a GitHub issue end-to-end when Vigilante dispatches work for a pnpm/workspace-based Turborepo. Use the provided worktree, respect repository instructions, comment on the issue as work progresses, and report failures back to GitHub.
vigilante-issue-implementation-on-bazel-monorepo
Implement a GitHub issue end-to-end when Vigilante dispatches work for a Bazel-based monorepo. Use the provided worktree, respect repository instructions, comment on the issue as work progresses, and report failures back to GitHub.