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 agentmods add skills/kirodotdev/kirocrew/five-whysnpx skills add kirodotdev/KiroCrew --skill five-whysgit 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/five-whys)<a href="https://agentmods.dev/skills/kirodotdev/kirocrew/five-whys"><img src="https://agentmods.dev/badge/skills/kirodotdev/kirocrew/five-whys.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 | $0.00088 | $0.04373 |
| Opus 5 | $0.00044 | $0.02187 |
| Sonnet 5 | $0.00018 | $0.00875 |
| Haiku 4.5 | $0.00009 | $0.00437 |
Grade A, and why
five-whys 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 5d 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 — 278 lines — stays where its author put it; the contents beside it link to each section on GitHub.
5 Whys — guided dive-deep MODE
This is a mode, not a one-shot answer — once triggered you enter it and stay in it across turns until the user is satisfied or exits. Its purpose is to help someone understand something deeply: a bug, an incident, a system, a concept, or a decision. It works by asking one focused question at a time, keeping every answer short and direct, and branching — so understanding is verified at each step and the exploration reaches the real root.
The engine of the mode: every step is one append to an event log; the tree, the current question, the open branches and the final report are all folded from that one log — never maintained by hand. 5 Whys is the default engine of a small research method built on that log; more capabilities (web search, recap, ...) plug into the same log — see Capabilities below.
The core loop (this is the whole mode)
Each turn does exactly one of these, then stops and waits:
- Answer the current question — short and direct (see disciplines below).
- Propose the next layer: 2-4 candidate branch questions about the answer you just gave. Each is a single, direct "why...?" / "how...?" / "what causes...?" — the obvious next things to dig into.
- Let the user steer. They can (a) pick one of your proposed questions, (b) pick several (each becomes a branch), or (c) type their own question — which becomes a new branch just the same. Never force your menu; the user's own question always wins.
- Append the events for what happened (an
ask, ananswer, afocusmove...) to the log viascripts/five_whys.py(see The mechanical core), then repeat.
So branches form naturally: every answer sprouts a small menu, the user follows one thread deep, and the unpicked questions wait as branches to return to.
The reasoning chain (the spine of every dive)
Peeling a thing apart should follow one basic chain of thought. Let it order the answers you give and the branch questions you propose, so the exploration always moves from grasping the thing to judging it:
What ships with it
1 file 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.
- 5d ago First seen · 278 lines · 88 tokens per session scan A 2f4e2ca93e20
five-whys is a skill published in the GitHub repository kirodotdev/KiroCrew (3,532 stars, last pushed 2d ago), licensed Apache-2.0. It adds 88 tokens to every session and 4,373 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
kodama-verification
Define measurable success criteria and collect targeted test, build, lint, type-check, or smoke-test evidence before claiming work is complete.
kodama-behavior
Classify requests, assess unfamiliar codebases, delegate work safely, and recover from failed attempts. Use for multi-step, ambiguous, or parallelizable work.
kodama-constraints
Enforce non-negotiable safety, scope, security, and quality constraints for implementation and review work.
project-release-check
Validate this example project's release readiness. Use before publishing a release candidate.
aatmf-t10-confidentiality-breach
AATMF T10 — Integrity & Confidentiality Breach. System prompt extraction, training-data extraction, model-weight leakage, private-key recovery.
sidewinder-rattlesnake
Adversary-emulation profile for SideWinder (G0121 / Rattlesnake / T-APT-04 / Razor Tiger), India's suspected state-sponsored cyber-espionage actor.