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/rubber-ducknpx skills add kirodotdev/KiroCrew --skill rubber-duckgit 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/rubber-duck)<a href="https://agentmods.dev/skills/kirodotdev/kirocrew/rubber-duck"><img src="https://agentmods.dev/badge/skills/kirodotdev/kirocrew/rubber-duck.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 5.1 | $0.00161 | $0.02252 |
| Opus 5 | $0.00081 | $0.01126 |
| Sonnet 5 | $0.00032 | $0.00450 |
| Haiku 4.5 | $0.00016 | $0.00225 |
Grade A, and why
rubber-duck 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 6d 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 — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rubber Duck Review
Overview
The classic debugging trope, aimed at hallucination. The main session is the Presenter — it did the work and holds the real reasoning (including the hedges it never wrote down). It reconstructs the topic out loud, in its own words, to a Listener: a spawned subagent pinned to a different-vendor model that has NOT seen the reasoning and interrogates it adversarially. Two forces do the work:
- The Feynman effect — reconstructing the argument from scratch surfaces the Presenter's own hand-waving before the Listener even replies.
- An unstaked skeptic — the Listener has no investment in the conclusion, so it catches what the artifact's own self-review rationalized past.
This is a dialogue, not a static-artifact review: the Presenter reconstructs the argument live, and the divergence between the reconstruction and the written artifact is itself a finding.
When to use / when NOT
Use before shipping a findings doc, design, RCA, or investigation you want to be honest — anything where a "confirmed" might be hiding an unproven leap, or a magnitude might be hand-waved. Do NOT use for simple lookups or routine turns: it costs one+ extra model run per round and real Presenter effort. A deliberate, occasional move.
Roles
- Presenter — you, the main session. Reconstructs the topic from understanding (NOT copy-paste), answers the Listener's probes honestly, builds the reconciliation ledger. Ideal: reconstruct before re-reading the artifact, so the divergence between what you believe and what you wrote is genuine; at minimum, articulate in your own words rather than pasting the doc.
- Listener — a spawned subagent. Cross-vendor, large-window, lean. Sees the Presenter's explanation plus the original user request (the ask, for grounding — not the artifact or the reasoning), so it attacks the claims as articulated, which is what exposes explanation-vs-artifact drift. Residual gap: a self-consistent fabrication the Presenter also grounds falsely can survive — the blind Listener bounds overclaim and inconsistency, not a mutually-consistent hallucination.
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.
- 6d ago First seen · 154 lines · 161 tokens per session scan A 014c12bcd98d
rubber-duck is a skill published in the GitHub repository kirodotdev/KiroCrew (3,667 stars, last pushed today), licensed Apache-2.0. It adds 161 tokens to every session and 2,252 once invoked, about $0.0008 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
debugging-websocket-issues
Use when seeing WebSocket errors like "Invalid frame header", "RSV1 must be clear", or "WSERRUNEXPECTEDRSV1" - covers multiple WebSocketServer conflicts, compression issues, and raw frame debugging techniques.
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
simplify-code
Sequential 3-lens cleanup of recent code changes.
python-debugpy
Debug Python: pdb REPL + debugpy remote (DAP).
node-inspect-debugger
Debug Node.js via --inspect + Chrome DevTools Protocol.
rn-debugging
This skill should be used when the user asks to "debug the app", "fix a crash", "diagnose a blank screen", "read error logs", "troubleshoot CDP connection", "check Metro status", "find native crashes", "inspect network failures", "the app crashed", "I see a blank screen", "the screen is white", "something broke", "app…