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 ai-discovergit 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/ai-discover)<a href="https://agentmods.dev/skills/kirodotdev/kirocrew/ai-discover"><img src="https://agentmods.dev/badge/skills/kirodotdev/kirocrew/ai-discover/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/ai-discover"><img src="https://agentmods.dev/badge/skills/kirodotdev/kirocrew/ai-discover.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 3 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00083 | $0.00732 |
| Opus 5.5 | $0.00033 | $0.00293 |
| Sonnet 5.5 | $0.00017 | $0.00146 |
| Haiku 4.5 | $0.00008 | $0.00073 |
Grade A, and why
ai-discover 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 13d 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ai-discover — the discovery step of the auto-improvement loop
This skill drives Phase A (discovery) of an auto-improvement cycle. It is discovery only: it never applies a change, never runs the keep-or-revert A/B, and never decides whether a finding is kept or drafted as a pull request. Those are the spine's deterministic Python gate / keeper / pipeline, which no model can argue past. That separation is the point — the measurement is the product.
How discovery actually runs
The spine runs discovery as ONE bounded agent turn per cycle
(spine/agent_discovery.py discover_surfaces_via_agent), not a fan-out. Do
NOT spawn subagents: the turn must end with the JSON array itself, and children
spawned from an unattended runner orphan and hang the run (see the
SessionAgentRunner notes in spine/agent_runner.py).
- Tools are Read, Grep and Glob only. There is no shell and no edit: discovery is read-only by capability, so you cannot run a profiler or write a test here.
- Read the priority slice you are given, stop after 2-3 solid findings or the
read budget, and reply with ONLY a JSON array (at most the stated limit) of
{file, line, symbol, rule, message, hypothesis}—ruleisAGENT, orCOVERAGEfor a coverage gap. Reply[]when nothing is testable. The final reply IS the output; there is no separate artifact file. - The same surface shape feeds both tracks. On the bug track the profile names
the reproducing test path and
author_bug_fixlater writes the RED test and the fix in an isolated worktree; on the perf trackauthor_perf_fixwrites the edit. The spine dedups by(kind, basename::symbol)locus, then gates (RED -> GREEN -> STAYGREEN for bugs, serial pinned A/B for perf).
Reporting a candidate honestly
State the expected win as a hypothesis, not a result. The spine measures it; if your estimate was wrong the candidate is reverted and that is a normal, useful outcome. A guess presented as a measurement is the failure mode this whole app exists to prevent.
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.
- 13d ago Changed · +8 tokens per session 3a12dc44d6b1
- 1mo ago First seen · 53 lines · 75 tokens per session scan A 4eb65ed33cb0
ai-discover is a skill published in the GitHub repository kirodotdev/KiroCrew (4,518 stars, last pushed today), licensed Apache-2.0. It adds 83 tokens to every session and 732 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 2026-08-30.
Other skills, from other repositories
ios-simulator
Verify and debug native, React Native, Expo, or Flutter apps on an iOS Simulator with agent-device. Use when an agent needs to launch an app, inspect its live UI, tap, type, scroll, validate a code change, collect failure evidence, or reproduce a workflow on an iPhone or iPad Simulator.
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…
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.
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.
arxiv-agentic-verifier
Source Paper: Scaling Agentic Verifier for Competitive Coding (ID: 4a4c4dae6a5145ebc4d62eb2d64b0f0f) Type: Code Verification / Test Generation.
rn-testing
This skill should be used when the user asks to "write a Maestro test", "create E2E flows", "add testIDs", "run UI tests", "run E2E tests", "verify a feature works", "test my screen", "set up maestro-runner", "mock network requests", "inspect store state", "write test assertions", or needs guidance on test timing…