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 explain-forgit 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/explain-for)<a href="https://agentmods.dev/skills/kirodotdev/kirocrew/explain-for"><img src="https://agentmods.dev/badge/skills/kirodotdev/kirocrew/explain-for/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/explain-for"><img src="https://agentmods.dev/badge/skills/kirodotdev/kirocrew/explain-for.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00071 | $0.03403 |
| Opus 5.5 | $0.00028 | $0.01361 |
| Sonnet 5.5 | $0.00014 | $0.00681 |
| Haiku 4.5 | $0.00007 | $0.00340 |
Grade A, and why
explain-for 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 11d 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 — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.
explain-for — write it for one named audience
One explanation cannot serve everyone. This skill makes you name the audience first, verify the facts second, and only then write.
Step 0 — check that this is actually an audience request
You reach this skill from its index entry, or — when skills.max_triggered is
above its default of 0 — from word-overlap against the trigger phrases above.
Either route is probabilistic and will sometimes land on a request that merely
contains the word "explain". Before entering the skill, confirm the user wants
an explanation pitched at somebody. If they just want to know why CI
failed, answer that question normally and ignore everything below.
Step 1 — resolve the audience
Pick exactly one audience.
Check memory before guessing. Crew carries a persistent user profile, and a request like "explain this to my daughter" or "break this down for Priya" often resolves against something already recorded — an age, a role, an interest. Search memory and lessons for that person and use what is there; guessing an age the profile already contradicts is the most visible way this skill fails.
If nothing resolves and no audience is named, do not silently invent one:
- Explicit smallest-audience phrasing ("dumb it down", "explain like I am") means Age 5. That is the request.
- Anything else with no audience — ask which audience in one line, or state the row you assumed in one clause so the user can correct it.
If the request names someone you cannot classify (a specific colleague, a title absent from the tables), map them onto the nearest row and say which row.
Ages
| Audience | Calibration |
|---|---|
| Age 5 | Smallest words. Analogies from toys, animals, candy, playground. One idea per sentence. |
| Age 10 | Elementary. Cause-and-effect is fine. Analogies from school, sports, video games. |
| Age 15 | Some abstraction is fine. Analogies from phones, games, social apps. Casual, never try-hard. |
| Age 20-30 | Direct and clear. Analogies from work, money, daily logistics. |
| Age 40+ | Respectful, unhurried. Analogies from home ownership, career, running a household. |
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.
- 11d ago Changed · +1 lines a3467a0089b3
- 29d ago Changed · -31 tokens per session b3b72ddb659b
- 1mo ago Changed · +1 lines 80c79b8dee35
- 1mo ago Changed · +2 lines a9828d0310f1
- 1mo ago Changed · +1 lines c7d77a2bd6e0
- 1mo ago Changed · +4 lines 1456b5e14a5f
- 1mo ago First seen · 263 lines · 102 tokens per session scan A 78359d37b7a9
explain-for is a skill published in the GitHub repository kirodotdev/KiroCrew (4,481 stars, last pushed today), licensed Apache-2.0. It adds 71 tokens to every session and 3,403 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 2026-09-02.
Other skills, from other repositories
cost-efficiency-analyzer
Analyzes cost structure, cost efficiency, and expense management from P&L data. Use when the user asks about costs, expenses, COGS, operating expenses, cost ratios, cost control, spending efficiency, margin compression from cost side, or wants to understand where money is going. Also use for "are we spending too…
sector-rotation
Identify which market sectors to overweight or underweight based on current macro conditions and sector performance data.
trend-analysis
Analyze price and volume trends for one or more stocks to determine momentum direction and key technical levels.
deploying-to-staging-environment
Use when deploying changes to staging across relay, relay-dashboard, and relay-cloud repos - coordinates multi-repo branch syncing using git worktrees, automatically triggers staging deployments via GitHub Actions.
writing-relayflows
Use when authoring a Relayflows flow (@relayflows/surface / @relayflows/sdk, the journal-based v2 engine — the CLI is flows, package versions 2.0.x) in TypeScript or YAML/JSON. Covers the three-rung ladder (run/llm/agent), the resident verbs (human/dispatch/done), verification gates, TypeScript vs YAML authoring…
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.