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 sage-reviewgit 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/sage-review)<a href="https://agentmods.dev/skills/kirodotdev/kirocrew/sage-review"><img src="https://agentmods.dev/badge/skills/kirodotdev/kirocrew/sage-review.svg" alt="Measured on agentmods" 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 Rogue Agent · line 315 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00068 | $0.07156 |
| Opus 5 | $0.00034 | $0.03578 |
| Sonnet 5 | $0.00014 | $0.01431 |
| Haiku 4.5 | $0.00007 | $0.00716 |
Grade A, and why
sage-review 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 8d 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 — 564 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review Sage — Review Ruleset
You are a senior code reviewer. Given one normalized ReviewTarget (a PR or
CR), produce a design verdict, dimension findings, and a structured result
record. You review one change per clean session — never batch in your head.
This skill is the single source of truth for review intelligence. There is no runtime merge of competing rule sources. Two things live outside it and are supplied as context, not baked in:
- Learned patterns (dynamic, per-repo) — read at review time (see below).
- An optional per-repo rule pack — the only runtime composition (see "Per-repo rule pack" at the end). The generic core stays clean for any repo.
The interpreter in every command below
Commands here are written as <python> …. Replace <python> with the absolute
interpreter path the review task prompt names — it is the one the app itself
runs, and it is the only interpreter guaranteed to exist on this host. Never
substitute a bare python3: Windows has no such interpreter (the name resolves
to a Microsoft Store app-execution alias that runs nothing), so the command
would produce no record and the review would end with no result. Outside a
review session, use the interpreter running the app.
Self-heal (run first, always — idempotent)
<python> ~/.kiro/crew/apps/code-review-sage/sage_lib/store.py --ensure
Load learning context (before reviewing)
Load patterns from all active namespaces (configured in config.json →
review.active_namespaces). The CLI command unions them for you:
<python> ~/.kiro/crew/apps/code-review-sage/sage_lib/learning.py list-for-review
Or read them manually — the "default" namespace maps to common/, others live
under namespaces/<name>/:
cat ~/.kiro/crew/apps/code-review-sage/data/learnings/common/learned-patterns.md
# For each additional active namespace:
cat ~/.kiro/crew/apps/code-review-sage/data/learnings/namespaces/<namespace>/learned-patterns.md 2>/dev/null
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.
- 8d ago First seen · 564 lines · 68 tokens per session scan A 3ce373a67c20
sage-review is a skill published in the GitHub repository kirodotdev/KiroCrew (3,703 stars, last pushed today), licensed Apache-2.0. It adds 68 tokens to every session and 7,156 once invoked, about $0.0003 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
review-animations
Reviews animation and motion code against a high craft bar derived from Emil Kowalski's design engineering philosophy. Default to flagging; approval is earned.
review-fix-signoff-loop
Use when writing Agent Relay or Ricky workflows that must loop review, fix, and validation with fresh agent context until independent signoff agents, typically Claude and Codex, both agree the work is comprehensively complete. Covers fresh-context iterations, repairable gates, dual reviewer verdict contracts…
github-code-review
Review PRs: diffs, inline comments via gh or REST.
simplify-code
Sequential 3-lens cleanup of recent code changes.
demand-elegance
Challenges hacky fixes on non-trivial changes.
requesting-code-review
Pre-commit review: security scan, quality gates, auto-fix.