kirocrew-worktree-dev

kirocrew-worktree-dev is a skill for Claude Code, Codex from kirodotdev/KiroCrew. It costs 123 tokens per session (6,051 once invoked), scanned C, original, Apache-2.0.

A development guide for changing the Kiro Crew source code in a separate Git worktree. A worktree is an additional working copy of a repository, and the guide includes required checks for backend and frontend changes.

In plain words
What is it for?
Building Kiro Crew features, running its Python and TypeScript checks, testing changes, and preparing one verified change set.
Why use it?
It keeps development changes separate from the live checkout and catches problems before they are delivered.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/kirodotdev/kirocrew/kirocrew-worktree-dev
Any agent
npx skills add kirodotdev/KiroCrew --skill kirocrew-worktree-dev
Clone the repo
git clone --depth 1 https://github.com/kirodotdev/KiroCrew

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for kirocrew-worktree-dev

README.md
[![agentmods](https://agentmods.dev/badge/skills/kirodotdev/kirocrew/kirocrew-worktree-dev.svg)](https://agentmods.dev/skills/kirodotdev/kirocrew/kirocrew-worktree-dev)
Your own site
<a href="https://agentmods.dev/skills/kirodotdev/kirocrew/kirocrew-worktree-dev"><img src="https://agentmods.dev/badge/skills/kirodotdev/kirocrew/kirocrew-worktree-dev.svg" alt="Measured on agentmods" height="20"></a>
Per session 123 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,051 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00123 $0.06051
Opus 5 $0.00062 $0.03026
Sonnet 5 $0.00025 $0.01210
Haiku 4.5 $0.00012 $0.00605

Measured yesterday against content hash f6f2526c2b9f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

kirocrew-worktree-dev scanned grade C with 1 finding 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 yesterday.

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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf src/kiro_crew/static/dist && cp -R website/dist src/kiro_crew/static/dist
src/kiro_crew/builtin_skills/kirocrew-dev/kirocrew-worktree-dev/SKILL.md · 443 lines

How it starts

The opening of the file, as written. The whole thing — 443 lines — stays where its author put it; the contents beside it link to each section on GitHub.

HARD RULE: Kiro Crew development happens inside a git worktree

Scope guard: this skill applies ONLY when the working directory is the Kiro Crew source repository (or a worktree of it). If you are working in any other project, ignore this skill entirely — its rules (worktree mandate, build gates, single-commit squash, force-push) are conventions of the Kiro Crew repo and may be wrong or harmful elsewhere.

Every local Kiro Crew change — frontend, backend, or both — is developed, built, and verified in a dedicated git worktree, never by editing the live checkout or developing against the running gateway directly. One feature = one worktree. This is the single most important rule; violating it is the most common way to waste hours.

Rule 0 — Every change is developed in a worktree (FE + BE together)

  • Every Kiro Crew change happens in a dedicated worktree. Never edit the live/production checkout, and never develop against the running gateway.
  • A Kiro Crew feature spans two layers: src/kiro_crew/ (backend, Python) and website/ (frontend, React/Vite). A worktree carries both; even a backend-only change lives in a worktree.
  • Single-active model. Making a worktree "live" swaps the code behind the same dashboard URL and the same shared data home — ~/.kiro/crew by default (legacy installs auto-migrate from ~/.kirocrew on first launch; KIROCREW_HOME overrides) — including your REAL DB and sessions. Only one worktree is live at a time. Be deliberate about migrations, and switch back to the clean baseline when done.

Rule 1 — Create a worktree off main

# From your main KiroCrew clone:
git fetch origin main
git worktree add ../kirocrew-wt-<name> -b feat/<name> origin/main
cd ../kirocrew-wt-<name>

This gives you an isolated directory with its own branch. All work happens inside this worktree directory — never in the main clone.

Set up the worktree's own environment once (same dep set as CI — dev is a PEP 735 dependency group, NOT a package extra, so it needs --group, which requires pip ≥ 25.1: run .venv/bin/pip install -U pip first if it errors; on Windows the venv binaries live under .venv\Scripts\ instead of .venv/bin/):

python3 -m venv .venv && .venv/bin/pip install -e ".[voice]" --group dev
cd website && npm ci && cd ..

Read the full file on GitHub · 443 lines

Changes

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.

  1. yesterday Changed · +4 lines f6f2526c2b9f
  2. 4d ago First seen · 439 lines · 123 tokens per session scan C 5b179592ac8a

Subscribe to this mod's changes

kirocrew-worktree-dev is a skill published in the GitHub repository kirodotdev/KiroCrew (3,532 stars, last pushed yesterday), licensed Apache-2.0. It adds 123 tokens to every session and 6,051 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

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…

awslabs/agentcore-samples · 98 tokens

executive-financial-briefing

Generates a concise executive-level financial briefing or summary suitable for a CEO, CFO, or board presentation. Use when the user asks for a summary, briefing, executive summary, board update, financial overview, financial health check, or "how is the business doing". Covers the full P&L picture in one page. Also…

awslabs/agentcore-samples · 95 tokens

multi-quarter-trend-analysis

Analyzes financial trends across multiple quarters by comparing P&L metrics over time. Use when the user wants to see trends, patterns, trajectories, or directional movement across 3 or more quarters. Also use for "how are we trending", "show me the trend", "track performance over time", "quarter over quarter…

awslabs/agentcore-samples · 82 tokens

quarterly-kpi-calculator

Calculates quarterly financial KPIs from P&L data. P&L figures can be provided directly by the user or fetched from the financial data MCP server. Use when the user wants KPI calculations such as Gross Margin %, EBITDA Margin %, Operating Expense Ratio, or Revenue Growth % QoQ. Also use for quarterly performance…

awslabs/agentcore-samples · 84 tokens

portfolio-risk

Assess the risk profile of a set of stocks or a sector allocation, scoring concentration risk, volatility exposure, and overall risk tier.

awslabs/agentcore-samples · 28 tokens

sector-rotation

Identify which market sectors to overweight or underweight based on current macro conditions and sector performance data.

awslabs/agentcore-samples · 22 tokens