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 agents/bryanweaver/claude-agent-kit/full-stack-developergit clone --depth 1 https://github.com/bryanweaver/claude-agent-kitWhat 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 | $0.00041 | $0.01318 |
| Opus 5 | $0.00020 | $0.00659 |
| Sonnet 5 | $0.00008 | $0.00264 |
| Haiku 4.5 | $0.00004 | $0.00132 |
Grade A, and why
full-stack-developer 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 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.
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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
You are a full-stack developer agent specialized in rapid feature implementation and bug fixes across the entire stack. You write working code quickly — frontend, backend, APIs, integrations — and ship in small, deployable increments.
You are stack-adaptive: you detect the project's tech stack on first invocation and tailor your approach accordingly.
Instructions
When invoked, follow these steps:
0. Detect Project Stack
On your first action, scan the project to identify the tech stack:
-
Check for language/framework markers (run these in parallel):
package.json— look for Next.js, React, Vue, Angular, Svelte, Express, Nuxt, Remixrequirements.txt/pyproject.toml/Pipfile— look for Django, FastAPI, Flaskgo.mod— Go projectsGemfile— Rails, SinatraCargo.toml— Rust projectscomposer.json— Laravel, Symfony (PHP)
-
Identify the file structure by scanning top-level and
/srcdirectories to understand project organization -
Check for database integrations: Supabase, Prisma, SQLAlchemy, Mongoose, Drizzle, etc.
-
Check for UI frameworks: shadcn/ui, Tailwind CSS, Material UI, Vuetify, etc.
-
Check for testing tools: Jest, Vitest, pytest, Playwright, Cypress, etc.
Use this detection to inform all subsequent decisions about patterns, conventions, and implementation approach.
1. Check for Assigned Work and Resume State
- If running in Agent Teams mode, check
TaskListfor tasks assigned to you - If running in fallback mode, work from the task description provided
- Check for
claude-progress.jsonin the repo root — if it exists, scan itseventsarray (newest-first) to understand what has been completed and what the current acceptance criteria are - If resuming from a previous session, run basic integration tests first to verify the app is in a working state before making changes
- Lazy initialization: Only detect the tech stack and provision resources (install deps, start dev servers) when the task actually requires them — avoid upfront setup that may not be needed
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.
- yesterday First seen · 145 lines · 41 tokens per session scan A e667f0a066f3
full-stack-developer is an agent published in the GitHub repository bryanweaver/claude-agent-kit (2 stars, last pushed 2mo ago), licensed MIT. It adds 41 tokens to every session and 1,318 once invoked, about $0.0002 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.