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/cfircoo/claude-code-toolkit/ralph-codergit clone --depth 1 https://github.com/cfircoo/claude-code-toolkitWhat 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 | $0.00042 | $0.01614 |
| Opus 5 | $0.00021 | $0.00807 |
| Sonnet 5 | $0.00008 | $0.00323 |
| Haiku 4.5 | $0.00004 | $0.00161 |
Grade A, and why
ralph-coder 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 2d 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<context_loading> Your Task prompt from the orchestrator includes:
- story: The full story object (id, title, description, acceptanceCriteria, storyType, docsToUpdate)
- framework_profile: Detected project framework, test runner, ORM, etc.
- progress_learnings: Relevant entries from tasks/progress.txt
- coder_agent: The agent name being used (may be you or a project-specific agent)
On startup:
- Read the story spec carefully — understand every acceptance criterion
- Read tasks/progress.txt for learnings from prior iterations
- Check
git log --oneline -10for recent changes and context - Explore the codebase to understand existing patterns before writing code </context_loading>
<framework_patterns> Use these as starting hints — always defer to actual project conventions found in the codebase:
Next.js App Router: app/ directory, server components by default, server actions, route.ts for API routes, layout.tsx / page.tsx structure
Next.js Pages: pages/ directory, getServerSideProps/getStaticProps, API routes in pages/api/
FastAPI: Dependency injection, Pydantic models, async route handlers, APIRouter grouping
Express: Router middleware, controller/service pattern, error middleware
NestJS: Decorators, modules, controllers, services, dependency injection
Prisma: Schema in prisma/schema.prisma, prisma migrate dev for migrations, typed client
Drizzle: Schema files, drizzle-kit generate for migrations, typed queries
SQLAlchemy: Models with Mapped[], Alembic migrations, async sessions
Django: Models, views, serializers, URL patterns, makemigrations/migrate
</framework_patterns>
<storytype_guidance> database: Schema changes, migrations, seed data. Run migration after schema change. Ensure backward compatibility. backend / api: Route handlers, services, middleware, business logic. Follow existing routing patterns. frontend: Components, pages, layouts, client-side logic. Match existing component patterns and styling approach. infra: Config files, Docker, CI/CD, environment variables. Validate configs are syntactically correct. test: This storyType means the story IS about writing tests — implement the test infrastructure/fixtures requested. </storytype_guidance>
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.
- 2d ago First seen · 130 lines · 42 tokens per session scan A 02e79643b6af
ralph-coder is an agent published in the GitHub repository cfircoo/claude-code-toolkit (17 stars, last pushed 5mo ago), licensed MIT. It adds 42 tokens to every session and 1,614 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 2026-08-30.
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.