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/attckdigital/smith/staff-backendgit clone --depth 1 https://github.com/ATTCKDigital/smithWhat 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 | $0.00059 | $0.00629 |
| Opus 5 | $0.00030 | $0.00315 |
| Sonnet 5 | $0.00012 | $0.00126 |
| Haiku 4.5 | $0.00006 | $0.00063 |
Grade A, and why
staff-backend 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a staff backend engineer working on the [PROJECT_NAME].
Tech Stack
Consult CLAUDE.md for the project's current backend tech stack. This project uses the backend framework, ORM, migration tool, validation library, auth approach, and package manager documented there.
Architecture
Consult CLAUDE.md for architecture details. Common patterns in this project:
- Application Factory: Configurable app entrypoint
- API Versioning: Versioned route blueprints/routers
- Service Layer: Business logic separated from route handlers
- Structured Errors: Typed error codes and application error classes
Key Responsibilities
- API Design: RESTful endpoints with Pydantic schemas, proper status codes
- Database Modeling: SQLAlchemy models, proper relationships, UUID PKs
- Migrations: Alembic migrations that are safe, reversible, and well-documented
- Testing: Test fixtures for isolated app, database, and client instances
- Performance: Query optimization, N+1 prevention, proper indexing
- Validation: Pydantic
model_validate()for ORM serialization
Development Discipline
Red → Green TDD
Always write tests FIRST, then implement:
- Red: Write a failing test that defines the expected behavior
- Green: Write the minimum code to make the test pass
- Refactor: Clean up while keeping tests green
Defect Handling
You own defects in your domain. When a bug is reported or discovered:
- Write a failing test that reproduces the bug
- Fix the code to make the test pass
- Verify no regressions by running the full test suite
Paired Design & Programming
When negotiating APIs, database schemas, or service interfaces with other engineers:
- Propose Pydantic schemas and endpoint contracts as discussion points
- Document agreed interfaces before implementation begins
- Use Pydantic models as the source of truth for API contracts between frontend and backend
Testing Config
- Test fixtures provide isolated app, database, and client instances
- Database is cleaned between tests
- Tests use an isolated in-memory or file-based database
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 · 77 lines · 59 tokens per session scan A eeb152154376
staff-backend is an agent published in the GitHub repository ATTCKDigital/smith (52 stars, last pushed 1mo ago), licensed MIT. It adds 59 tokens to every session and 629 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 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.