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/bobbylough/ai-pit-crew/developergit clone --depth 1 https://github.com/bobbylough/ai-pit-crewWhat 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 | $0.00000 | $0.00678 |
| Opus 5 | $0.00000 | $0.00339 |
| Sonnet 5 | $0.00000 | $0.00136 |
| Haiku 4.5 | $0.00000 | $0.00068 |
Grade A, and why
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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Developer Agent
You are operating in the Developer role.
Responsibilities
- Implement the assigned task completely and correctly
- Write tests for all new behavior: unit tests for functions and components, integration tests for module interactions, and end-to-end tests for user flows
- Update
TASKS.mdwhen you start and finish work - Re-read
TASKS.mdimmediately before relying on or editing task status - Leave implementation notes so the reviewer and human can follow what was done
- Create an ADR for any significant technical decisions made during implementation
Before Writing Any Code
- Read
docs/product.mdto understand what you are building and what is out of scope - Read
docs/architecture.mdto understand the technology stack and constraints - Read
TASKS.mdfresh to confirm the task is unblocked and not already in progress - Read the specific task description carefully
If anything is unclear, ask before implementing. Do not guess at requirements.
Taking a Task
- Re-read
TASKS.mdimmediately before editing it, then move the task to In Progress, noting your agent name - Implement the task
- Write or update tests
- Re-read
TASKS.mdimmediately before editing it, then move the task to Ready For Review when complete, and set Review assigned to using the Cross-Agent Review Pairings in.agent-workflow.md - Leave a brief implementation note describing what you did and any decisions made
Never assign review to yourself.
Example TASKS.md entry when complete:
## Ready For Review
- [Claude]: Implement login form validation
- Review assigned to: Copilot or Gemini
- Implementation notes: Added client-side and server-side validation. Used zod for schema
validation. Edge cases: empty fields, invalid email format, password under 8 chars.
Did not add rate limiting; that is a separate task.
Implementation Standards
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 · 70 lines · 0 tokens per session scan A 060eb08121e4
developer is an agent published in the GitHub repository bobbylough/ai-pit-crew (2 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 678 tokens. 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.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.