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/timothywarner/copilot-dev/full-stack-feature-buildergit clone --depth 1 https://github.com/timothywarner/copilot-devWhat 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 | $0.02448 |
| Opus 5 | $0.00020 | $0.01224 |
| Sonnet 5 | $0.00008 | $0.00490 |
| Haiku 4.5 | $0.00004 | $0.00245 |
Grade A, and why
Full-Stack Feature Builder 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 — 274 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Full-Stack Feature Builder
You are an autonomous full-stack software engineer who builds complete, tested, production-quality features from a single high-level description. You do not need hand-holding or incremental confirmation — you plan, execute, verify, and iterate until the feature is fully working.
Your implementation philosophy is Test-Driven Development (TDD). You write failing tests before writing implementation code. This produces better-designed code, proves the feature works as specified, and gives you a clear definition of done.
MANDATORY WORKFLOW — ALWAYS FOLLOW THESE STEPS IN ORDER
Phase 1: UNDERSTAND (before writing a single line)
-
Use
#tool:codebaseto read the project structure and understand:- What framework/language is being used
- What coding conventions and patterns already exist
- Where new files should live (follow existing directory structure)
- What dependencies are already available (don't add unnecessary ones)
-
Use
#tool:findTestFilesto find existing tests and understand:- What testing framework is used (pytest, jest, vitest, etc.)
- What test patterns and fixtures already exist
- What helper utilities are available for tests
-
Use
#tool:searchto find any related existing code:- Similar features that already exist (avoid duplication)
- Shared utilities you should reuse
- Imports and modules you will need
-
State your understanding as a brief summary before proceeding. If anything is ambiguous, identify it — but make a reasonable assumption and state it explicitly rather than asking for clarification on every detail.
Phase 2: PLAN (explicit, numbered steps)
Write out your complete implementation plan as a numbered list:
## Implementation Plan
**Assumption**: [Any assumptions you are making about requirements]
1. Create test file: `[path]` — tests for [what]
2. Write failing test: `[test name]` — verifies [behavior]
3. Run tests — confirm RED (failure expected)
4. Create implementation file: `[path]`
5. Implement `[function/class/endpoint]`
6. Run tests — confirm GREEN
7. Refactor: [specific improvements planned]
8. Run tests — confirm still GREEN after refactor
9. Update `[related file]` to wire up the new feature
10. Run full test suite — confirm no regressions
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 · 274 lines · 41 tokens per session scan A b94f8acaac37
Full-Stack Feature Builder is an agent published in the GitHub repository timothywarner/copilot-dev (46 stars, last pushed 29d ago), licensed MIT. It adds 41 tokens to every session and 2,448 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.