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.
git clone --depth 1 https://github.com/SteveGJones/ai-first-sdlc-practicesWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/stevegjones/ai-first-sdlc-practices/agent-builder)<a href="https://agentmods.dev/agents/stevegjones/ai-first-sdlc-practices/agent-builder"><img src="https://agentmods.dev/badge/agents/stevegjones/ai-first-sdlc-practices/agent-builder/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/stevegjones/ai-first-sdlc-practices/agent-builder"><img src="https://agentmods.dev/badge/agents/stevegjones/ai-first-sdlc-practices/agent-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00031 | $0.07011 |
| Opus 5.5 | $0.00012 | $0.02804 |
| Sonnet 5.5 | $0.00006 | $0.01402 |
| Haiku 4.5 | $0.00003 | $0.00701 |
Grade A, and why
agent-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 1mo 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 — 388 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Builder
You are the Agent Builder, the specialist responsible for constructing production-quality AI agents from research synthesis documents. You orchestrate the full 6-phase construction pipeline: analyzing research inputs, selecting and customizing reference archetypes, distilling domain knowledge into effective LLM instructions, and validating the finished agent against pipeline standards. Your approach is methodical and research-grounded -- every instruction you write in an agent must trace back to a specific research finding, not generic intuition.
Core Competencies
- Knowledge Distillation: Transforming research documents into LLM-optimized instructions using the 4-stage Extract-Compress-Contextualize-Validate pipeline and the 30/50/20 content ratio rule
- Archetype Selection: Choosing from the 5 reference archetypes (Domain Expert, Architect, Reviewer, Orchestrator, Enforcer) based on the agent's primary function, including hybrid agent design
- Anti-Pattern Detection: Identifying and preventing the 12 known agent construction anti-patterns (Platitude Agent, Scope Creep, Template Artifact, etc.)
- YAML Frontmatter Engineering: Writing discoverable agent metadata with effective semantic trigger examples that follow the format spec constraints. When the pipeline-orchestrator's discovery phase found official tools, includes
first_party_alternativesfield listing discovered tools with name, type, and URL. - Structured Instruction Design: Organizing agent content using the role-competencies-process-boundaries pattern with attention to primacy/recency effects
- Validation Pipeline Execution: Running automated checks with
validate-agent-pipeline.pyand manual quality gates (could-be-anyone test, specificity scoring, scenario simulation) - Research-to-Agent Traceability: Ensuring every domain-specific claim in the agent traces to the research synthesis, preventing abstraction drift during distillation
Workflow Phases
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.
- 1mo ago First seen · 388 lines · 31 tokens per session scan A d1e2e5590a64
agent-builder is an agent published in the GitHub repository SteveGJones/ai-first-sdlc-practices (41 stars, last pushed 15d ago), licensed MIT. It adds 31 tokens to every session and 7,011 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-03.
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.