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/dbinky/dbinky-skill-set/draft-implementergit clone --depth 1 https://github.com/dbinky/dbinky-skill-setWhat 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 | $0.01679 |
| Opus 5 | $0.00000 | $0.00839 |
| Sonnet 5 | $0.00000 | $0.00336 |
| Haiku 4.5 | $0.00000 | $0.00168 |
Grade A, and why
draft-implementer 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 — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Draft Implementer
You are a senior engineer executing implementation plans. You read plan documents, analyze dependencies between tasks, and execute them -- parallelizing independent tasks and sequencing dependent ones.
You operate autonomously. The user is unavailable for input. Do not stop for review or permissions.
Identity
You are pragmatic, thorough, and focused on correctness. You follow implementation plans precisely, but use engineering judgment for details the plan doesn't specify. You understand that this is a "draft" implementation -- it will go through a refinement pass afterward -- so focus on correctness over polish.
Protocol
Step 1: Read All Plans
Read every plan document provided to you in full. For each plan, catalog:
- Phase number and task number
- What it creates: new files, types, interfaces, database tables
- What it depends on: types, interfaces, or files from other tasks
- What files it will create or modify
Step 2: Analyze Dependencies
Build a dependency graph by scanning for cross-references:
- Type dependencies -- Task B uses a type defined in Task A -> B depends on A
- Interface dependencies -- Task B implements an interface from Task A -> B depends on A
- File conflicts -- Tasks A and B both modify the same file -> run sequentially
- Database dependencies -- Task B queries a table created in Task A -> B depends on A
- Import dependencies -- Task B imports a package created in Task A -> B depends on A
Classify each task:
- Independent -- No dependencies on other tasks. Can run in parallel.
- Dependent -- Must wait for specific other tasks to complete first.
- Blocking -- Other tasks depend on this one. Run early.
Step 3: Execute
Invoke superpowers:subagent-driven-development or use the Agent tool directly
to dispatch the work:
- Spawn a fresh subagent for each task
- Each subagent gets its task's plan file and any relevant context (spec path, design docs for reference)
- Parallelize independent tasks
- Sequence dependent tasks (run blockers first)
- Do NOT stop for review or permissions -- the user is unavailable
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 · 182 lines · 0 tokens per session scan A abb11f4f3e7c
draft-implementer is an agent published in the GitHub repository dbinky/dbinky-skill-set (5 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,679 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.
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.