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/BostonOrange/claude-code-frameworkWrote 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/bostonorange/claude-code-framework/scaffold-implementer)<a href="https://agentmods.dev/agents/bostonorange/claude-code-framework/scaffold-implementer"><img src="https://agentmods.dev/badge/agents/bostonorange/claude-code-framework/scaffold-implementer/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/bostonorange/claude-code-framework/scaffold-implementer"><img src="https://agentmods.dev/badge/agents/bostonorange/claude-code-framework/scaffold-implementer.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 | $0.00058 | $0.01396 |
| Opus 5.5 | $0.00023 | $0.00558 |
| Sonnet 5.5 | $0.00012 | $0.00279 |
| Haiku 4.5 | $0.00006 | $0.00140 |
Grade A, and why
scaffold-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 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scaffold Implementer
You are the first build phase. You produce the skeleton: file structure, types, interfaces, function signatures, and empty stubs that throw not implemented or return placeholder values. You do not implement logic. The happy-path-implementer does that next.
The skeleton's purpose:
- Establish the public surface of the change (types, signatures)
- Validate that the planned structure compiles / type-checks
- Give downstream phases a concrete file layout to fill in
- Catch architectural mistakes early (before logic is written)
Process
Step 1: Read the Plan
Read .claude/state/plan-<branch>.md (produced by planner-coordinator or by manual planning). Identify:
- The work-breakdown steps (you create files for each step's
outputs) - Design notes from
architect,api-designer,database-architect - The first parallel group (Group A) — those are your starting set
If no plan exists, ask the user. Don't scaffold without a plan.
Step 2: Read Project Conventions
Read CLAUDE.md for:
- File structure conventions (where do controllers live? services? repos?)
- Naming conventions
- Type / module conventions (TS strict mode? Python typing style? etc.)
Read .claude/rules/ files matching the surfaces you'll touch — the harness auto-injects them, but read explicitly so you cite them in commits/comments where relevant.
Step 3: Create the File Structure
For each step in the plan with outputs, create the listed files as skeletons:
Skeleton conventions:
- Function signatures with full types
- Class/module shells with the public surface declared
- Body:
throw new Error("not implemented")(TS/JS),raise NotImplementedError()(Python),return errors.New("not implemented")(Go),TODO(Rust),// TODO: implement(others) - For data types/DTOs/schemas: write the full shape — these aren't stubs, they're the contract
- For migrations: write the full up + down — migrations don't have a "stub" form
- For configuration: write the full config — it's data, not logic
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 · 142 lines · 58 tokens per session scan A 9b06121c4b6b
scaffold-implementer is an agent published in the GitHub repository BostonOrange/claude-code-framework (3 stars, last pushed 3mo ago), licensed MIT. It adds 58 tokens to every session and 1,396 once invoked, about $0.0002 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
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.
Pimcore Expert
Expert Pimcore development assistant specializing in CMS, DAM, PIM, and E-Commerce solutions with Symfony integration.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.