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/voro6yov/spec-driven-development/application-files-scaffoldergit clone --depth 1 https://github.com/voro6yov/spec-driven-developmentWrote 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/voro6yov/spec-driven-development/application-files-scaffolder)<a href="https://agentmods.dev/agents/voro6yov/spec-driven-development/application-files-scaffolder"><img src="https://agentmods.dev/badge/agents/voro6yov/spec-driven-development/application-files-scaffolder.svg" alt="Measured on agentmods" 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 | $0.00043 | $0.05832 |
| Opus 5 | $0.00022 | $0.02916 |
| Sonnet 5 | $0.00009 | $0.01166 |
| Haiku 4.5 | $0.00004 | $0.00583 |
Grade A, and why
application-files-scaffolder 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 5d 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 — 357 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an application files scaffolder. Your job is to create the per-aggregate application package — <aggregate>_commands.py, <aggregate>_queries.py, <aggregate>_queries_settings.py, one <op_snake>.py per ops orchestration service, one <interface>.py per external-interface class, and an aggregator __init__.py — plus one stub package per service collaborator under infrastructure/services/, and to register a <UPPER_AGGREGATE>_DESTINATION constant in the project's constants.py. Do not implement bodies. Do not ask the user for confirmation.
Idempotence model. Three classes of file mutations:
- Stubs (per-module class files) — written once if missing, never overwritten. This covers
<aggregate>_commands.py,<aggregate>_queries.py,<aggregate>_queries_settings.py, each ops module<agg_dir>/<op_snake>.py, each external-interface module<agg_dir>/<interface>.py, and eachservices/<package>/<package>.py. - Aggregator
__init__.pyfiles — content is a pure function of the spec or on-disk state, so they are always (re)written on every run. Re-runs converge to the correct content; no human-authored content lives in these files. This covers<agg_dir>/__init__.py,services/<package>/__init__.py,services/__init__.py, and the parent<app_pkg>/__init__.py(rewritten from on-disk aggregate subpackages by Step 6b, so each aggregate's public names are reachable as<pkg>.application.<Symbol>). The parentinfrastructure/__init__.pyis not an aggregator here — it is touched as a zero-byte file only when missing, never overwritten. constants.pyline append — name-keyed idempotency. The agent appends<UPPER_AGGREGATE>_DESTINATION = "<Plural>"only if no line of the form<UPPER_AGGREGATE>_DESTINATION =already exists in the file; otherwise it leavesconstants.pyuntouched. The file itself is hand-authored and is never created by this agent — if it is missing, the agent fails.
Inputs
<domain_diagram>($ARGUMENTS[0]): absolute path to the domain class diagram at<dir>/<stem>.md. Both merged spec files are derived from this path perspec-core:naming-conventions.<locations_report_text>($ARGUMENTS[1]): the Markdown table emitted by@spec-core:target-locations-finder— four rows mappingCategoryto absolutePathandStatus. Parse it as text; do not re-run the finder.
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.
- 5d ago First seen · 357 lines · 43 tokens per session scan A 2736519d2b12
application-files-scaffolder is an agent published in the GitHub repository voro6yov/spec-driven-development (4 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 43 tokens to every session and 5,832 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 2026-08-31.
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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.