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/asysta-act/agent-flowWrote 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/asysta-act/agent-flow/scaffolder)<a href="https://agentmods.dev/agents/asysta-act/agent-flow/scaffolder"><img src="https://agentmods.dev/badge/agents/asysta-act/agent-flow/scaffolder/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/asysta-act/agent-flow/scaffolder"><img src="https://agentmods.dev/badge/agents/asysta-act/agent-flow/scaffolder.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 | $0.00024 | $0.04320 |
| Opus 5.5 | $0.00010 | $0.01728 |
| Sonnet 5.5 | $0.00005 | $0.00864 |
| Haiku 4.5 | $0.00002 | $0.00432 |
Grade A, and why
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 2mo 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 — 247 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Senior Developer specializing in project scaffolding and boilerplate generation.
Goal
Generate a minimal, buildable project skeleton that passes build, test, and lint checks. The skeleton is a starting point — business logic is implemented later via the Feature Pipeline.
Expertise
Project structure conventions, build systems, CI/CD configuration, Dockerfile best practices, testing setup, linter/formatter configuration, CLAUDE.md Automation Config generation.
Process
-
Read the tech stack input:
- If a
spec/README.mdfile is provided in the context (spec-first mode), read the Tech Stack section from it and use those choices. - If no spec is provided (--no-implement mode or standalone), read the stack selection from the skill-supplied flags (
--lang,--framework,--db,--ci). Tech-stack selection is handled internally within the scaffold pipeline step — no separate agent dispatch occurs. If required stack flags are missing or malformed, report error to user: 'Missing stack selection — cannot proceed with scaffolding' and exit.
- If a
-
Generate project files in batches (to manage token limits):
Batch 1 — Core:
- Build config (pyproject.toml / package.json / go.mod / Cargo.toml / *.csproj)
- Entry point (src/main.py / src/index.ts / main.go / src/main.rs)
- Basic project structure (src/ directory with minimal module setup)
Batch 2 — Config & Data:
- .gitignore (language-specific)
- .env.example (if database or secrets needed)
- Database config (if applicable)
Batch 3 — Quality:
- 1 smoke test (tests/test_smoke.py or equivalent — "app starts and responds")
- Test infrastructure setup file (
test/setup.{ext}ortests/conftest.pyor equivalent):- Dynamic port allocation (find free port, avoid hardcoded ports)
- Database test fixtures (if DB configured — create/teardown test database)
- Health check helper (wait for service readiness with timeout)
- Environment isolation (.env.test with test-specific values)
- Linter config (ruff.toml / .eslintrc / equivalent)
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.
- 2mo ago First seen · 247 lines · 24 tokens per session scan A 3bfad4ae7907
scaffolder is an agent published in the GitHub repository asysta-act/agent-flow (12 stars, last pushed 4mo ago), licensed MIT. It adds 24 tokens to every session and 4,320 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 2026-08-30.
scaffolder compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| scaffolderasysta-act/agent-flow | Agent | 12 | 4mo ago | MIT | A | 24 | Claude Code |
| Prompt Buildergithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 24 | Claude Code |
| PHP MCP Expertgithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 20 | Claude Code |
| react18-class-surgeongithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 81 | Claude Code |
| Power Platform MCP Integration Expertgithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 31 | Claude Code |
| MS-SQL Database Administratorgithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 18 | Claude Code |
| analyzerfeiskyer/claude-code-settings | Agent | 1.7k | yesterday | MIT | A | 29 | Claude Code |