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 skills add isvlasov/rageatc-oss --skill scaffolding-projectgit clone --depth 1 https://github.com/isvlasov/rageatc-ossWrote 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/skills/isvlasov/rageatc-oss/scaffolding-project)<a href="https://agentmods.dev/skills/isvlasov/rageatc-oss/scaffolding-project"><img src="https://agentmods.dev/badge/skills/isvlasov/rageatc-oss/scaffolding-project/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/skills/isvlasov/rageatc-oss/scaffolding-project"><img src="https://agentmods.dev/badge/skills/isvlasov/rageatc-oss/scaffolding-project.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 | $0.00041 | $0.01322 |
| Opus 5 | $0.00020 | $0.00661 |
| Sonnet 5 | $0.00008 | $0.00264 |
| Haiku 4.5 | $0.00004 | $0.00132 |
Grade C, and why
scaffolding-project scanned grade C with 1 finding 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 10d 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- Update: append observations when something noteworthy happens. Do not rewrite — this file is append-only. One exception: /codify sweeps append a `Codified →` marker line to processed entries. Include only durable in How it starts
The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scaffolding a Project
Creates the standard file structure for a rageatc-code-oss project — run once per new project, before architecture and decomposition. The scaffold creates empty templates and a pre-populated CLAUDE.md; content is filled in by later skills (managing-product → PRD, architecting-software → ARCHITECTURE, decomposing-work/enriching-roadmap → ROADMAP, planning-software → ORCHESTRATION-PLAN). Not for projects with files already in place — check first.
Inputs Required
- Project root path — absolute path where files will be created
- Project name — used to populate CLAUDE.md heading
- Workflow tier — Quick, Standard, or Thorough (determines whether docs/decisions/ is created)
Outputs Produced
<project-root>/
├── CLAUDE.md # Pre-populated orchestrator orientation file
├── STATUS.md # Living project state — current position, decisions, next steps
├── PRD.md # Empty template — managed by managing-product
├── ARCHITECTURE.md # Empty template — managed by architecting-software
├── ROADMAP.md # Empty template — managed by decomposing-work / enriching-roadmap
├── ORCHESTRATION-PLAN.md # Empty template — managed by planning-software
├── LEARNINGS.md # Empty, updated only when noteworthy
└── docs/
└── decisions/ # Created only for Thorough tier (for ADRs)
Workflow
Step 1: Confirm inputs
Check that you have:
- Project root path (absolute)
- Project name
- Workflow tier (Quick / Standard / Thorough)
If any are missing, ask before proceeding.
Step 2: Check for existing files
Before creating anything, check whether the project root already contains any of the target files. If existing files are present, stop and confirm with the orchestrator which files to create. Do not overwrite without explicit approval.
Step 3: Create the directory structure
Create the project root if it does not exist. For Thorough tier only, also create docs/decisions/.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 153 lines · 41 tokens per session scan C bf39dc32a3c8
scaffolding-project is a skill published in the GitHub repository isvlasov/rageatc-oss (9 stars, last pushed 1mo ago), licensed MIT. It adds 41 tokens to every session and 1,322 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
design-method
Use when starting any design task — resolves register, sets the 3 dials, locks Gate 0, and routes to the right move and target skill.
design-webapp
Use when building or extending a dashboard, SaaS screen, or any authenticated app surface — use design-web instead for a marketing site.
design-web
Use when building or revising a marketing/landing/campaign page, register brand locked at Gate 0 — use design-webapp for app screens instead.
react-tanstack-router
Use when implementing routing in a React app (NOT Next.js) with TanStack Router — file-based routes, loaders, search params.
git-flow
Use when committing, branching, opening PRs, or deciding merge/branch strategy.
fusecore
Use when creating modules, understanding FuseCore structure, or implementing features in a FuseCore modular-monolith Laravel project.