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 bitovi/cascade-mcp --skill cascade-analyze-feature-scopegit clone --depth 1 https://github.com/bitovi/cascade-mcpWrote 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/bitovi/cascade-mcp/cascade-analyze-feature-scope)<a href="https://agentmods.dev/skills/bitovi/cascade-mcp/cascade-analyze-feature-scope"><img src="https://agentmods.dev/badge/skills/bitovi/cascade-mcp/cascade-analyze-feature-scope/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/bitovi/cascade-mcp/cascade-analyze-feature-scope"><img src="https://agentmods.dev/badge/skills/bitovi/cascade-mcp/cascade-analyze-feature-scope.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00111 | $0.02768 |
| Opus 5 | $0.00056 | $0.01384 |
| Sonnet 5 | $0.00022 | $0.00554 |
| Haiku 4.5 | $0.00011 | $0.00277 |
Grade A, and why
cascade-analyze-feature-scope 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 9d 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 — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scope Analysis
Produce a Scope Analysis — the central artifact that drives all downstream work. This takes per-frame analyses, epic context, reference documentation, and Figma comments, then categorizes every observed feature by scope and groups them by user workflow.
This is the most critical step in the pipeline. Questions, shell stories, and story descriptions all consume the scope analysis as their primary input.
When to Use
This is a sub-skill — called by parent skills after all content has been loaded, analyzed, and all Figma frames have been analyzed. Every parent skill (generate-questions, write-jira-story) needs scope analysis before proceeding.
Prerequisites
- Figma frame analyses exist at
.temp/cascade/figma/{fileKey}/frames/*/analysis.md - Content summaries exist at
.temp/cascade/context/*-summary.md - All content loading iterations are complete (no unloaded URLs remain in
to-load.md) - Epic context is available (from the Jira issue loaded by
load-linked-resource-content)
Procedure
1. Gather all inputs
Read these files:
Epic context (PRIMARY source of truth for scope decisions):
.temp/cascade/context/jira-{epicKey}.md— the epic/story description- If the epic already has a
## Scope Analysissection, extract it as the "previous scope analysis" for regeneration
Figma frame analyses:
- All
analysis.mdfiles from.temp/cascade/figma/{fileKey}/frames/*/analysis.md - If multiple Figma files, gather from all file keys
Reference documentation:
- All
*-summary.mdfiles from.temp/cascade/context/(Confluence, Google Docs summaries) - Read the full content files too if summaries are insufficient
Figma annotations (per-frame):
.temp/cascade/figma/{fileKey}/frames/*/context.md— comments, notes, and connections per frame- These may contain answers to previously asked questions
2. Check the codebase (if available)
This step is conditional — only perform if the agent has access to a local codebase (e.g. workspace file access in VS Code Copilot, Claude Code, or similar). If no codebase is accessible, skip to step 3.
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.
- 9d ago First seen · 233 lines · 111 tokens per session scan A 541cb8337fd9
cascade-analyze-feature-scope is a skill published in the GitHub repository bitovi/cascade-mcp (24 stars, last pushed 20d ago), licensed MIT. It adds 111 tokens to every session and 2,768 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.