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-answer-design-questions-post-to-jiragit 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-answer-design-questions-post-to-jira)<a href="https://agentmods.dev/skills/bitovi/cascade-mcp/cascade-answer-design-questions-post-to-jira"><img src="https://agentmods.dev/badge/skills/bitovi/cascade-mcp/cascade-answer-design-questions-post-to-jira/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-answer-design-questions-post-to-jira"><img src="https://agentmods.dev/badge/skills/bitovi/cascade-mcp/cascade-answer-design-questions-post-to-jira.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 | $0.00059 | $0.01129 |
| Opus 5 | $0.00030 | $0.00564 |
| Sonnet 5 | $0.00012 | $0.00226 |
| Haiku 4.5 | $0.00006 | $0.00113 |
Grade A, and why
cascade-answer-design-questions-post-to-jira 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 12d 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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Answer Design Questions — Post to Jira
Walk through design behavior questions one at a time, collecting answers from the user and building a growing Q&A comment on a Jira issue.
When to Use
Use after generate-behavior-questions has produced frame-specific questions and the user chooses to answer questions here and post Q&A to Jira.
Required Input
- Questions organized by Figma frame (output from
generate-behavior-questions) - Jira issue key (e.g.,
PROJ-123)
Procedure
1. Initialize tracking file
Create .temp/cascade/context/questions-answers-{issueKey}.md to track progress:
---
jiraIssueKey: PROJ-123
jiraCommentId: null
---
## Behavior Q&A
(Q&A pairs will be appended here as the user answers)
2. Flatten questions into ordered list
From the frame-organized questions, build a flat list preserving frame context:
Frame: Login Screen
Q1: Should the "Remember me" checkbox be checked by default?
Q2: What error message appears for invalid credentials?
Frame: Dashboard
Q3: Is the widget layout user-configurable?
3. Ask each question
For each question, use the structured question UI (askQuestions in Copilot, AskUserQuestion in Claude Code) with suggested answer options.
Generate 2-4 suggested answers based on context from:
- The frame's
analysis.mdandcontext.md(Figma annotations, designer notes) - Scope analysis findings
- Common UX patterns for the component type
- Any partial information from Jira/Confluence/Google Docs
Always include a "Skip" option.
Example:
header: "Question 1 of 5 — Frame: Case Details"
question: "The designer note says 'show 4 voters before +X others,' but the Text-Listing component only has 3 entry slots. Should the tooltip show a max of 3 or 4 voter names before truncating?"
options:
- label: "Show 4 names (match designer note)"
description: "Add a 4th entry slot to the component"
- label: "Show 3 names (match current component)"
description: "Update the designer note to match the XML structure"
- label: "Skip"
allowFreeformInput: true
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.
- 12d ago First seen · 143 lines · 59 tokens per session scan A 8df2cdda936f
cascade-answer-design-questions-post-to-jira is a skill published in the GitHub repository bitovi/cascade-mcp (24 stars, last pushed 22d ago), licensed MIT. It adds 59 tokens to every session and 1,129 once invoked, about $0.0003 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
huashu-keynote-black
OpenDesign's all-hands: the year in review, the three priorities, and what every team owns next quarter. Built as a decision-grade corporate strategy deck for whole company.
kanban-board
A Kanban board is a visual task list with columns for stages such as To do, In progress, In review, and Done. It can show filters, labels, due dates, assignees, comments, and swimlanes that group cards.
acid-blue-business
A visual presentation style for modern business topics, using electric blue with black, white, and grey, directional layouts, and clear spacing. It is intended for business content rather than traditional data dashboards.
design-inventory
Use to run the Claude Design to ClosedLoop pipeline against the current web-ui. Stage A inventories a design export zip into schema-validated findings (typed design units - screens, regions like nav bars, standalone components like a chat dialog; UX and behavioral changes; Storybook component reuse mapping; token…
visual-dashboard
Start a browser-based dashboard that visualizes architecture, implementation plans, and project status. Persists artifacts in .bigpowers/dashboard/. Reads specs/state.yaml, release-plan.yaml, epics, and planning-status via HTTP API or opencode panel.
contribution-workflow
Create or document a contribution workflow for a design system — the multi-stage process for evaluating, accepting, and shepherding new contributions through to publication. Trigger when someone says: how should someone contribute, contribution process, adding a new component, contribution guidelines, what's the…