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 skills/alvinindra/figma-mcp-rust/prototype-flow-mappingnpx skills add alvinindra/figma-mcp-rust --skill prototype-flow-mappinggit clone --depth 1 https://github.com/alvinindra/figma-mcp-rustWrote 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/alvinindra/figma-mcp-rust/prototype-flow-mapping)<a href="https://agentmods.dev/skills/alvinindra/figma-mcp-rust/prototype-flow-mapping"><img src="https://agentmods.dev/badge/skills/alvinindra/figma-mcp-rust/prototype-flow-mapping.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 5.1 | $0.00047 | $0.00543 |
| Opus 5 | $0.00023 | $0.00271 |
| Sonnet 5 | $0.00009 | $0.00109 |
| Haiku 4.5 | $0.00005 | $0.00054 |
Grade A, and why
prototype-flow-mapping 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.
What it actually says
Analyze Figma Prototype Reactions and Map Interaction Flows
Goal
Process the JSON output from the get_reactions tool to understand prototype flows and produce a clear, structured map of interactions between screens/nodes.
Input Data
You will receive JSON data from get_reactions. Each node may contain reactions like: { "trigger": { "type": "ON_CLICK" }, "action": { "type": "NAVIGATE", "destinationId": "destination-node-id" } }
Step-by-Step Process
1. Gather Context
- Call get_nodes_info(nodeIds: [...]) on all relevant nodes to get their names and types
- Call get_design_context(depth: 2, detail: "minimal") to understand the page structure
2. Filter and Transform Reactions
- Iterate through the get_reactions JSON output
- Keep only reactions where action type implies navigation:
- NAVIGATE, OPEN_OVERLAY, SWAP_OVERLAY
- Ignore: CHANGE_TO, CLOSE_OVERLAY, and others without a destinationId
- Extract per reaction:
- sourceNodeId: the node the reaction belongs to
- destinationId: action.destinationId
- actionType: action.type
- triggerType: trigger.type
3. Generate Flow Map
For each valid reaction, create a human-readable description:
- "On click, navigate to [Destination Name]"
- "On drag, open [Destination Name] overlay"
- "On hover, swap to [Destination Name]"
Combine these into a structured flow map grouped by source screen.
4. Output Format
Produce a summary like:
Flow Map:
- [Screen A] --ON_CLICK/NAVIGATE--> [Screen B]
- [Screen A] --ON_CLICK/OPEN_OVERLAY--> [Modal C]
- [Screen B] --ON_CLICK/NAVIGATE--> [Screen C]
5. Verification
- Use get_screenshot(nodeIds: [...]) on key screens to visually confirm the flow
- Cross-check node names from get_nodes_info with the flow map
Notes
- Node IDs use colon format (4029:12345), never hyphens
- Use get_reactions on a set of nodes that represent screens or interactive frames
- Focus on NAVIGATE actions for the primary user journey
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 · 63 lines · 47 tokens per session scan A 94dac91ceb4a
prototype-flow-mapping is a skill published in the GitHub repository alvinindra/figma-mcp-rust (33 stars, last pushed today), licensed MIT. It adds 47 tokens to every session and 543 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 2026-08-30.
Other skills, from other repositories
omh-rust
This is a Hermes-native rust workflow skill.
design-mcp-server
Design the tool surface, resources, and service layer for a new MCP server. Use when starting a new server, planning a major feature expansion, or when the user describes a domain/API they want to expose via MCP. Produces a design doc at docs/design.md that drives implementation.
api-canvas
DataCanvas primitive reference — a Tier 3 SQL/analytical workspace for tabular MCP servers, backed by DuckDB. Use when registering tables from upstream APIs, running ad-hoc SQL across them, and exporting results. Covers the acquire → register → query → export flow, per-table TTL, the token-sharing pattern for…
add-test
Scaffold a test file for an existing tool, resource, or service. Use when the user asks to add tests, improve coverage, or when a definition exists without a matching test file.
api-telemetry
Catalog of OpenTelemetry instrumentation built into framework @cyanheads/mcp-ts-core — spans, metrics, completion logs, env config, runtime caveats, custom instrumentation patterns, and cardinality rules. Use when enabling OTel export, adding custom spans or metrics in services, debugging missing telemetry, looking up…
polish-docs-meta
Finalize documentation and project metadata for a ship-ready MCP server. Use after implementation is complete, tests pass, and devcheck is clean. Safe to run at any stage — each step checks current state and only acts on what still needs work.