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 gohypergiant/agent-skills --skill accelint-persona-reviewgit clone --depth 1 https://github.com/gohypergiant/agent-skillsWrote 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/gohypergiant/agent-skills/accelint-persona-review)<a href="https://agentmods.dev/skills/gohypergiant/agent-skills/accelint-persona-review"><img src="https://agentmods.dev/badge/skills/gohypergiant/agent-skills/accelint-persona-review/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/gohypergiant/agent-skills/accelint-persona-review"><img src="https://agentmods.dev/badge/skills/gohypergiant/agent-skills/accelint-persona-review.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 | $0.00083 | $0.01663 |
| Opus 5 | $0.00042 | $0.00831 |
| Sonnet 5 | $0.00017 | $0.00333 |
| Haiku 4.5 | $0.00008 | $0.00166 |
Grade A, and why
accelint-persona-review 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 — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Persona-Based Design Review
Evaluate Figma designs from the perspective of specific operator personas. Generic UX advice ("make it more intuitive") misses insights that emerge from the persona's documented profile - their responsibilities, pain points, systems they monitor, and operational context.
Workflow
1. Load Persona Profile
Start by loading the persona index to find available personas:
Read references/personas/_index.md
Then load the specific persona requested by the user:
Read references/personas/{persona-id}.md
Do NOT load multiple persona files - only load the one requested by the user.
Do NOT load evaluation-examples.md yet - wait until Step 4.
If the persona doesn't exist, list available options from the index and ask the user to choose.
2. Gather Design Context
Figma URL provided:
Use appropriate Figma MCP tool to fetch the design (e.g., mcp__figma-desktop__get_design_context with extracted node ID from URL pattern node-id=1-2 → 1:2).
No URL (default): Use Figma MCP desktop to get current file/selection. If nothing selected, prompt user to select a frame or component.
Figma MCP unavailable: Ask user to provide a screenshot of the design. Analyze the screenshot using visual inspection, but note that without full design context (component properties, layout constraints, interaction states), the review will be limited to visual elements only.
3. Search Supporting Documentation
Use Outline MCP to find relevant context. Since Outline requires workspace selection, use this pattern:
ListMcpResourcesTool(server: "outline")
Search for documents covering:
- UI standards/guidelines for this operator role
- Previous design reviews or feedback
- System requirements or specifications
- Training materials or user guides
Prioritize documents mentioning the persona's role, responsibilities, or systems they interact with.
Outline MCP unavailable: Proceed with the review based solely on the persona profile and design context. Note in your review that supporting documentation wasn't available, and recommend areas where organizational standards should be consulted.
What ships with it
10 files 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.
- README.md 2.0 KB
- references/evaluation-examples.md 5.1 KB
- references/personas/_index.md 1.2 KB
- references/personas/_template.md 1.1 KB
- references/personas/air-surveillance-tech.md 1.4 KB
- references/personas/air-weapons-officer.md 2.1 KB
- references/personas/mission-crew-commander.md 2.0 KB
- references/personas/senior-director.md 2.0 KB
- references/personas/surveillance-tech.md 2.2 KB
- references/personas/weapons-director.md 1.9 KB
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 · 179 lines · 83 tokens per session scan A 3bc6f8dc868c
accelint-persona-review is a skill published in the GitHub repository gohypergiant/agent-skills (24 stars, last pushed today), licensed Apache-2.0. It adds 83 tokens to every session and 1,663 once invoked, about $0.0004 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 $ultragoal 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.