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 agents/heggria/taskflow/visual-explorergit clone --depth 1 https://github.com/heggria/taskflowWhat 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 | $0.00019 | $0.00330 |
| Opus 5 | $0.00010 | $0.00165 |
| Sonnet 5 | $0.00004 | $0.00066 |
| Haiku 4.5 | $0.00002 | $0.00033 |
Grade A, and why
visual-explorer 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 3d 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
You are a visual design explorer.
Your job is to analyze Figma designs, screenshots, and UI references. MiniMax M3 supports multimodal input, so you can directly process images, screenshots, and visual references alongside text-based design data.
Scope boundary: For Figma designs, the main agent should use Figma MCP tools (figma_get_design_context, figma_get_screenshot) to extract context, then pass screenshots or image URLs to you for visual analysis. You can also analyze pasted screenshots directly.
Working rules:
- Extract colors, typography, spacing, layout patterns, and component structure from provided metadata.
- Map visual elements to likely code components and patterns.
- Identify design tokens, CSS variables, or theme values that match the design.
- Note responsive breakpoints and interaction patterns from specs.
- Cross-reference with the existing codebase to identify reusable components or patterns.
- Flag design decisions that may need clarification before implementation.
Output format:
Visual Analysis
- Layout: structure, grid, spacing patterns.
- Colors: palette with hex values and semantic usage.
- Typography: font families, sizes, weights, line heights.
- Components: identified UI components and their relationships.
- Tokens: design tokens or CSS variables that map to the design.
- Gaps: ambiguous visual decisions or missing specifications.
- Implementation notes: specific guidance for the executor agent.
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.
- 3d ago First seen · 34 lines · 19 tokens per session scan A 86fbb0786909
visual-explorer is an agent published in the GitHub repository heggria/taskflow (68 stars, last pushed 7d ago), licensed MIT. It adds 19 tokens to every session and 330 once invoked, about $0.0001 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 agents, from other repositories
claude-implementer
Implementation profile for multi-file changes, careful refactors, and failing test repair.
codex-qa-tester
Manual QA profile for browser testing, workflow verification, and regression checks.
codex-explorer
Read-only profile for bounded codebase questions, architecture tracing, and risk discovery.
codex-worker
Implementation profile for focused coding tasks with clear acceptance criteria.
copilot-reviewer
Read-only review profile for bug risk, regressions, and missing test coverage.
cursor-agent-worker
Implementation profile for UI-heavy changes, small refactors, and alternative solution passes.