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 Leobeckham-162632/codex-visio-replica --skill visio-image-replicagit clone --depth 1 https://github.com/Leobeckham-162632/codex-visio-replicaWrote 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/leobeckham-162632/codex-visio-replica/visio-image-replica)<a href="https://agentmods.dev/skills/leobeckham-162632/codex-visio-replica/visio-image-replica"><img src="https://agentmods.dev/badge/skills/leobeckham-162632/codex-visio-replica/visio-image-replica/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/leobeckham-162632/codex-visio-replica/visio-image-replica"><img src="https://agentmods.dev/badge/skills/leobeckham-162632/codex-visio-replica/visio-image-replica.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00157 | $0.02934 |
| Opus 5.5 | $0.00063 | $0.01174 |
| Sonnet 5.5 | $0.00031 | $0.00587 |
| Haiku 4.5 | $0.00016 | $0.00293 |
Grade A, and why
visio-image-replica 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 2mo 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 — 261 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Visio Image Replica
Reconstruct a supplied two-dimensional reference as native, editable Visio content. Treat structure, text, connections, and editability as stronger evidence than a visual similarity score.
Operating boundaries
- Use this skill for image-to-editable-Visio reconstruction, including diagrams, schematics, topologies, mechanism figures, architecture figures, maps, and infographics.
- Do not route image upscaling, ordinary enhancement, beautification, or artistic generation here.
- Stop if no reference image is supplied, either required MCP is unavailable, Visio is unavailable, the content cannot be handled legally, or an overwrite would lack explicit authorization.
- Never overwrite a reference, historical task, prior iteration, or existing final delivery.
- Never use an embedded full-page reference image as the final drawing. A temporary alignment guide is allowed only while constructing the scene and must be removed by default.
- Use
visio-comand Visio ShapeSheet for primary drawing. Usewindows-mcponly to start or focus Visio, inspect a visible window, handle a safe file dialog that COM cannot handle, capture UI evidence, or recover from an exceptional condition. - Never claim universal one-to-one pixel identity or infer illegible text as certain.
Load references progressively
Read workflow.md before starting. Load only the additional references needed for the current stage:
- Scene work: scene-schema.md, coordinate-system.md, and object-analysis.md.
- Rendering and styling: visio-rendering.md, chunked-rendering.md, shapesheet-style-map.md, and text-and-fonts.md.
- Connector work: connector-comparison.md.
- Iteration and acceptance: iteration-policy.md, quality-gates.md, and output-contract.md.
- Failures: error-recovery.md and troubleshooting.md.
What ships with it
32 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.
- agents/openai.yaml 534 B
- assets/stencils/.gitkeep 1 B
- assets/templates/.gitkeep 1 B
- references/chunked-rendering.md 2.7 KB
- references/connector-comparison.md 2.3 KB
- references/coordinate-system.md 1.1 KB
- references/error-recovery.md 1.2 KB
- references/iteration-policy.md 1.0 KB
- references/object-analysis.md 1.2 KB
- references/output-contract.md 1.1 KB
- references/quality-gates.md 2.0 KB
- references/scene-schema.md 1.2 KB
- references/shapesheet-style-map.md 1.1 KB
- references/text-and-fonts.md 957 B
- references/troubleshooting.md 1.4 KB
- references/visio-rendering.md 1.3 KB
- references/workflow.md 1.7 KB
- scripts/build_dependency_plan.py 6.2 KB runs code
- scripts/compare_iterations.py 3.0 KB runs code
- scripts/create_scene_template.py 3.8 KB runs code
- scripts/create_task_workspace.py 3.2 KB runs code
- scripts/package_delivery.py 4.8 KB runs code
- scripts/preflight.py 3.4 KB runs code
- scripts/select_best_iteration.py 4.0 KB runs code
- scripts/validate_delivery.py 4.0 KB runs code
- scripts/validate_scene_package.py 5.2 KB runs code
- tests/test_dependency_plan.py 1.9 KB runs code
- tests/test_frontmatter.py 2.0 KB runs code
- tests/test_output_contract.py 3.9 KB runs code
- tests/test_references.py 1.7 KB runs code
- tests/test_scripts.py 7.2 KB runs code
- tests/test_skill_structure.py 1.8 KB runs code
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.
- 2mo ago First seen · 261 lines · 157 tokens per session scan A 976a4190c2eb
visio-image-replica is a skill published in the GitHub repository Leobeckham-162632/codex-visio-replica (6 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 157 tokens to every session and 2,934 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-08-31.
visio-image-replica compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| visio-image-replicaLeobeckham-162632/codex-visio-replica | Skill | 6 | 3mo ago | Apache-2.0 | A | 157 | Codex |
| frame-flowchart-stickynexu-io/open-design | Skill | 106k | today | Apache-2.0 | A | 26 | Claude Code, Codex |
| drawio-skillAgents365-ai/drawio-skill | Skill | 11k | yesterday | MIT | A | 107 | Claude Code, Codex |
| frame-flowchart-stickynexu-io/html-anything | Skill | 9.4k | today | Apache-2.0 | A | 27 | Claude Code, Codex |
| mermaid-diagramwecode-ai/Wegent | Skill | 882 | yesterday | Apache-2.0 | A | 102 | Claude Code, Codex |
| cocosketchSnowflake-Labs/cocoplus | Skill | 727 | 2d ago | MIT | A | 20 | Claude Code |
| svg-diagramPM-Shawn/Abu-Cowork | Skill | 419 | 3d ago | Apache-2.0 | A | 70 | Claude Code |