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 sliamh11/Deus --skill repo-visualisergit clone --depth 1 https://github.com/sliamh11/DeusWrote 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/sliamh11/deus/repo-visualiser)<a href="https://agentmods.dev/skills/sliamh11/deus/repo-visualiser"><img src="https://agentmods.dev/badge/skills/sliamh11/deus/repo-visualiser.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium analysis-evasion · line 1 Suspicious Unicode normalization or mixed-script contentFix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
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 | $0.00093 | $0.02747 |
| Opus 5 | $0.00046 | $0.01373 |
| Sonnet 5 | $0.00019 | $0.00549 |
| Haiku 4.5 | $0.00009 | $0.00275 |
Grade A, and why
repo-visualiser 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.
How it starts
The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analyze the repository the user names — defaulting to the current one — at latest main, and render it as an isometric system map: every component is a building on a grid, every dependency is an edge carrying a payload, and everything drawn carries a citation to the code that proves it.
The citations are the point. A building you inferred but never read is a fiction rendered in 3D. Draw only what you have read.
1. Pin the target at latest main
Resolve the repo path, then pin the exact tree you will analyze:
- Has a remote:
git fetch origin, then read the tree atorigin/main— or at the remote HEAD's default branch when it isn't calledmain(git symbolic-ref refs/remotes/origin/HEAD). Never analyze the working tree; it drifts from main, and the user asked for main. - No remote: use the local default branch and say so on the map.
Done when the resolved branch and short sha are recorded, and they get stamped into the rendered output.
2. Survey the system
Go codegraph-first, not grep-first, where those tools are present: search_code / codegraph_context for semantic candidates → codegraph_callers / codegraph_callees / codegraph_impact for structure → grep and read to confirm exactly. Where the codegraph tools are unavailable, fall back to semantic search plus grep and read, and say which you used in the final report. The citation requirement does not relax with the tooling.
Every node you admit carries three things:
| Field | Meaning |
|---|---|
| kind | entrypoint | service | store | queue | job | external |
| responsibility | one line, in the system's own vocabulary |
| citation | path:line where the component is defined |
An external system has no definition site in this repo. Cite the nearest in-repo proof that the dependency is real — the client construction, the endpoint or binary constant, or the call site — and mark it as a use site rather than a definition, so the map doesn't imply you read code you don't have.
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 · 113 lines · 93 tokens per session scan A 2c1d062ac82b
repo-visualiser is a skill published in the GitHub repository sliamh11/Deus (51 stars, last pushed 3d ago), licensed MIT. It adds 93 tokens to every session and 2,747 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
skin-creator
Create and apply a two-asset LobsterAI visual skin from the user's style description. Use only when the AI Skin Designer kit supplies the structured skinpack workflow marker; do not use for ordinary theme or image requests.
sn-infographic
An image-making tool that turns supplied content into an infographic, a visual format for explaining information with arranged text and graphics.
ui-design-source
Use this skill when the user provides Figma material, design-export files, screenshots of design tools, PDFs, JSON, existing HTML, or asks for design-to-HTML/code fidelity. It adapts OpenDesign/Figma handoff discipline for UIDesigner without requiring a live Figma runtime.
design-system-importer
Use this when COMPOSE or an AUTO compose segment has any external reference media or style source: a reference image, reference video, DESIGN.md, brand guide, screenshot, existing website, design notes, or an explicit named visual direction.
ui-design-system
Use this skill when creating, extending, or auditing a product UI system. It adapts Better Design-style design-system discipline without requiring an external runtime package.
ui-reference-packs
Use this skill after ui-design-contract only when UIDesigner needs a visual-system reference, product pattern, or style benchmark. It adapts OpenDesign's design-system and template catalogue into a small routed reference layer for HTML-first UI work.