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 tykisgod/quick-question --skill depsgit clone --depth 1 https://github.com/tykisgod/quick-questionWrote 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/tykisgod/quick-question/deps)<a href="https://agentmods.dev/skills/tykisgod/quick-question/deps"><img src="https://agentmods.dev/badge/skills/tykisgod/quick-question/deps/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/tykisgod/quick-question/deps"><img src="https://agentmods.dev/badge/skills/tykisgod/quick-question/deps.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 | $0.00016 | $0.00711 |
| Opus 5.5 | $0.00006 | $0.00284 |
| Sonnet 5.5 | $0.00003 | $0.00142 |
| Haiku 4.5 | $0.00002 | $0.00071 |
Grade A, and why
deps 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 1mo 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Respond in the user's preferred language (detect from their recent messages, or fall back to the language setting in CLAUDE.md).
Arguments: $ARGUMENTS
- No arguments: analyze all .asmdef files in the project
- A module name (e.g. "Player"): analyze only that module's dependency chain, upstream and downstream; the Mermaid diagram shows only related modules
Execution Steps
1. Collect All .asmdef Files
Use Glob to find Assets/**/*.asmdef, excluding Tests and Editor asmdefs (filenames containing .Tests., .Editor., or .PlayModeTests.).
If the project has no .asmdef files (pure directory-based project), scan using statements in .cs files instead, aggregate modules by namespace, and build the dependency graph from the using references.
2. Build GUID → Name Mapping
For each .asmdef, read its name field and the guid field of its .asmdef.meta.
3. Parse Dependency Relationships
For each .asmdef, map the GUIDs in its references array to names through the lookup table and record ModuleA → [ModuleB, ModuleC].
4. Output Mermaid Dependency Graph
Generate a Mermaid flowchart, arranged by layer from top to bottom. Layers are inferred from the graph: modules with no dependencies are Layer 0, modules depending only on Layer 0 are Layer 1, etc.
```mermaid
graph TD
subgraph "Layer 0"
Core
end
subgraph "Layer 1"
Player
AI
end
subgraph "Layer 2"
UI
Networking
end
Player --> Core
AI --> Core
UI --> Player
Networking --> Core
```
- Normal dependencies: solid arrow
--> - Circular dependencies: red dashed
-.->|cycle| - Layer violations: orange bold
==>|violation|
5. Output Dependency Matrix
| Module ↓ Depends on → | Core | Player | AI | UI | ... |
|------------------------|:----:|:------:|:--:|:--:|:---:|
| Core | - | | | | |
| Player | ✓ | - | | | |
| AI | ✓ | | - | | |
| UI | | ✓ | | - | |
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.
- 1mo ago Changed · -29 lines 5786cb364dce
- 2mo ago First seen · 113 lines · 16 tokens per session scan A 9ae1b899e035
deps is a skill published in the GitHub repository tykisgod/quick-question (13 stars, last pushed 13d ago), licensed MIT. It adds 16 tokens to every session and 711 once invoked, about $0.0001 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 2026-08-30.
deps compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| depstykisgod/quick-question | Skill | 13 | 13d ago | MIT | A | 16 | Claude Code |
| gemininowork-studio/notfair-plugin | Skill | 4.1k | 8d ago | MIT | A | 184 | Claude Code |
| auditoliver-kriska/claude-elixir-phoenix | Skill | 574 | yesterday | MIT | A | 35 | Claude Code |
| boundariesoliver-kriska/claude-elixir-phoenix | Skill | 574 | yesterday | MIT | A | 33 | Claude Code |
| triageoliver-kriska/claude-elixir-phoenix | Skill | 574 | yesterday | MIT | A | 32 | Claude Code |
| security-architecture-reviewcbrock84/headcount | Skill | 2.6k | 19d ago | MIT | A | 78 | Claude Code |
| pr-threads-addressposit-dev/skills | Skill | 554 | 4d ago | MIT | A | 48 | Claude Code |