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.
git clone --depth 1 https://github.com/yu-iskw/skill-inspectorWrote 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/rules/yu-iskw/skill-inspector/tech-stack)<a href="https://agentmods.dev/rules/yu-iskw/skill-inspector/tech-stack"><img src="https://agentmods.dev/badge/rules/yu-iskw/skill-inspector/tech-stack/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/rules/yu-iskw/skill-inspector/tech-stack"><img src="https://agentmods.dev/badge/rules/yu-iskw/skill-inspector/tech-stack.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 | $0.00192 | $0.00192 |
| Opus 5.5 | $0.00077 | $0.00077 |
| Sonnet 5.5 | $0.00038 | $0.00038 |
| Haiku 4.5 | $0.00019 | $0.00019 |
Grade A, and why
tech-stack 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.
What it actually says
Tech Stack
This project uses:
- Package Manager: pnpm (v10.x)
- Node.js Version: (read from .node-version)
pnpm Best Practices
Common Commands
- Install All Dependencies:
pnpm install - Add Dependency:
- To package:
pnpm add <pkg> - As dev dependency:
pnpm add -D <pkg>
- To package:
- Run Scripts:
pnpm <script>(e.g.,pnpm test)
Dependency Management
pnpm uses a content-addressable store and a non-flat node_modules structure. This ensures:
- Strictness: You cannot access dependencies that are not explicitly declared in your
package.json. - Efficiency: Disk space is saved by sharing package files across projects.
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 First seen · 28 lines · 192 tokens per session scan A 626d6ac71534
tech-stack is a cursor rule published in the GitHub repository yu-iskw/skill-inspector (2 stars, last pushed 15d ago), licensed Apache-2.0. It adds 192 tokens to every session, about $0.0008 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.
Other cursor rules, from other repositories
threat-infographic
Threat infographic generator — transforms structured threat model output into visual infographic specifications and images via Gemini API. Supports multiple templates: Baseball Card (risk summary dashboard) and System Architecture (annotated architecture diagram with attack surface badges).
agent-autonomy
AI agent autonomy threat agent — detects excessive autonomy, goal misalignment, unconstrained action scope, missing human-in-the-loop checkpoints, cascading multi-agent failures, and autonomous resource consumption against Processes.
denial-of-service
STRIDE denial of service threat agent — detects availability degradation threats including resource exhaustion, algorithmic complexity attacks, connection pool exhaustion, cascading dependency failures, and application-layer flooding against Processes, Data Stores, and Data Flows.
repudiation
STRIDE repudiation threat agent — detects accountability failures including missing audit trails, insufficient log detail, log tampering vulnerabilities, timestamp manipulation, and deniable actions against External Entities and Processes.
threat-report
Threat report generator — produces narrative threat analysis with executive summary, Mermaid attack trees for Critical and High findings, prioritized remediation roadmap with effort estimates, cross-cutting theme detection, and complete finding traceability.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.