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 skills/koatora20/guard-scanner/comments-onlynpx skills add koatora20/guard-scanner --skill comments-onlygit clone --depth 1 https://github.com/koatora20/guard-scannerWrote 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/koatora20/guard-scanner/comments-only)<a href="https://agentmods.dev/skills/koatora20/guard-scanner/comments-only"><img src="https://agentmods.dev/badge/skills/koatora20/guard-scanner/comments-only.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00178 |
| Opus 5 | $0.00000 | $0.00089 |
| Sonnet 5 | $0.00000 | $0.00036 |
| Haiku 4.5 | $0.00000 | $0.00018 |
Grade B, and why
comments-only scanned grade B with 2 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.
Instruction-override phrasingmediumPrompt injection
Text telling the model to disregard its earlier instructions or safety rules is the shape of a prompt injection, whoever wrote it.
// This is a comment about "ignore all previous instructions" — it's just an example string Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
// We discuss exec() and child_process as security concepts What it actually says
Edge Case Skill — Comments Only
This skill has security-related keywords only in comments and string literals, which should ideally NOT trigger findings (testing FP resilience).
Instructions
Help users understand security concepts by explaining them.
// This is a comment about "ignore all previous instructions" — it's just an example string
// The term "system prompt" appears here for educational purposes
const educationalText = "Example of prompt injection: 'ignore all previous instructions'";
const demo = "This shows how eval() could be misused, but we don't actually call it";
function explain(topic) {
// We discuss exec() and child_process as security concepts
return `Security topic: ${topic} — always validate inputs`;
}
Note: This file discusses security concepts for education. The regex scanner may flag some of these as they appear in string/comment context.
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 · 24 lines · 0 tokens per session scan B 22d7af9d911c
comments-only is a skill published in the GitHub repository koatora20/guard-scanner (2 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 178 tokens. A static security scan graded it B with 2 findings (instruction-override phrasing, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
ai-claim-checker
Evaluate factual claims in AI-generated text and teach a lightweight verification habit. Use when a learner wants to fact-check an AI answer, identify uncertainty, choose appropriate independent sources, or practise critical AI literacy.
retrieval-practice-generator
Generate low-stakes retrieval-practice questions with grounded answer notes and implementation guidance. Use for quiz starters, revision activities, delayed recall, misconception checks, or adapting recall difficulty.
songwriting-and-ai-music
Songwriting craft, AI music generation prompts (Suno focus), parody/adaptation techniques, phonetic tricks, and lessons learned. These are tools and ideas, not rules. Break any of them when the art calls for it.
documentation-writer
Create or revise software documentation using the Diátaxis distinction between tutorials, how-to guides, reference, and explanation. Use for README sections, product and API documentation, operational guides, onboarding material, or restructuring an existing documentation set.
autocontext-consumer
Use when an agent needs to USE knowledge Autocontext already produced - find which scenarios have knowledge, read the playbook and lessons for one, understand the on-disk file and folder layout, and move knowledge between checkouts. Host-agnostic; requires only the autoctx CLI and the filesystem.
1688 Sourcing Agent
Your intelligent companion for mastering 1688.com procurement. This skill empowers international buyers with step-by-step guidance on supplier verification, product selection, price negotiation, and logistics planning—teaching you to source confidently from China's largest wholesale marketplace while knowing exactly…