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 alejandrosaenz117/bonfires-marketplace --skill osv-scannergit clone --depth 1 https://github.com/alejandrosaenz117/bonfires-marketplaceWrote 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/alejandrosaenz117/bonfires-marketplace/osv-scanner)<a href="https://agentmods.dev/skills/alejandrosaenz117/bonfires-marketplace/osv-scanner"><img src="https://agentmods.dev/badge/skills/alejandrosaenz117/bonfires-marketplace/osv-scanner/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/alejandrosaenz117/bonfires-marketplace/osv-scanner"><img src="https://agentmods.dev/badge/skills/alejandrosaenz117/bonfires-marketplace/osv-scanner.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 | $0.00071 | $0.01277 |
| Opus 5.5 | $0.00028 | $0.00511 |
| Sonnet 5.5 | $0.00014 | $0.00255 |
| Haiku 4.5 | $0.00007 | $0.00128 |
Grade A, and why
osv-scanner 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scan Dependencies for Vulnerabilities
Scans a project's dependencies for known vulnerabilities using the OSV database.
The user is asking about dependency security. Help them identify vulnerable packages and estimate which vulnerabilities actually reach their code.
Your Task
- Identify the scanning scope: Confirm which directory or file to scan (default to workspace root)
- Choose scan mode: Decide between quick scan (list vulnerabilities) or reachability triage (estimate which vulnerabilities your code actually calls)
- Scan dependencies: Use appropriate tool (scan or triage)
- Report findings: Present results grouped by severity, with actionable next steps
- Suggest remediation: Recommend upgrades, suppression, or monitoring based on reachability
Decision Tree: Scan vs. Triage
Do you need to know if vulnerable code is *actually called* in your project?
│
├─→ YES (or unsure): Use TRIAGE
│ ├─ Shows: FOUND_IN_SOURCE, UNCERTAIN, NOT_FOUND_IN_GREP
│ ├─ Time: ~2-5 min (grep-based reachability analysis)
│ ├─ When: Deciding whether to upgrade or ignore a CVE
│ ├─ Example: "We have 42 vulnerabilities, but triage shows only 3 are
│ │ actually called — we can suppress the other 39 safely."
│ └─ Command: `/osv-scanner triage [path]`
│
└─→ NO (just need the list): Use SCAN
├─ Shows: All vulnerabilities, sorted by severity
├─ Time: <30 seconds
├─ When: Compliance/audit inventory, rapid security posture check
├─ Example: "Report all CVEs in dependencies for the board."
└─ Command: `/osv-scanner scan [path]`
Output Format
Scan Output
Present findings in severity tiers (CRITICAL, HIGH, MEDIUM, LOW, INFO) with:
- Package name and current version
- Vulnerability ID and CVSS score
- Advisory summary (1-2 sentences)
- Link to full advisory
- Remediation (upgrade version or suppress reason)
Example (abbreviated):
CRITICAL (2 vulnerabilities)
├─ express 4.17.1
│ ├─ CVE-2022-24999 (CVSS 7.5)
│ │ Open Redirect in query parser
│ │ Fix: Upgrade to express 4.18.0+
│ │ https://osv.dev/CVE-2022-24999
│ └─ CVE-2024-1086 (CVSS 8.1)
│ Authentication bypass in middleware
│ Fix: Upgrade to express 4.21.0+
HIGH (5 vulnerabilities)
├─ lodash 4.17.20
│ ├─ CVE-2021-23337 (CVSS 6.1)
│ │ Prototype pollution in defaultsDeep
│ │ Fix: Upgrade to lodash 4.17.21+
│ │ https://osv.dev/CVE-2021-23337
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 · 118 lines · 71 tokens per session scan A 130b25418365
osv-scanner is a skill published in the GitHub repository alejandrosaenz117/bonfires-marketplace (4 stars, last pushed 22d ago), licensed MIT. It adds 71 tokens to every session and 1,277 once invoked, about $0.0003 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 skills, from other repositories
code-quality-principles
Applies KISS, YAGNI, and SOLID principles for clean code with reduced complexity. Use when refactoring or reviewing code for over-engineering.
plugin-review
Review plugin quality with tiered checks and dependency scoping. Use for PR and pre-release audits.
improve-codebase-architecture
Review module boundaries, interface depth and high-leverage refactors with evidence.
backend-clean-architecture
Use this skill when the user asks 'where does this code go', 'what layer', 'clean architecture', 'hexagonal', 'ports and adapters', 'domain layer', 'application layer', 'infrastructure layer', 'should this be in service or repository', or when designing or reviewing backend code organization. This skill enforces…
duo-build
Build an issue or feature interactively toward an indexed shared goal, with automatic read-only peer review; resume the same run across Claude Code and Codex.
code-quality-review
A code-review guide for judging whether software stays easy to understand, change, test, and extend.