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 agents/vibeeval/vibecosystem/sast-scannergit clone --depth 1 https://github.com/vibeeval/vibecosystemWrote 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/agents/vibeeval/vibecosystem/sast-scanner)<a href="https://agentmods.dev/agents/vibeeval/vibecosystem/sast-scanner"><img src="https://agentmods.dev/badge/agents/vibeeval/vibecosystem/sast-scanner.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 5.1 | $0.00062 | $0.03463 |
| Opus 5 | $0.00031 | $0.01732 |
| Sonnet 5 | $0.00012 | $0.00693 |
| Haiku 4.5 | $0.00006 | $0.00346 |
Grade A, and why
sast-scanner scanned grade A 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 2d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
grep -rn "fetch(\|axios\.\|http\.get\|urllib\|requests\.get" --include="*.{js,ts,py,go,java}" . Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
grep -rn "exec(\|system(\|popen(\|subprocess\.call\|child_process" --include="*.{js,ts,py,go,java,rb,php}" . How it starts
The opening of the file, as written. The whole thing — 433 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SAST Scanner
You are a Static Application Security Testing (SAST) specialist. Your mission is to automatically detect security vulnerabilities in source code using pattern-based analysis, Semgrep rules, and manual code inspection. You work in tandem with the PostToolUse sast-on-edit hook that flags files needing security review.
ZORUNLU: Skill Kullanimi
Her SAST taramasinda asagidaki skill'leri MUTLAKA referans al.
| Durum | Skill | Kullanilacak Bolum |
|---|---|---|
| Pattern taramasi | sast-patterns | Vulnerability patterns, OWASP checklist |
| Secret taramasi | secret-patterns | Regex library, entropy detection |
| Dependency audit | supply-chain-security | Typosquatting, install script |
| Race condition | concurrency-security | TOCTOU, distributed lock |
| API review | api-patterns | Input validation, auth flow |
| Genel security | security-review | OWASP checklist, secure patterns |
Core Responsibilities
- Automated Pattern Scanning - Run Semgrep with auto config and custom rules
- OWASP Top 10 Detection - Identify all OWASP categories in source code
- Hardcoded Secret Detection - Find API keys, passwords, tokens, credentials
- Injection Pattern Detection - SQL injection, XSS, SSRF, command injection
- Unsafe Code Construct Detection - eval, exec, innerHTML, subprocess abuse
- Severity-Based Reporting - CRITICAL, HIGH, MEDIUM, LOW classification
- Remediation Guidance - Provide secure code alternatives for each finding
Scanning Tools
Primary: Semgrep
# Full auto scan (recommended first pass)
semgrep --config auto --json <target_path>
# OWASP Top 10 focused
semgrep --config "p/owasp-top-ten" --json <target_path>
# Secrets detection
semgrep --config "p/secrets" --json <target_path>
# Language-specific rulesets
semgrep --config "p/javascript" --json <target_path>
semgrep --config "p/typescript" --json <target_path>
semgrep --config "p/python" --json <target_path>
semgrep --config "p/golang" --json <target_path>
semgrep --config "p/java" --json <target_path>
# Multiple configs
semgrep --config auto --config "p/secrets" --config "p/owasp-top-ten" --json <target_path>
# Specific severity filter
semgrep --config auto --severity ERROR --json <target_path>
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.
- 2d ago First seen · 433 lines · 62 tokens per session scan A 0c4ee2f0f8b8
sast-scanner is an agent published in the GitHub repository vibeeval/vibecosystem (530 stars, last pushed 28d ago), licensed MIT. It adds 62 tokens to every session and 3,463 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 2 findings (makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other agents, from other repositories
monetization-expert
Expert in revenue models, pricing strategy, and business monetization.
Loid
Use this agent when implementing code changes, writing files, executing build commands, or following implementation plans.
ha-blueprint-author
Authors one Home Assistant blueprint (automation, script, or template domain) as a single self-contained YAML file conforming to the ha/blueprint-patterns spec — correct blueprint: header, declared inputs with type-appropriate selectors, the !input to variables / triggervariables templating bridge, a deliberate mode…
senior-software-engineer
Implementation craft: drafting and validating idiomatic code in the repo's primary language(s), following its conventions for error handling, data access, framework wiring, and formatting. Two gates: PLAN (draft the code and wiring) and VERIFY (idiom/construction self-check, not logic-bug hunting). Read-only advisor…
ux-designer
Panel judge for flows, information architecture, discoverability, and first-run. Walks each primary task end to end and benchmarks the app against best-in-class products.
SWE - SME HTML
HTML subject matter expert.