vantage

vantage is a skill for Claude Code from tinoimammp/vantage-security-agent. It costs 230 tokens per session (2,179 once invoked), scanned A, original, MIT.

A source-code security scanner for web and mobile application repositories. Static application security testing, or SAST, checks code, configuration, and dependencies without running the application.

In plain words
What is it for?
Auditing web or mobile code for issues such as injection, cross-site scripting, broken access control, authentication bypasses, server-side request forgery, unsafe XML handling, and exposed secrets.
Why use it?
It helps find security weaknesses before they reach a deployed application, while keeping the review within the source repository.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: mentions subagents.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the vantage plugin — 1 skill, 6 commands shipped together

Good fit Auditing web or mobile code for issues such as injection, cross-site scripting, broken access control, authentication bypasses, server-side request forgery, unsafe XML handling, and exposed secrets.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add tinoimammp/vantage-security-agent
Claude Code
/plugin install vantage

Made for: Claude Code.

Or install vantage, the plugin that ships this one along with the rest of its 1 skill, 6 commands.

Wrote 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.

agentmods badge for vantage

README.md
[![agentmods](https://agentmods.dev/badge/skills/tinoimammp/vantage-security-agent/vantage/github.svg)](https://agentmods.dev/skills/tinoimammp/vantage-security-agent/vantage)
Your own site
<a href="https://agentmods.dev/skills/tinoimammp/vantage-security-agent/vantage"><img src="https://agentmods.dev/badge/skills/tinoimammp/vantage-security-agent/vantage/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.

agentmods 80×15 button for vantage

Your own site · 80×15
<a href="https://agentmods.dev/skills/tinoimammp/vantage-security-agent/vantage"><img src="https://agentmods.dev/badge/skills/tinoimammp/vantage-security-agent/vantage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 230 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,179 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00230 $0.02179
Opus 5 $0.00115 $0.01090
Sonnet 5 $0.00046 $0.00436
Haiku 4.5 $0.00023 $0.00218

Measured 10d ago against content hash 5d4600bd4806, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

vantage 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 10d 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.

skills/vantage/SKILL.md · 152 lines

How it starts

The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Pentest SAST — Orchestration Skill

This skill is the entry point for the vantage plugin. It covers both the web and mobile scan pipelines, and the separate fix capability. It is intentionally short: everything phase-specific lives in ${CLAUDE_PLUGIN_ROOT}/agents/{web,mobile,others}/*.md, read on demand. Cross-phase control (gates, parallelism, resume) lives in ${CLAUDE_PLUGIN_ROOT}/workflow/orchestration.md.

Two roots — do not confuse them

  • Plugin assets (workflow/, agents/, schemas/, templates/, knowledge/, examples/, START-HERE.md, TIMESTAMPS.md) live at ${CLAUDE_PLUGIN_ROOT} — always resolve them from there, never from the target project's working directory.
  • Artifacts (scope, endpoints, findings, PoCs, reports, fixes) are per-engagement output, always written under ./.vantage/artifacts/... relative to the target project currently open — never inside the plugin's own install directory.

Golden rules (non-negotiable)

  1. SAST only during scanning. Analyze source code, configuration, and dependencies. Never run the application, never install a mobile build, never send requests, never exploit live systems. (Live verification of a PoC is a separate, human-run manual step.)
  2. One exception: fix-agent. Every scan-phase agent is strictly read-only. fix-agent — invoked only by /vantage:fix-issue, /vantage:fix, or /vantage:fix-diff, never automatically — is the sole agent allowed to edit the target repository's source code, and only to implement an already-validated finding's remediation. See "Fixing findings" below.
  3. Artifacts are the single source of truth. Every phase reads the previous phase's artifact and writes its own — no shared memory between agents.
  4. Validate before reporting or fixing. No finding reaches a report, and no finding gets fixed, without passing validator-agent first.
  5. Impact-first. Critical → High → Medium before Low/Informational.
  6. Never block on the user. If scope.json is missing, auto-generate it from ${CLAUDE_PLUGIN_ROOT}/artifacts/recon/scope.json.template (a plugin asset) with sane defaults and proceed. If the user's request implies a platform ("this is an Android app", "review this iOS codebase" → mobile; otherwise → web), set platform accordingly instead of always defaulting to web.

Read the full file on GitHub · 152 lines

Changes

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.

  1. 10d ago First seen · 152 lines · 230 tokens per session scan A 5d4600bd4806

Subscribe to this mod's changes

vantage is a skill published in the GitHub repository tinoimammp/vantage-security-agent (4 stars, last pushed 1mo ago), licensed MIT. It adds 230 tokens to every session and 2,179 once invoked, about $0.0011 per session on Opus 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.

Related

Other skills, from other repositories

sast-semgrep

Static application security testing (SAST) using Semgrep for vulnerability detection, security code review, and secure coding guidance with OWASP and CWE framework mapping. Use when: (1) Scanning code for security vulnerabilities across multiple languages, (2) Performing security code reviews with pattern-based…

AgentSecOps/SecOpsAgentKit · 116 tokens

sast-semgrep

Static application security testing (SAST) using Semgrep for vulnerability detection, security code review, and secure coding guidance with OWASP and CWE framework mapping. Use when: (1) Scanning code for security vulnerabilities across multiple languages, (2) Performing security code reviews with pattern-based…

rohunj/claude-build-workflow · 116 tokens

secure-code-review

Performs a structured security code review against OWASP ASVS 4.0.3 verification requirements and CWE Top 25. Auto-invoked on pull request reviews, when code touching authentication, authorization, cryptography, or input handling is shared. Produces findings mapped to ASVS controls and CWE identifiers with severity…

UnitOneAI/SecuritySkills · 74 tokens

Mixed-Language Monorepos

This skill should be used when the user is auditing a "polyglot monorepo", "multi-language codebase", "microservices with different languages", "Go + Python + TypeScript", or any codebase with services written in different programming languages. Provides strategies for cross-service security analysis and unified…

allsmog/vuln-scout · 71 tokens

review-pr

Diff-aware PR security review with verified findings and PR comment payload.

allsmog/vuln-scout · 16 tokens

verify-requirements

Help a developer check the code they just changed against their company security requirements — or, if none are configured, against a built-in best-practices baseline. Scopes to the current diff, dispatches the appsec-reviewer subagent to grade only the triggered requirements, and prints concrete, code-aware guidance…

appsec-foundry/appsec-advisor · 105 tokens