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 markoblogo/abvx-agent-skills --skill authorized-security-routergit clone --depth 1 https://github.com/markoblogo/abvx-agent-skillsWrote 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/markoblogo/abvx-agent-skills/authorized-security-router)<a href="https://agentmods.dev/skills/markoblogo/abvx-agent-skills/authorized-security-router"><img src="https://agentmods.dev/badge/skills/markoblogo/abvx-agent-skills/authorized-security-router/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/markoblogo/abvx-agent-skills/authorized-security-router"><img src="https://agentmods.dev/badge/skills/markoblogo/abvx-agent-skills/authorized-security-router.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00078 | $0.01263 |
| Opus 5 | $0.00039 | $0.00632 |
| Sonnet 5 | $0.00016 | $0.00253 |
| Haiku 4.5 | $0.00008 | $0.00126 |
Grade A, and why
authorized-security-router 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.
How it starts
The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Authorized Security Router
Route security work before acting. This skill is for authorized defensive analysis, triage, and reporting. It is not an exploitation, evasion, credential, persistence, phishing, or C2 playbook.
Scope Gate
Before selecting a route, establish:
- authorization: own system, internal review, client-approved scope, CTF/lab, or inspect-only public repository/artifact review;
- target boundary: repository, app, package, binary, API, URL, firmware image, sample hash, or document set;
- action level: inspect-only, local static analysis, local sandbox analysis, browser verification, report-only, or remediation planning;
- prohibited actions: no unauthorized access, no destructive testing, no live exploitation, no credential extraction, no persistence, no evasion, no phishing, no C2, no scope expansion.
Public review means inspect-only review of public repositories or static artifacts. It does not authorize interacting with public URLs, third-party apps, production APIs, login flows, or browser-driven security testing. URL, app, API, and browser-facing security routes require own-system, client-approved, internal, or lab/CTF authorization.
If scope is unclear or the request asks for offensive execution, stop and ask for a safer authorized framing.
Allowed Routes
Use the smallest defensive route that fits the task:
| Target / intent | Route | Pair with |
|---|---|---|
| APK or mobile app review | Manifest, permissions, redacted secret indicators, network endpoints, package metadata, static call-chain notes | evidence-ledger-research |
| Static binary triage | File metadata, strings, imports, symbols, packer indicators, suspicious capability inventory | evidence-ledger-research |
| Frontend JS security review | Source maps, bundled endpoints, dangerous DOM sinks, token handling, request signing logic, redacted secret indicators | browser-verification, web-quality-audit |
| Firmware or IoT inventory | Filesystem layout, services, redacted credential indicators, exposed configs, SBOM hints, update mechanism notes | evidence-ledger-research |
| Malware or suspicious sample triage | Hashes, strings, YARA/Sigma candidate indicators, behavior hypotheses, sandbox-safe report plan | evidence-ledger-research |
| API or GraphQL audit | Auth boundaries, object-level access checks, token handling, schema exposure, unsafe defaults | web-quality-audit when browser-facing |
| LLM or agent security review | Prompt injection surface, tool permission boundaries, data exfil paths, memory poisoning risks | agents-best-practices |
| Supply chain audit | SBOM, dependency risk, redacted secret indicators, CI/CD exposure, package provenance, release integrity | delivery-preflight-gate |
| Security issue intake | Classify severity, affected surface, evidence needed, next actor, and remediation owner | repo-issue-triage |
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 119 lines · 78 tokens per session scan A 26109595521c
authorized-security-router is a skill published in the GitHub repository markoblogo/abvx-agent-skills (16 stars, last pushed yesterday), licensed MIT. It adds 78 tokens to every session and 1,263 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
cli-e2e
Write, modify, or debug Docker-based Composio CLI end-to-end tests under ts/e2e-tests/cli, including binary invocation, fixture isolation, output assertions, and package manifests. Use for CLI E2E test suites only; use cli-command for CLI source implementation.
trace
Dispatch trace subagent to investigate unknown issues — reproduces, traces, and reports root cause for fix handoff.
codex-agent
Use when you want a second-opinion review via Codex CLI, cross-verification after another agent implements changes, debugging help, or alternative implementation proposals. Requires Codex CLI to be installed and authenticated.
openlore-analyze-codebase
Run a full static OpenLore analysis and summarize architecture, call graph, refactoring issues, and duplicate code. Use when asked to analyze, map, or assess a codebase without LLM inference.
css-debug
Use this skill to diagnose CSS and frontend layout issues such as positioning, overflow clipping, Tailwind class conflicts, z-index stacking, and React rendering visibility problems.
config-validator
Validate AIWG configuration files and project setup for correctness and completeness.