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 vikisingh23/neuraforge-ai --skill security-reviewgit clone --depth 1 https://github.com/vikisingh23/neuraforge-aiWrote 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/vikisingh23/neuraforge-ai/security-review)<a href="https://agentmods.dev/skills/vikisingh23/neuraforge-ai/security-review"><img src="https://agentmods.dev/badge/skills/vikisingh23/neuraforge-ai/security-review/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/vikisingh23/neuraforge-ai/security-review"><img src="https://agentmods.dev/badge/skills/vikisingh23/neuraforge-ai/security-review.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 | $0.00025 | $0.00144 |
| Opus 5 | $0.00013 | $0.00072 |
| Sonnet 5 | $0.00005 | $0.00029 |
| Haiku 4.5 | $0.00003 | $0.00014 |
Grade A, and why
security-review 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 7d 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.
What it actually says
Scan code for security vulnerabilities.
What it checks
- SQL injection (string concatenation in queries)
- XSS (unsanitized user input in output)
- Hardcoded secrets (API keys, passwords, tokens in code)
- PII exposure (sensitive data in logs or error responses)
- Weak crypto, missing auth, CSRF, rate limiting gaps
For full instructions, read agents/security-review.md.
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.
- 7d ago First seen · 21 lines · 25 tokens per session scan A 931f3af160ab
security-review is a skill published in the GitHub repository vikisingh23/neuraforge-ai (4 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 25 tokens to every session and 144 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
audit
Use before releases, after large PRs, or during onboarding to run a single read-only analysis of a codebase's quality, risk, and design. The one analysis front door. Reads the glossary to resolve a selector that zooms across three layers — track, aspect, family/category/entity — then delegates to the oop-orchestrator…
pattern-implement
Use after /audit pattern-fit surfaces an opportunity, or directly on a design-pattern id, to implement that pattern into a target scope with a safe parallel-change sequence and verify it with the project's own detected commands. Resolves the pattern against the glossary and delegates to the oop-orchestrator in…
improve
Use after /audit flags problem areas, or directly on a smell/antipattern/family, to apply the smallest corrective refactor and verify it with the project's own detected commands. The FIX action reached from the audit report's Recommended Actions handoff (/fix-risks ). Resolves the selection against the glossary and…
onboarding
Use when someone is new to claude-oop-excellence and asks how to use it, where to start, what /audit does, or which command to run next — a read-only orientation to the plugin. Explains the mental model (one read-only front door, /audit; three layers; two tracks — RISK and PATTERN) and the analyze → act flow that…
glossary
Use to look up the canonical name, category, family, principle, signs, and severity of any code smell, antipattern, vulnerability, supply-chain risk, or design pattern this plugin recognizes. Read-only reference: resolve an entity by id, list every entity in a family or category, or check which corrective patterns fix…
commands-standards
Standards for authoring SDD plugin commands — frontmatter, user interaction, skill/agent invocation, CLI integration, and output formatting.