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 PIsberg/vibetags --skill vibetags-guardrailsgit clone --depth 1 https://github.com/PIsberg/vibetagsWrote 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/pisberg/vibetags/vibetags-guardrails)<a href="https://agentmods.dev/skills/pisberg/vibetags/vibetags-guardrails"><img src="https://agentmods.dev/badge/skills/pisberg/vibetags/vibetags-guardrails/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/pisberg/vibetags/vibetags-guardrails"><img src="https://agentmods.dev/badge/skills/pisberg/vibetags/vibetags-guardrails.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 6 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
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 | $0.00046 | $0.05681 |
| Opus 5.5 | $0.00018 | $0.02272 |
| Sonnet 5.5 | $0.00009 | $0.01136 |
| Haiku 4.5 | $0.00005 | $0.00568 |
Grade A, and why
vibetags-guardrails 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 — 294 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AUTO-GENERATED AI RULES
Generated by VibeTags | https://github.com/PIsberg/vibetags
Do not edit manually.
LOCKED FILES (DO NOT EDIT)
com.example.payment.PaymentProcessor- Reason: Tied to legacy database schema v2.3. Changes will break production payment processing. Contact the payments team before modifying.com.example.security.SecurityConfig- Reason: CRITICAL: Security configuration managed by DevOps team. Any changes require security review and approval ticket SEC-XXXXcom.example.security.SecurityConfig.getEncryptionAlgorithm()- Reason: Encryption algorithm tied to compliance requirements (PCI-DSS)com.example.security.SecurityConfig.getKeyRotationHours()- Reason: Key rotation period mandated by company policycom.example.security.SecurityConfig.getMaxLoginAttempts()- Reason: Max login attempts set by security team to prevent brute forcecom.example.security.SecurityConfig.validateToken(java.lang.String)- Reason: Token validation must match auth server exactly. Changes will break all client authenticationcom.example.service.OrderService.calculateTax(java.lang.String,double)- Reason: Tax calculation uses Avalara API integration. Credentials and endpoint configuration managed by finance team.com.example.service.OrderService.processPayment(java.lang.String,double)- Reason: Payment processing uses Stripe API v2024.10. Changes require PCI compliance review.com.example.service.OrderService.validateOrder(java.util.Map<java.lang.String,java.lang.Object>)- Reason: Order validation implements 47 business rules. Last changed in Q2 2024 after 3-month testing cycle. DO NOT MODIFY without running full test suite.com.example.testing.GoldenPayloadFixtures- Reason: These byte sequences are the partner's recorded settlement responses. Regenerating or reformatting them makes the suite agree with itself and disagree with production.
CONTEXTUAL RULES
com.example.security.SecurityConfig- Focus: This class is READ-ONLY for AI assistants. Do not suggest modifications.
- Avoid: Any changes to encryption algorithms, key sizes, or validation logic
com.example.service.InventoryService- Focus: Maintain inventory consistency across concurrent requests. All stock updates must be atomic.
- Avoid: Non-atomic read-modify-write sequences, unsynchronized shared state
com.example.service.NotificationService- Focus: Implement notification delivery with retry logic and error handling
- Avoid: Hard-coded credentials, synchronous blocking calls
com.example.service.OrderService- Focus: Maintain transactional integrity. All database operations must use proper transaction management.
- Avoid: Raw SQL queries, direct database connections without connection pooling
com.example.service.PricingService- Focus: Optimize pricing calculations for accuracy and throughput. Internal algorithms may use any efficient approach.
- Avoid: Floating-point arithmetic for monetary values — use BigDecimal internally, but note that the contract-frozen signatures use double for backwards compatibility
com.example.strategy.PaymentStrategy- Focus: Follow the Strategy pattern strictly. Each payment method should be a separate strategy class implementing this interface.
- Avoid: Monolithic if-else chains, hard-coded payment logic, single class handling all payment types
com.example.utils.StringParser- Focus: Optimize for memory usage over CPU speed. Minimize object allocations and avoid creating intermediate string objects.
- Avoid: java.util.regex, String.split(), StringBuilder in loops
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 Changed · -8 lines ebc7210a8961
- 1mo ago Changed · +11 lines a9b14b367e99
- 2mo ago First seen · 291 lines · 46 tokens per session scan A 525ffe6cebb4
vibetags-guardrails is a skill published in the GitHub repository PIsberg/vibetags (25 stars, last pushed today), licensed MIT. It adds 46 tokens to every session and 5,681 once invoked, about $0.0002 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 2026-08-30.
vibetags-guardrails compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| vibetags-guardrailsPIsberg/vibetags | Skill | 25 | today | MIT | A | 46 | Claude Code, Codex |
| java-springWrongStack/WrongStack | Skill | 404 | yesterday | MIT | A | 91 | Claude Code |
| spring-boot-developmentmanutej/luxor-claude-marketplace | Skill | 63 | 4mo ago | none | A | 31 | Claude Code |
| java-boilerplatechidekina/aria-superpowers | Skill | 2 | 1mo ago | none | A | 48 | Claude Code |
| spring-boot-engineereric861129/SKILLS_All-in-one | Skill | 52 | 6mo ago | MIT | A | 91 | Claude Code, Codex |
| java-architecteric861129/SKILLS_All-in-one | Skill | 52 | 6mo ago | MIT | A | 67 | Claude Code, Codex |
| omh-code-reviewrlaope/oh-my-hermes | Skill | 5.2k | yesterday | MIT | A | 48 | Claude Code, Codex |