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 jpantsjoha/ai-native-developer-experience --skill governance-guardrailgit clone --depth 1 https://github.com/jpantsjoha/ai-native-developer-experienceWrote 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/jpantsjoha/ai-native-developer-experience/governance-guardrail)<a href="https://agentmods.dev/skills/jpantsjoha/ai-native-developer-experience/governance-guardrail"><img src="https://agentmods.dev/badge/skills/jpantsjoha/ai-native-developer-experience/governance-guardrail/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/jpantsjoha/ai-native-developer-experience/governance-guardrail"><img src="https://agentmods.dev/badge/skills/jpantsjoha/ai-native-developer-experience/governance-guardrail.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 | $0.00056 | $0.01236 |
| Opus 5 | $0.00028 | $0.00618 |
| Sonnet 5 | $0.00011 | $0.00247 |
| Haiku 4.5 | $0.00006 | $0.00124 |
Grade A, and why
governance-guardrail 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 9d 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 — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Governance Guardrail
A policy position the team cannot cite is a policy the team will unknowingly violate.
This skill checks alignment between what the team is building and the enterprise policies, compliance frameworks, and security controls that govern it. It never invents a policy position — it surfaces gaps as explicitly owned unknowns.
When to use
- At R2/R3 risk classification, before architecture decisions are locked
- When the operating profile names a governance pointer (policy doc, compliance framework, security baseline, approved-technology list)
- Before any decision that touches data classification, residency, procurement, or approved-vendor constraints
- As a pre-condition for
adversarial-gateon high-stakes or regulated work - When
delivery-orchestratoridentifies a compliance, security, or data-handling concern
Operating model context
Governance alignment is not an audit that happens after delivery. It is a constraint that shapes architecture from day one. Discovering a compliance gap after a decision is locked is expensive; discovering it during bootstrap or spec is cheap.
This skill operates at the policy layer, above the cloud-expert skills:
gcp-expert/aws-expert/azure-expert/alibaba-expert— vendor-specific technical guardrails: IAM, data residency, cost. Use them to implement correctly within a chosen platform.governance-guardrail(this skill) — checks whether the chosen platform, stack, and data model are permitted by enterprise policy in the first place.
Route cloud-specific implementation questions to the cloud-expert skills after this skill
confirms the architecture is policy-compliant. Feed open findings into adversarial-gate
before high-stakes decisions are locked.
Procedure
1. Locate the governance pointer
The project operating profile (docs/operating-model/PROJECT-OPERATING-PROFILE.md)
should name one of:
- A policy document (URL, file path, or shared drive location)
- A compliance framework (SOC 2, ISO 27001, GDPR, HIPAA, etc.)
- An approved-technology or approved-vendor list
- A security baseline or architecture review board record
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.
- 9d ago First seen · 124 lines · 56 tokens per session scan A cb694397af28
governance-guardrail is a skill published in the GitHub repository jpantsjoha/ai-native-developer-experience (11 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 56 tokens to every session and 1,236 once invoked, about $0.0003 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
solo-legal
Use when "privacy policy", "terms of service", "legal pages", "GDPR", "CCPA", "app store legal", or project needs compliance documents. Do NOT use for NDA or contracts.
high-risk-supplier-review
Coordinate a complete high-risk supplier review from case intake through evidence checks, sanctions screening, risk scoring, remediation, human approval, verification, and publication.
evidence-freshness-review
Check supplier evidence ages against the 365-day policy, preserve evidence identifiers, and classify expired records as blocking findings.
sanctions-screening
Evaluate a supplier's supplied sanctions-screening record, preserve the screening reference, and fail closed when a possible match exists.
supplier-risk-scoring
Combine validated evidence, sanctions status, supplier tier, and remediation state into an explainable deterministic risk score and route.
violation-workflow
Process violation through escalation workflow.