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.
/plugin marketplace add geledek/enterprise-ai-transformation-skills/plugin install enterprise-ai-transformation-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/geledek/enterprise-ai-transformation-skills/tech-agent-guardrail)<a href="https://agentmods.dev/skills/geledek/enterprise-ai-transformation-skills/tech-agent-guardrail"><img src="https://agentmods.dev/badge/skills/geledek/enterprise-ai-transformation-skills/tech-agent-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/geledek/enterprise-ai-transformation-skills/tech-agent-guardrail"><img src="https://agentmods.dev/badge/skills/geledek/enterprise-ai-transformation-skills/tech-agent-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 | $0.00148 | $0.01842 |
| Opus 5 | $0.00074 | $0.00921 |
| Sonnet 5 | $0.00030 | $0.00368 |
| Haiku 4.5 | $0.00015 | $0.00184 |
Grade A, and why
tech-agent-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 12d 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 — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tech — Agentic AI Governance Check (IMDA)
A four-dimension governance assessment for any AI agent deployment. Runs IMDA's Model AI Governance Framework (Agentic AI, 2026) iteratively across the agent lifecycle.
The framework is iterative — not a one-time gate. If anomalies appear in monitoring (Dimension 3), re-run Dimensions 1 and 2.
Verdict vocabulary (stable output contract): Deploy / Deploy-with-conditions / Do-not-deploy-until-gaps-addressed. This governs the agent's autonomy and accountability; where the underlying data may legally run is tech-data-deployment.
Dimension 1: Assess and Bound the Risks Upfront
Core question: Is this use case suitable for an agent, and how do we limit its blast radius by design?
SUITABILITY CHECK:
- What is the intended scope of the agent's actions? (Tasks it can take, data it can access, systems it can touch)
- What is the blast radius if the agent takes an unintended action? (Internal-only / operational / customer-facing / regulatory)
- Is this use case suitable for autonomous operation, or does it require a human decision-maker in the loop?
RISK SCORING: For each of the following risk dimensions, rate LOW / MEDIUM / HIGH:
- Impact — what is the worst-case consequence of an agent error?
- Likelihood — how often could errors occur given current controls?
- Recovery — how quickly and completely can an error be reversed?
STRUCTURAL BOUNDS: Agents must be bounded by design, not by prompt. Identify:
- Which tools does this agent have access to? (Should it have access to all of them, or should access be scoped narrower?)
- What data can it read? What data can it modify?
- Does it operate with a single all-powerful agent pattern? (Red flag — avoid; use scoped agents instead)
- What authorizations and identity credentials are issued for this agent?
Output: SUITABILITY | RISK SCORES (impact/likelihood/recovery) | STRUCTURAL BOUNDS | AGENT IDENTITY STATUS
Dimension 2: Make Humans Meaningfully Accountable
What ships with it
1 file 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.
- 12d ago First seen · 164 lines · 148 tokens per session scan A ff97ed720e8c
tech-agent-guardrail is a skill published in the GitHub repository geledek/enterprise-ai-transformation-skills (9 stars, last pushed 2mo ago), licensed MIT. It adds 148 tokens to every session and 1,842 once invoked, about $0.0007 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.
Other skills, from other repositories
ai-interaction-pattern-advisor
Advises WHICH AI interaction pattern fits a product, service, or workflow — at what level of automation, with what trust mechanics and what organizational change. Acts as a senior Service Designer and AI Transformation specialist. Use whenever the user is deciding how AI should show up in an experience, or is…
ai-act-classification
Classify AI systems and GPAI models under the current EU AI Act. Use for Article 5 prohibited-practice screening, Article 6 and Annex I/III high-risk analysis, Article 6(3) exceptions, Article 50 transparency duties, GPAI duties, role allocation, deadlines, or an evidence-backed classification memo.
ai-act-compliance
Assess and build an EU AI Act compliance programme. Use for inventories, role maps, deadline readiness, Article 4 AI literacy, high-risk provider or deployer controls, GPAI governance, policy roadmaps, remediation plans, or executive compliance status.
ai-vendor-assessment
Assess an AI vendor, model provider, or supplier relationship. Use for EU AI Act role and evidence checks, GDPR processor terms, security and resilience review, model-change controls, incident routes, audit rights, contractual redlines, or a go/no-go procurement recommendation.
dpia-ai
Run or review a GDPR data protection impact assessment for an AI system. Use for Article 35 trigger screening, necessity and proportionality, profiling and automated decisions, bias and explainability risks, mitigations, DPO consultation, Article 36 prior consultation, or DPIA and EU AI Act FRIA coordination.
governance-documentation
Create, review, or organise EU AI Act governance evidence. Use for Article 11 and Annex IV technical documentation, logs, quality management, conformity records, declarations, registration, deployer records, post-market monitoring, incident files, evidence indexes, or review packs.