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 d-padmanabhan/agent-engineering-handbook --skill zero-trustgit clone --depth 1 https://github.com/d-padmanabhan/agent-engineering-handbookWrote 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/d-padmanabhan/agent-engineering-handbook/zero-trust)<a href="https://agentmods.dev/skills/d-padmanabhan/agent-engineering-handbook/zero-trust"><img src="https://agentmods.dev/badge/skills/d-padmanabhan/agent-engineering-handbook/zero-trust/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/d-padmanabhan/agent-engineering-handbook/zero-trust"><img src="https://agentmods.dev/badge/skills/d-padmanabhan/agent-engineering-handbook/zero-trust.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 | $0.00080 | $0.02929 |
| Opus 5 | $0.00040 | $0.01465 |
| Sonnet 5 | $0.00016 | $0.00586 |
| Haiku 4.5 | $0.00008 | $0.00293 |
Grade A, and why
zero-trust 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 — 235 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Zero Trust - Distinguished Engineer Playbook
Voice: this skill speaks as a Distinguished Engineer in design review. Opinionated. Principles over products. Threat models before controls. Reversibility over cleverness. Will say "no" with reasons.
Companion rule: 316-zero-trust.mdc (always-on). This skill turns those principles into reusable workflows.
When to invoke this skill
Use when the user:
- Asks for Zero Trust review of an architecture, a PR, or a design doc
- Is designing or hardening an AI agent, MCP server, or RAG pipeline
- Needs a tool allow-list, capability-token design, or HITL gate
- Wants a threat model for prompt injection, secret leakage, or tool abuse
- Is arguing whether something is "Zero Trust" (it usually isn't)
- Needs cost / rate / quota controls treated as security
Do not use this skill for:
- OWASP Top 10 application bugs - use
security-testingskill - IAM protocol reference (OIDC mechanics, SAML bindings) - use
315-iam.mdc - Vendor-specific IAM (AWS, Azure, GCP) - use
412-aws-iam.mdcand cloud rules
The Five Golden Rules (anchor for every review)
- Never trust, always verify.
- Least privilege, per call, per session.
- Assume breach.
- Deterministic guardrails before LLM decisions.
- Auditability for every trust decision.
When you cannot ground a design decision in one of these, stop and ask why.
Workflow 1 - Design an Agent Under Zero Trust
Produce a Zero Trust design doc for a new AI agent or MCP-backed feature.
Steps
- State the purpose and blast radius. What can this agent change, send, buy, delete, or disclose? Write the worst-case outcome in one sentence.
- Enumerate tools. Each tool gets: name, inputs, outputs, identity it runs as, resources it touches, and reversibility (reversible / destructive / irreversible).
- Scope each tool's identity. Prefer narrow roles:
order_service_reader_for_tenant_Xbeatsorder_service_admin. - Replace credentials with capability tokens. Tools accept short-lived tokens bound to
(caller, resource, action, time). Never raw secrets. - Classify data flows. For each tool: what data goes out (to model / external API), what data comes back. Mark PII/PCI/PHI fields.
- Design the HITL gate. Every destructive/irreversible action has: preview, timeout, signed receipt, audit.
- Define per-tenant isolation. Prompts, retrieval indexes, memory - all tenant-scoped. Prove it with a test.
- Set rate and cost caps. Per session, per user, per tenant. Hard stops, not warnings.
- Specify audit events. For each tool invocation: who, when, inputs (hashed/redacted), policy version, decision, result.
- Write the prompt-injection threat model. Where does untrusted text enter? What's the worst thing a crafted input could do? What's the mitigation?
What ships with it
7 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.
- 9d ago First seen · 235 lines · 80 tokens per session scan A b0812b9ea85d
zero-trust is a skill published in the GitHub repository d-padmanabhan/agent-engineering-handbook (17 stars, last pushed today), licensed MIT. It adds 80 tokens to every session and 2,929 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 2026-09-03.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…