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 agentmods add skills/azure-samples/eshoplite/humanizernpx skills add Azure-Samples/eShopLite --skill humanizergit clone --depth 1 https://github.com/Azure-Samples/eShopLiteWhat 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 | $0.00011 | $0.01005 |
| Opus 5 | $0.00005 | $0.00502 |
| Sonnet 5 | $0.00002 | $0.00201 |
| Haiku 4.5 | $0.00001 | $0.00101 |
Grade A, and why
humanizer 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 3d 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.
This is a copy
100% identical to humanizer — 210 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context
Use this skill whenever PAO drafts external-facing responses for issues or discussions.
- Tone must be warm, helpful, and human-sounding — never robotic or corporate.
- Brady's constraint applies everywhere: Humanized tone is mandatory.
- This applies to all external-facing content drafted by PAO in Phase 1 issues/discussions workflows.
Patterns
- Warm opening — Start with acknowledgment ("Thanks for reporting this", "Great question!")
- Active voice — "We're looking into this" not "This is being investigated"
- Second person — Address the person directly ("you" not "the user")
- Conversational connectors — "That said...", "Here's what we found...", "Quick note:"
- Specific, not vague — "This affects the casting module in v0.8.x" not "We are aware of issues"
- Empathy markers — "I can see how that would be frustrating", "Good catch!"
- Action-oriented closes — "Let us know if that helps!" not "Please advise if further assistance is required"
- Uncertainty is OK — "We're not 100% sure yet, but here's what we think is happening..." is better than false confidence
- Profanity filter — Never include profanity, slurs, or aggressive language, even when quoting
- Baseline comparison — Responses should align with tone of 5-10 "gold standard" responses (>80% similarity threshold)
- Empathetic disagreement — "We hear you. That's a fair concern." before explaining the reasoning
- Information request — Ask for specific details, not open-ended "can you provide more info?"
- No link-dumping — Don't just paste URLs. Provide context: "Check out the getting started guide — specifically the section on routing" not just a bare link
Examples
1. Welcome
Hey {author}! Welcome to Squad 👋 Thanks for opening this.
{substantive response}
Let us know if you have questions — happy to help!
2. Troubleshooting
Thanks for the detailed report, {author}!
Here's what we think is happening: {explanation}
{steps or workaround}
Let us know if that helps, or if you're seeing something different.
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.
- 3d ago First seen · 106 lines · 11 tokens per session scan A 944d6d69a671
humanizer is a skill published in the GitHub repository Azure-Samples/eShopLite (168 stars, last pushed 1mo ago), licensed MIT. It adds 11 tokens to every session and 1,005 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to humanizer, differing in 210 lines, and is treated as a copy.
Other skills, from other repositories
foundry-agent-deploy
Build, register, and wire up a Foundry Hosted Agent end-to-end on Azure: build the container to ACR, register a hosted-agent version with the azure-ai-projects SDK, grant least-privilege RBAC, configure the CopilotKit runtime App Service, and verify through the Static Web App. Use when deploying or redeploying a…
foundry-hosted-agent-maf
Author a Microsoft Agent Framework (.NET) agent that is hosted as a Foundry Hosted Agent and speaks AG-UI over the invocations protocol. Use when building, refactoring, or reviewing a .NET agent that must run as a Foundry Hosted Agent and drive a CopilotKit / AG-UI frontend. WHEN: "build a Foundry hosted agent"…
mine
Mine a project or conversation into your MemPalace — extract and store memories for later retrieval.
status
Show MemPalace status — room counts, storage usage, and palace health.
mempalace-recall
Recall protocol for MemPalace — search the palace before answering about past work, people, projects, or prior decisions. Apply when the user asks what was decided, what happened before, who someone is, what was discussed last time, or anything that may already be filed in their memory palace; or when mempalace-recall…
multi-repo-release
Prepares and validates GPT-RAG umbrella releases across component repositories and the AI Landing Zone. Use for manifest pins, changelog entries, release branches, tags, and GitHub Release notes.