Borrowing it
Nothing to install: this file belongs to cgfixit/AzureAI-CopilotStudio-PersonalAgent-Instructions. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/cgfixit/AzureAI-CopilotStudio-PersonalAgent-Instructions/main/.claude/skills/new-example/SKILL.mdgit clone --depth 1 https://github.com/cgfixit/AzureAI-CopilotStudio-PersonalAgent-InstructionsWrote 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/cgfixit/azureai-copilotstudio-personalagent-instructions/new-example)<a href="https://agentmods.dev/skills/cgfixit/azureai-copilotstudio-personalagent-instructions/new-example"><img src="https://agentmods.dev/badge/skills/cgfixit/azureai-copilotstudio-personalagent-instructions/new-example/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/cgfixit/azureai-copilotstudio-personalagent-instructions/new-example"><img src="https://agentmods.dev/badge/skills/cgfixit/azureai-copilotstudio-personalagent-instructions/new-example.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 | $0.00059 | $0.01625 |
| Opus 5.5 | $0.00024 | $0.00650 |
| Sonnet 5.5 | $0.00012 | $0.00325 |
| Haiku 4.5 | $0.00006 | $0.00162 |
Grade A, and why
new-example 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 2mo 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
New Example — full scaffold protocol
Produce a new fully-instantiated agent instruction file for the requested domain.
The output must be indistinguishable in quality from examples/incident-response.md
(the canonical shape): a standalone system prompt someone can paste into
Azure AI Studio / Copilot Studio / OpenAI Assistants / Claude Projects unedited.
Step 0: Name and scope
- Filename: kebab-case,
examples/<domain>.md(e.g.finops-governance.md). Existing filenames are frozen — never rename an existing example to make room. - Collision check: confirm the file doesn't exist and the domain doesn't substantially overlap one of the current examples (cloud-infra, incident-response, network/security, PowerShell coding, Python coding, Veeam backup/DR, YARA). If it overlaps, propose extending the existing file instead and stop for user confirmation.
Step 1: Research the domain BEFORE writing
Collect, with dates and real URLs where they exist:
- Products & versions — the 3-6 products/tools the agent will cover, each with its current major version. Honesty rule: if the domain uses real products, every version, deprecation, and behavior claim you write must be verifiable against that vendor's official docs. If you cannot verify, use clearly fictional products (like TEMPLATE.md's "Product X") — never plausible-but-invented claims about real ones.
- ≥2 critical constraints — hard, dated rules of the form the template's
[CRITICAL_CONSTRAINT_*]placeholders expect ("X was deprecated in vN (date) — never state it works in vN+1", "Feature Y requires license Z"). These anchor the file's version-strictness and later feed/red-teamtest generation. - Tiered sources — Tier 1: the domain's official docs/release notes/API references (real URLs); Tier 2: official blogs/best-practice guides; Tier 3: internal-notes categories.
- Escalation contact — fake but plausible (
<domain>[email protected], ticket process ID likeKB-<DOMAIN>-WORKFLOW). Never a real internal address. - Reasoning dimensions — the 4-8 domain-specific checklist dimensions for the o3 Reasoning Protocol (what must the agent pin down before answering: edition? platform? version? blast radius? licensing?).
- Response-mode triggers — the 4-6 phrasings users in this domain actually use, mapped to output modes (Procedure / Quick Fact / Troubleshoot / Design / Clarify).
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.
- 2mo ago First seen · 130 lines · 59 tokens per session scan A 9020ee321f13
new-example is a skill published in the GitHub repository cgfixit/AzureAI-CopilotStudio-PersonalAgent-Instructions (1 stars, last pushed 15d ago), licensed MIT. It adds 59 tokens to every session and 1,625 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 2026-08-31.
Other skills, from other repositories
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
omh-rust
This is an OMH rust workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
redteam-web-detail-pack
Routing and boundary guidance for authorized general web application security testing. Use as a web testing router when the attack surface should be dispatched to more specific web vulnerability skills.
android-pentest
A guide for authorized security testing of Android apps, covering APK inspection, runtime testing, traffic capture, code review, and function hooking. An APK is the installable package used by an Android app.
manage-schemas
Creates, views, edits, deletes, and validates note schemas for the MCP Task Orchestrator in .taskorchestrator/config.yaml — the templates that define which notes agents must fill at each workflow phase. Also recommends schema designs from a library of workflow patterns (autonomous coding loops, spec-driven teams…
queues-jobs
Implement reliable asynchronous jobs and message consumers with explicit delivery, retry and shutdown semantics. Use when adding BullMQ or another established queue, background processing or scheduled work; enqueue success is not job completion.