AzureAI-CopilotStudio-PersonalAgent-Instructions: Skill for Claude Code

.claude/skills/azureAI-optimize/SKILL.md

azureAI-optimize is a skill for Claude Code from cgfixit/AzureAI-CopilotStudio-PersonalAgent-Instructions. It costs 39 tokens per session (1,737 once invoked), scanned A, original, MIT.

A repository-optimization skill for a documentation and prompt library containing instructions for Azure AI o3 personal agents. It analyzes examples, documentation consistency, security, CI checks, and missing content.

In plain words
What is it for?
Use it to improve Azure AI agent examples, add checks such as Markdown linting and link validation, harden repository settings, and suggest new domain coverage.
Why use it?
It helps find unfinished placeholders, missing instruction sections, README mismatches, workflow gaps, and security weaknesses in a repository without a build system or tests.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths.

This is cgfixit/AzureAI-CopilotStudio-PersonalAgent-Instructions's own configuration. It tells Claude Code how to work on AzureAI-CopilotStudio-PersonalAgent-Instructions itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything AzureAI-CopilotStudio-PersonalAgent-Instructions configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/cgfixit/AzureAI-CopilotStudio-PersonalAgent-Instructions/main/.claude/skills/azureAI-optimize/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/cgfixit/AzureAI-CopilotStudio-PersonalAgent-Instructions

Made for: Claude Code.

Wrote 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.

agentmods badge for azureAI-optimize

README.md
[![agentmods](https://agentmods.dev/badge/skills/cgfixit/azureai-copilotstudio-personalagent-instructions/azureai-optimize/github.svg)](https://agentmods.dev/skills/cgfixit/azureai-copilotstudio-personalagent-instructions/azureai-optimize)
Your own site
<a href="https://agentmods.dev/skills/cgfixit/azureai-copilotstudio-personalagent-instructions/azureai-optimize"><img src="https://agentmods.dev/badge/skills/cgfixit/azureai-copilotstudio-personalagent-instructions/azureai-optimize/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.

agentmods 80×15 button for azureAI-optimize

Your own site · 80×15
<a href="https://agentmods.dev/skills/cgfixit/azureai-copilotstudio-personalagent-instructions/azureai-optimize"><img src="https://agentmods.dev/badge/skills/cgfixit/azureai-copilotstudio-personalagent-instructions/azureai-optimize.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,737 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00039 $0.01737
Opus 5 $0.00019 $0.00869
Sonnet 5 $0.00008 $0.00347
Haiku 4.5 $0.00004 $0.00174

Measured 10d ago against content hash fb53d3f732f2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

azureAI-optimize 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 10d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (analyze.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.claude/skills/azureAI-optimize/SKILL.md · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Optimize the AzureAI-CopilotStudio-PersonalAgent-Instructions repository. This is a documentation/prompt-engineering library (no build system, no tests). Every deliverable is a Markdown file containing system instructions for enterprise AI personal agents.

Step 1: Run the analysis driver

bash .claude/skills/azureAI-optimize/analyze.sh .

Read the output carefully. It reports:

  1. Unfilled placeholders in examples/ (bugs — these should be filled)
  2. Missing core sections per example (Purpose, Core Mission, Forbidden Actions, Escalation, Security, Source Hierarchy)
  3. Azure AI o3 reasoning protocol presence/absence per file
  4. README ↔ examples/ consistency (files missing from the README structure block)
  5. CI workflow gaps (markdown lint, link check, placeholder audit)
  6. Security hardening (action pinning, CODEOWNERS, branch protection)
  7. Domain coverage (existing vs suggested new domains)

Step 2: Pick an optimization category and execute

Based on the analysis output and the user's request, choose one or more of these categories. If the user didn't specify, pick the highest-impact items from the analysis.

A. Enhance examples for Azure AI Enterprise o3

The examples/Network&SecurityAgent.md is the reference implementation for o3 optimization — it includes a ## Reasoning Protocol (o3-Optimized) section with a structured pre-response checklist (QUERY TYPE → LAYER/DOMAIN → ENVIRONMENT ASSUMPTIONS → GROUNDING CHECK → VERSION STRICTNESS → FAILURE MODES → SELF-CRITIQUE → OUTPUT DECISION) and explicit confidence rules.

For each example flagged as ENHANCE in the analysis:

  1. Read examples/Network&SecurityAgent.md sections 2 (Reasoning Protocol) and 3 (Response Modes) as the pattern to follow.
  2. Add a domain-appropriate ## Reasoning Protocol (o3-Optimized) section after Core Mission. Adapt the checklist dimensions to the domain (e.g., for PowerShell: EDITION → MODULE AVAILABILITY → COMPATIBILITY → ERROR HANDLING STRATEGY; for YARA: RULE TYPE → TARGET ARTIFACT → FP RISK → PERFORMANCE IMPACT).
  3. Add explicit confidence-surfacing rules: state confidence with source, escalate below 70%.
  4. Add a ## Response Modes table mapping trigger phrases to output modes (Procedure, Quick Fact, Troubleshoot, etc.).
  5. Preserve all existing content — these are additive enhancements.

Read the full file on GitHub · 105 lines

Files

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.

Changes

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.

  1. 10d ago First seen · 105 lines · 39 tokens per session scan A fb53d3f732f2

Subscribe to this mod's changes

azureAI-optimize is a skill published in the GitHub repository cgfixit/AzureAI-CopilotStudio-PersonalAgent-Instructions (1 stars, last pushed 8d ago), licensed MIT. It adds 39 tokens to every session and 1,737 once invoked, about $0.0002 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.