AzureAI-CopilotStudio-PersonalAgent-Instructions: Skill for Codex

.codex/skills/sol-optimize/SKILL.md

sol-optimize is a skill for Codex from cgfixit/AzureAI-CopilotStudio-PersonalAgent-Instructions. It costs 73 tokens per session (777 once invoked), scanned A, original, MIT.

A procedure for reviewing and minimally updating example instruction files for GPT-5.6 Sol, an OpenAI model family. It preserves the examples' safety rules, source priorities, escalation behavior, and output requirements.

In plain words
What is it for?
Analyze selected example files, apply Sol-specific prompt improvements, and validate the changed examples against the procedure.
Why use it?
It helps migrate examples focused on older reasoning models without weakening their existing safeguards or changing their intended behavior.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: mentions Codex; $skill-name invocation.

This is cgfixit/AzureAI-CopilotStudio-PersonalAgent-Instructions's own configuration. It tells Codex 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/.codex/skills/sol-optimize/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/cgfixit/AzureAI-CopilotStudio-PersonalAgent-Instructions

Made for: Codex.

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 sol-optimize

README.md
[![agentmods](https://agentmods.dev/badge/skills/cgfixit/azureai-copilotstudio-personalagent-instructions/sol-optimize.svg)](https://agentmods.dev/skills/cgfixit/azureai-copilotstudio-personalagent-instructions/sol-optimize)
Your own site
<a href="https://agentmods.dev/skills/cgfixit/azureai-copilotstudio-personalagent-instructions/sol-optimize"><img src="https://agentmods.dev/badge/skills/cgfixit/azureai-copilotstudio-personalagent-instructions/sol-optimize.svg" alt="Measured on agentmods" height="20"></a>
Per session 73 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 777 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 $0.00073 $0.00777
Opus 5 $0.00036 $0.00388
Sonnet 5 $0.00015 $0.00155
Haiku 4.5 $0.00007 $0.00078

Measured 8d ago against content hash 6ac4f530d231, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

sol-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 8d 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.

.codex/skills/sol-optimize/SKILL.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sol Optimize

Optimize deployable examples only. Do not edit TEMPLATE.md, CI, or unrelated repo surfaces unless the user explicitly expands scope.

Workflow

  1. Establish scope.
    • If the user names an examples/*.md file, target only that file.
    • Otherwise inventory every example (with the sol suffix in file name)and select the smallest coherent set with a concrete Sol-specific problem.
    • Run python .codex/scripts/repo_audit.py analyze . before editing.
    • Treat its o3 guidance result as baseline hygiene, not proof of Sol readiness.
  2. Refresh current model guidance.
    • Use $openai-docs to fetch the live GPT-5.6 model guidance and its Prompting best practices section.
    • If that skill is unavailable, use only https://developers.openai.com/api/docs/guides/model-guidance?model=gpt-5.6.
    • Treat live OpenAI documentation as canonical. Do not hardcode pricing, limits, availability, or optional feature behavior in example prompts.
  3. Audit each target against the Sol rubric below.
  4. Make the smallest behavior-preserving edit in the file's existing dialect.
  5. Validate every changed example and report measured versus wording-only results.

Sol Rubric

Preserve domain facts and every safety invariant: authoritative-source hierarchy, version strictness, forbidden actions, escalation, security/privacy, connected-tool scope, checkpoints, and required output formats.

Prefer:

  • lean, outcome-oriented instructions that state each rule once;
  • explicit goals, context, hard constraints, required evidence, success criteria, stopping conditions, and output format;
  • one clear autonomy and approval policy that permits safe in-scope work and stops before external, destructive, costly, or scope-expanding actions;
  • targeted clarification only when ambiguity materially changes correctness or safety;
  • concise, precise descriptions for tools that are actually available;
  • observable verification before claiming completion.

Remove or tighten only when redundant or harmful:

Read the full file on GitHub · 74 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. 8d ago First seen · 74 lines · 73 tokens per session scan A 6ac4f530d231

Subscribe to this mod's changes

sol-optimize is a skill published in the GitHub repository cgfixit/AzureAI-CopilotStudio-PersonalAgent-Instructions (1 stars, last pushed 6d ago), licensed MIT. It adds 73 tokens to every session and 777 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 2026-08-31.