optimization-policy-designer

optimization-policy-designer is a skill for Claude Code, Codex from CloudChef/atlasclaw-providers. It costs 34 tokens per session (564 once invoked), scanned A, original, Apache-2.0.

An editor for the saved SmartCMP cost-optimization policy, including its rules, scope, severity, remediation text, notifications, and task definition.

In plain words
What is it for?
Use it to read the current policy and prepare complete replacement rule content or changed editor fields without publishing or executing the policy.
Why use it?
It helps you change the requested part of a policy while keeping the rest of the policy contract intact for manual review.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to read the current policy and prepare complete replacement rule content or changed editor fields without publishing or executing the policy.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/cloudchef/atlasclaw-providers/optimization-policy-designer
Install

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.

Any agent
npx skills add CloudChef/atlasclaw-providers --skill optimization-policy-designer
Clone the repo
git clone --depth 1 https://github.com/CloudChef/atlasclaw-providers

Made for: Claude Code, 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 optimization-policy-designer

README.md
[![agentmods](https://agentmods.dev/badge/skills/cloudchef/atlasclaw-providers/optimization-policy-designer.svg)](https://agentmods.dev/skills/cloudchef/atlasclaw-providers/optimization-policy-designer)
Your own site
<a href="https://agentmods.dev/skills/cloudchef/atlasclaw-providers/optimization-policy-designer"><img src="https://agentmods.dev/badge/skills/cloudchef/atlasclaw-providers/optimization-policy-designer.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 564 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 $0.00034 $0.00564
Opus 5 $0.00017 $0.00282
Sonnet 5 $0.00007 $0.00113
Haiku 4.5 $0.00003 $0.00056

Measured 8d ago against content hash d5e11aa6354b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

optimization-policy-designer 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/read_current_policy.py), 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.

providers/SmartCMP-Provider/skills/optimization-policy-designer/SKILL.md · 59 lines

What it actually says

optimization-policy-designer

Read the current saved cost-optimization policy and produce user-directed replacement content.

Workflow

  1. Always call smartcmp_read_current_optimization_policy first. Never ask for a policy ID already supplied by page Context.
  2. Treat the returned rule, scope, resource types, severity, remediation text, notifications, and task definition as one policy contract.
  3. Apply only the requested change. Preserve unrelated fields and the current expression language.
  4. Return the complete updated ruleContent with no ellipses. If any other editor field changes, return a complete JSON object containing every changed field and its full replacement value.
  5. Call out assumptions when the current policy or user request lacks metric, billing, resource-state, or remediation evidence. Never fabricate a metric or Provider field.
  6. State that the output is for manual review and copying into CMP. Do not claim that the policy was saved, enabled, executed, or published.

Safety

  • No policy or remediation write APIs.
  • No recommendation execution.
  • Keep cost-optimization category and resource-type gates intact unless the user explicitly asks to change them.
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 · 59 lines · 34 tokens per session scan A d5e11aa6354b

Subscribe to this mod's changes

optimization-policy-designer is a skill published in the GitHub repository CloudChef/atlasclaw-providers (15 stars, last pushed 5d ago), licensed Apache-2.0. It adds 34 tokens to every session and 564 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 2026-08-30.