agentmods.dev

change-control

change-control is a skill for Claude Code, Codex from getnable/finopsmcp. It costs 36 tokens per session (297 once invoked), scanned A, original, Apache-2.0.

A procedure for controlling infrastructure changes when an organization records SOC 2 change-management evidence. SOC 2 is an audit framework for controls over service operations and security.

In plain words
What is it for?
Use it when deploying or changing infrastructure under a freeze, when approval evidence is requested, or when preparing a change-evidence report.
Why use it?
It makes change-freeze decisions, approvals, and recorded evidence explicit while preventing unsafe overrides such as force-pushing protected branches.

Skill for Claude CodeCodex

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

not rated 20repo +1 6d ago A scan 36 tokens original Apache-2.0

Good fit Use it when deploying or changing infrastructure under a freeze, when approval evidence is requested, or when preparing a change-evidence report.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/getnable/finopsmcp/change-control
View source ↗ getnable/finopsmcp getnable.com
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 getnable/finopsmcp --skill change-control
Clone the repo
git clone --depth 1 https://github.com/getnable/finopsmcp

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 change-control

README.md
[![agentmods](https://agentmods.dev/badge/skills/getnable/finopsmcp/change-control/github.svg)](https://agentmods.dev/skills/getnable/finopsmcp/change-control)
Your own site
<a href="https://agentmods.dev/skills/getnable/finopsmcp/change-control"><img src="https://agentmods.dev/badge/skills/getnable/finopsmcp/change-control/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 change-control

Your own site · 80×15
<a href="https://agentmods.dev/skills/getnable/finopsmcp/change-control"><img src="https://agentmods.dev/badge/skills/getnable/finopsmcp/change-control.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 297 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 $0.00036 $0.00297
Opus 5.5 $0.00014 $0.00119
Sonnet 5.5 $0.00007 $0.00059
Haiku 4.5 $0.00004 $0.00030

Measured 20d ago against content hash f8a890f05b9c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

change-control 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 20d 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.

packs/change-control/skills/change-control/SKILL.md · 25 lines

What it actually says

Change control

This organization keeps change-management evidence (SOC 2 CC8.1) from nable's guard ledger. Every infrastructure change an agent attempts is recorded with what the guard decided and who approved it.

  • During a change freeze, the guard asks before deploys and denies teardowns. When it asks, tell the user what the change is, which freeze is in force and until when, and let them decide. Do not look for another command that does the same thing, and never retry a denied command in another form.
  • Never merge with --admin, force-push a protected branch, or change branch protection or rulesets. Propose the change to a person instead.
  • When asked for change evidence, run nable pack report io.github.getnable/change-control cc8.1-evidence --since 90d (add --json for the records). Say plainly that it is evidence drawn from the guard ledger, not a SOC 2 report or a certification.
  • Approval chains the pack's adapter finds in CODEOWNERS and GitHub exports are proposals. Show them to the user; never confirm an org fact yourself.
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. 20d ago First seen · 25 lines · 36 tokens per session scan A f8a890f05b9c

Subscribe to this mod's changes

change-control is a skill published in the GitHub repository getnable/finopsmcp (20 stars, last pushed 6d ago), licensed Apache-2.0. It adds 36 tokens to every session and 297 once invoked, about $0.0001 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 2026-10-17.

Cost OptimizationDevOps and cloudSecurityaiawsazureclaudecost
Related

change-control compared with skills from other repositories

change-control next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
change-controlgetnable/finopsmcpSkill206d agoApache-2.0A36Claude Code, Codex
cloud-cost-agentdautovri/cloud-cost-agentSkill22mo agoMITA83Claude Code
notionArvo-AI/auroraSkill454yesterdayApache-2.0A23Claude Code
datadogArvo-AI/auroraSkill454yesterdayApache-2.0A28Claude Code
scalewayArvo-AI/auroraSkill454yesterdayApache-2.0A29Claude Code
ak-cloud-deployyaalalabs/agent-kernelSkill192yesterdayApache-2.0A177Claude Code, Codex
aws-cost-opsautomateyournetwork/netclawSkill715yesterdayApache-2.0A45Claude Code, Codex