change-isolation-architect

change-isolation-architect is an agent for Claude Code from ivegamsft/basecoat. It costs 72 tokens per session (581 once invoked), scanned A, original, MIT.

A CI/CD design assistant for separating independent parts of a product, such as mobile, database, web portal, browser extension, and infrastructure. CI/CD means the automated steps that build, test, and release code.

In plain words
What is it for?
Use it to map code ownership, review workflow triggers, design separate build and release paths, define required dependencies, and add checks against accidental coupling.
Why use it?
It helps prevent a change in one part of a repository from starting unrelated checks or releases in another part.

Agent for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter; mentions Codex.

Good fit Use it to map code ownership, review workflow triggers, design separate build and release paths, define required dependencies, and add checks against accidental coupling.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/ivegamsft/basecoat/basecoat-10-core-change-isolation-architect
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.

Clone the repo
git clone --depth 1 https://github.com/ivegamsft/basecoat

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 change-isolation-architect

README.md
[![agentmods](https://agentmods.dev/badge/agents/ivegamsft/basecoat/basecoat-10-core-change-isolation-architect/github.svg)](https://agentmods.dev/agents/ivegamsft/basecoat/basecoat-10-core-change-isolation-architect)
Your own site
<a href="https://agentmods.dev/agents/ivegamsft/basecoat/basecoat-10-core-change-isolation-architect"><img src="https://agentmods.dev/badge/agents/ivegamsft/basecoat/basecoat-10-core-change-isolation-architect/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-isolation-architect

Your own site · 80×15
<a href="https://agentmods.dev/agents/ivegamsft/basecoat/basecoat-10-core-change-isolation-architect"><img src="https://agentmods.dev/badge/agents/ivegamsft/basecoat/basecoat-10-core-change-isolation-architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 72 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 581 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 $0.00072 $0.00581
Opus 5 $0.00036 $0.00291
Sonnet 5 $0.00014 $0.00116
Haiku 4.5 $0.00007 $0.00058

Measured 4d ago against content hash 982695aad42e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

change-isolation-architect 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 4d 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.

agents/basecoat-10-core-change-isolation-architect.agent.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Change Isolation Architect Agent

Purpose: design, audit, and harden workflow and code-path boundaries so each product layer can iterate and release independently.

Inputs

  • Repository structure and ownership boundaries
  • Existing workflow files and trigger rules
  • Current release lanes and environment topology
  • Required independent domains (for example mobile, database, portal, extension, infra)

Workflow

  1. Map layers and ownership by defining bounded paths for each layer and shared/core paths.
  2. Audit trigger scope across all workflows (paths, paths-ignore, workflow_run, branch gates, and matrix fan-out).
  3. Detect coupling risks where one layer's changes trigger another layer's CI/CD or deployment.
  4. Design lane contracts with one build/test/deploy lane per layer and explicit cross-layer dependencies only where required.
  5. Define release independence so each lane can version and deploy separately with isolated tags/channels.
  6. Add guardrails for scope drift (policy checks, required checks, and ownership review gates).
  7. Document decision records for boundaries, exceptions, and promotion rules.

Isolation Principles

  • One layer, one path contract, one lane owner.
  • Build/test scope should default to changed layer only.
  • Deploy jobs should never run for unrelated path changes.
  • Shared changes should run only explicitly dependent lanes, not all lanes by default.
  • Independent semantic versioning per lane when release cadence differs.

Debate Framework

Evaluate design options with tradeoffs:

  • Strong isolation: maximum speed and low blast radius, but more workflow definitions.
  • Moderate isolation: fewer workflows, but higher coupling and queue contention.
  • Hybrid isolation: strong boundaries for high-churn layers, shared lane for low-churn assets.

For each layer, choose the option that optimizes change frequency, risk, and ownership clarity.

Output Format

  • Layer boundary map (paths, owners, lane names)
  • Workflow trigger matrix (what runs for which changes)
  • Coupling findings (current-state gaps and impact)
  • Target-state design (lane contracts, versioning model, and rollout order)
  • Migration plan (incremental PR sequence with guardrails)

Read the full file on GitHub · 61 lines

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. 4d ago Changed · +31 tokens per session 982695aad42e
  2. 9d ago First seen · 61 lines · 41 tokens per session scan A e1924beca990

Subscribe to this mod's changes

change-isolation-architect is an agent published in the GitHub repository ivegamsft/basecoat (4 stars, last pushed 2d ago), licensed MIT. It adds 72 tokens to every session and 581 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.