sdd-change-apply

A command for implementing an approved change proposal in a codebase. A change proposal describes added, modified, or removed requirements, an implementation plan, testing needs, and success measures.

In plain words
What is it for?
Use it to apply changes such as adding two-factor authentication, migrating to GraphQL, or refactoring an authentication service, while following project context, feature-flag, and testing requirements.
Why use it?
It provides a controlled path from an agreed design to code and checks that the proposal is approved before implementation begins.

Command for Claude Code

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.

agentmods
npx agentmods add commands/nahisaho/codegraphmcpserver/sdd-change-apply
Clone the repo
git clone --depth 1 https://github.com/nahisaho/CodeGraphMCPServer

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,087 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.04087
Opus 5 $0.00000 $0.02044
Sonnet 5 $0.00000 $0.00817
Haiku 4.5 $0.00000 $0.00409

Measured 2d ago against content hash fa3c6e23d29b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sdd-change-apply 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 2d 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.

.claude/commands/sdd-change-apply.md · 764 lines

How it starts

The opening of the file, as written. The whole thing — 764 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SDD Change Apply Command

Apply a change proposal to the codebase.


Instructions for GitHub Copilot

You are executing the #sdd-change-apply [change-name] command to implement an approved change proposal.

Command Format

#sdd-change-apply add-2fa
#sdd-change-apply migrate-to-graphql
#sdd-change-apply refactor-auth-service

Your Task

Implement the changes defined in the change proposal, following constitutional governance and best practices.


Process

1. Read Change Proposal

IMPORTANT: Read the approved change proposal first:

# Read proposal
storage/changes/{{change-name}}-proposal.md

Extract:

  • ADDED requirements
  • MODIFIED requirements
  • REMOVED requirements
  • Implementation plan
  • Testing requirements
  • Success metrics

Verify Approval:

  • Status must be "Approved" (not "Proposed" or "Rejected")
  • If not approved, abort and notify user

2. Read Steering Context (Article VI)

# Read these files
steering/product.md      # Product context
steering/structure.md    # Architecture patterns
steering/tech.md         # Technology stack

3. Set Up Feature Flag

Create Feature Flag (for gradual rollout):

// lib/feature-flags/flags.ts

export const FEATURE_FLAGS = {
  // ... existing flags ...

  enable_{{feature}}: {
    enabled: false,  // Start disabled
    description: '{{CHANGE_DESCRIPTION}}',
    rolloutPercentage: 0,
  },
} as const;

Update Configuration:

// lib/feature-flags/config.ts

export function isFeatureEnabled(flag: keyof typeof FEATURE_FLAGS): boolean {
  if (process.env.NODE_ENV === 'test') {
    return true; // Always enabled in tests
  }

  const config = FEATURE_FLAGS[flag];
  if (!config.enabled) return false;

  // Gradual rollout logic
  return Math.random() * 100 < config.rolloutPercentage;
}

4. Implement Changes (Library-First - Article I)

For Each ADDED Requirement:

Step 4.1: Create Library Module

Read the full file on GitHub · 764 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. 2d ago First seen · 764 lines · 0 tokens per session scan A fa3c6e23d29b

Subscribe to this mod's changes

sdd-change-apply is a command published in the GitHub repository nahisaho/CodeGraphMCPServer (12 stars, last pushed 8mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,087 tokens. 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.