apply

A command for applying changes from an OpenAPI description across an entire codebase. It updates generated API code and the components, pages, and utilities that use changed API fields or types.

In plain words
What is it for?
Detecting API-description changes, finding affected files, planning updates, applying approved edits, and checking the result.
Why use it?
It handles the knock-on effects of API changes, such as renamed fields or altered types, instead of leaving outdated usages behind. It prepares a change plan for approval and can run a TypeScript check afterward when available.

Command

Part of the oas plugin — 6 skills, 6 commands shipped together

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/jhlee0409/claude-plugins/apply
Clone the repo
git clone --depth 1 https://github.com/jhlee0409/claude-plugins

Or install oas, the plugin that ships this one along with the rest of its 6 skills, 6 commands.

Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,541 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 $0.00017 $0.03541
Opus 5 $0.00009 $0.01770
Sonnet 5 $0.00003 $0.00708
Haiku 4.5 $0.00002 $0.00354

Measured 2d ago against content hash 54a46286a3b7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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.

plugins/oas/commands/apply.md · 568 lines

How it starts

The opening of the file, as written. The whole thing — 568 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OpenAPI Apply

Apply OpenAPI spec changes throughout your entire codebase. This command handles the complete ripple effect - updating not just generated API code, but also all components, pages, and utilities that use the changed APIs.

This is the killer feature: When an API field is renamed or a type changes, this command finds and updates EVERY usage automatically.


EXECUTION INSTRUCTIONS

When /oas:apply is invoked, Claude MUST perform these steps in order:

Step 0: MCP Dependency Check

Invoke skill: mcp-dependency

  • Verify OpenAPI Sync MCP server is installed
  • If not available, offer to install via npm install -g @jhlee0409/openapi-sync-mcp
  • Only proceed after MCP is confirmed available
  1. Use skill: cache-manager - Detect spec changes (diff)
  2. Load mapping - Read usage mapping from /oas:map
  3. Analyze changes - Classify each change type
  4. Calculate impact - Find all affected files
  5. Generate change plan - Create detailed modification plan
  6. User confirmation - Show plan and get approval
  7. Apply changes - Execute modifications with Edit tool
  8. Verify - Run TypeScript check if available
  9. Report - Show summary of all changes

Usage

# Apply all pending changes
/oas:apply

# Preview only (recommended first)
/oas:apply --dry-run

# Apply specific change only
/oas:apply --change=User.status

# Skip confirmation
/oas:apply --yes

# Apply with automatic TypeScript fix
/oas:apply --fix

Change Types & Handling

Type 1: Field Renamed

Spec Change:

# Before
User:
  properties:
    userName: { type: string }

# After
User:
  properties:
    name: { type: string }  # Renamed from userName

Impact Analysis:

Field renamed: User.userName → User.name

Affected locations:
  1. src/entities/users/model/types.ts:5
     - interface User { userName: string }
     + interface User { name: string }

  2. src/pages/users/[id].tsx:25
     - <h1>{user.userName}</h1>
     + <h1>{user.name}</h1>

  3. src/features/user-profile/UserCard.tsx:18
     - const displayName = user.userName
     + const displayName = user.name

  4. src/utils/formatters.ts:12
     - return `${user.userName} (${user.email})`
     + return `${user.name} (${user.email})`

Total: 4 files, 4 changes

Read the full file on GitHub · 568 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 · 568 lines · 17 tokens per session scan A 54a46286a3b7

Subscribe to this mod's changes

apply is a command published in the GitHub repository jhlee0409/claude-plugins (4 stars, last pushed 7mo ago), licensed MIT. It adds 17 tokens to every session and 3,541 once invoked, about $0.0001 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.