diff-specs

A tool for comparing two versions of an OpenAPI specification, the document that describes an HTTP API’s endpoints and data formats. It can identify breaking changes and suggest migration steps.

In plain words
What is it for?
Comparing an older and newer API specification, reviewing breaking changes, categorising differences, and planning client updates.
Why use it?
It helps find API changes that could break existing clients before a new specification is released. Results can be limited to breaking changes or read in pages for large comparisons.

Skill for Claude CodeCodex

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 skills/erraggy/oastools/diff-specs
Any agent
npx skills add erraggy/oastools --skill diff-specs
Clone the repo
git clone --depth 1 https://github.com/erraggy/oastools

Made for: Claude Code, Codex.

Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 745 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 $0.00019 $0.00745
Opus 5 $0.00010 $0.00373
Sonnet 5 $0.00004 $0.00149
Haiku 4.5 $0.00002 $0.00075

Measured 2d ago against content hash 9235ab21d21b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

diff-specs 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.

plugin/skills/diff-specs/SKILL.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Diff Two OpenAPI Specifications

Step 1: Compare the specs

⚠️ Note: The diff tool is designed for comparing versions of the same API (e.g., v1.2 vs v1.3). Diffing unrelated APIs (e.g., Stripe vs GitHub) will produce thousands of changes that aren't meaningful. If the user wants to compare different APIs, suggest exploring each one separately with the explore-api workflow.

Call the diff tool with both spec versions:

{
  "base": {"file": "<old-version-path>"},
  "revision": {"file": "<new-version-path>"}
}

To focus only on breaking changes:

{
  "base": {"file": "<old-version-path>"},
  "revision": {"file": "<new-version-path>"},
  "breaking_only": true
}

Step 2: Categorize changes

Paginating large diffs

Results are paginated (default limit: 100). When returned < total_changes, there are more changes:

{
  "base": {"file": "<old-version-path>"},
  "revision": {"file": "<new-version-path>"},
  "offset": 100, "limit": 100
}

⚠️ Strategy for large diffs: Start with breaking_only: true to see all breaking changes first — these are usually the most important and fewest. Then page through the full diff only if the user needs the complete picture. The total_changes, breaking_count, warning_count, and info_count fields always reflect the full result, even when paginated.

Present the diff results organized by severity:

  1. Breaking (critical/error) -- Changes that will break existing API consumers

    • Removed endpoints or operations
    • Removed or renamed required parameters
    • Changed response status codes
    • Narrowed allowed values (enum removals, stricter validation)
    • Changed authentication requirements
  2. Warnings -- Changes that may affect consumers

    • Deprecated endpoints
    • Changed optional parameter defaults
    • Modified response schemas (new required fields)
  3. Informational -- Non-breaking changes

    • Added endpoints or operations
    • Added optional parameters
    • Extended enum values
    • Documentation updates

Read the full file on GitHub · 95 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 · 95 lines · 19 tokens per session scan A 9235ab21d21b

Subscribe to this mod's changes

diff-specs is a skill published in the GitHub repository erraggy/oastools (5 stars, last pushed 3d ago), licensed MIT. It adds 19 tokens to every session and 745 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.