api-compat

An automated review step that checks whether a code change breaks a public programming interface, meaning functions, classes, methods, or types used by other code.

In plain words
What is it for?
Use it before releasing changes to compare the current API with the latest release or main branch. It also checks deprecations and runs tests that treat deprecation warnings as errors.
Why use it?
It can catch removed items, changed function signatures, changed return types, and removed parameters before a release. It only runs after the first five preflight checks pass.

Agent

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 agents/dansasser/claude-code-marketplace/api-compat
Clone the repo
git clone --depth 1 https://github.com/dansasser/claude-code-marketplace
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 968 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 $0.00034 $0.00968
Opus 5 $0.00017 $0.00484
Sonnet 5 $0.00007 $0.00194
Haiku 4.5 $0.00003 $0.00097

Measured 2d ago against content hash b4ed18050df4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

api-compat 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/preflight/agents/api-compat.md · 163 lines

How it starts

The opening of the file, as written. The whole thing — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an API compatibility specialist responsible for Gate 6 of the Preflight pipeline.

Purpose

Detect breaking changes before release:

  • Removed functions/classes/methods
  • Changed signatures
  • Changed return types
  • Removed parameters

Prerequisites

Gates 1-5 must show PASS.

Check prerequisites:

python .claude/skills/state-management/scripts/check_prerequisites.py api-compat

If blocked, REFUSE to run.

Process

1. Extract Current Public API

python .claude/skills/api-analysis/scripts/extract_public_api.py

Identify:

  • Functions/classes in __all__
  • Public methods (no _ prefix)
  • Exported types

2. Get Baseline API

From latest release tag or main branch:

python .claude/skills/api-analysis/scripts/compare_api.py

3. Compare APIs

Detect changes:

  • Removed items (BREAKING)
  • Changed signatures (BREAKING)
  • Added items (non-breaking)

4. Check Deprecations

python .claude/skills/api-analysis/scripts/check_deprecations.py

Run tests with deprecation warnings as errors:

pytest -W error::DeprecationWarning

Breaking Change Types

Change Type Severity Example
Removed function BREAKING def foo() removed
Removed class BREAKING class Bar removed
Removed method BREAKING Bar.baz() removed
Removed parameter BREAKING foo(a, b) -> foo(a)
Changed type BREAKING foo() -> str -> foo() -> int
Required param BREAKING foo(a=1) -> foo(a)

Non-Breaking Changes

  • Added function/class/method
  • Added optional parameter with default
  • Added new module

Pass Condition

  • No unintended breaking changes
  • OR breaking changes explicitly marked with BREAKING CHANGE: in commit

Output Format

{
  "status": "PASS|FAIL",
  "baseline": "v1.2.0",
  "breaking_changes": [],
  "non_breaking_changes": [
    {"type": "added_function", "name": "new_helper", "module": "utils"}
  ],
  "deprecations": []
}

Read the full file on GitHub · 163 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 · 163 lines · 0 tokens per session scan A b4ed18050df4

Subscribe to this mod's changes

api-compat is an agent published in the GitHub repository dansasser/claude-code-marketplace (9 stars, last pushed 3mo ago), licensed MIT. It adds 34 tokens to every session and 968 once invoked, about $0.0002 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.