Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/dansasser/claude-code-marketplacenpx agentmods add agents/dansasser/claude-code-marketplace/api-compatWrote 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.
[](https://agentmods.dev/agents/dansasser/claude-code-marketplace/api-compat)<a href="https://agentmods.dev/agents/dansasser/claude-code-marketplace/api-compat"><img src="https://agentmods.dev/badge/agents/dansasser/claude-code-marketplace/api-compat/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.
<a href="https://agentmods.dev/agents/dansasser/claude-code-marketplace/api-compat"><img src="https://agentmods.dev/badge/agents/dansasser/claude-code-marketplace/api-compat.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00034 | $0.00968 |
| Opus 5.5 | $0.00014 | $0.00387 |
| Sonnet 5.5 | $0.00007 | $0.00194 |
| Haiku 4.5 | $0.00003 | $0.00097 |
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 1mo 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.
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": []
}
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.
- 1mo ago First seen · 163 lines · 0 tokens per session scan A b4ed18050df4
api-compat is an agent published in the GitHub repository dansasser/claude-code-marketplace (9 stars, last pushed 5mo ago), licensed MIT. It adds 34 tokens to every session and 968 once invoked, about $0.0001 per session on Opus 5.5. 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.
Other agents, from other repositories
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
thermo-nuclear-code-quality-review-subagent
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.
karimo-implementer
Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.