accordant-cross-language

A testing approach for checking whether any software system follows its specification, even when the system is written outside .NET. It records requests and responses as a trace and compares that history with the expected behavior.

In plain words
What is it for?
Use it to validate HTTP or gRPC services, export test plans as JSON, run tests from another programming language, and check recorded request-and-response sequences.
Why use it?
It lets teams test systems written in Python, Go, Java, Rust, C++, or other languages without rewriting the system in .NET.

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/microsoft/accordant/cross-language
Any agent
npx skills add microsoft/accordant --skill cross-language
Clone the repo
git clone --depth 1 https://github.com/microsoft/accordant

Made for: Claude Code, Codex.

Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,611 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 $0.00066 $0.01611
Opus 5 $0.00033 $0.00805
Sonnet 5 $0.00013 $0.00322
Haiku 4.5 $0.00007 $0.00161

Measured 3d ago against content hash 13b8551d5153, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

accordant-cross-language 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 3d 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.

agent/skills/cross-language/SKILL.md · 192 lines

How it starts

The opening of the file, as written. The whole thing — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Testing Any System with Accordant

The spec is an oracle — it doesn't need to call your system, just see what happened. This skill covers how to use Accordant when the system under test isn't in .NET.

Decision Guide

Situation Approach
System has an HTTP/gRPC API Use Accordant normally — bind operations to a .NET client. Server language doesn't matter.
Want to test from another language Export test plans to JSON, execute from your runner, capture traces, validate with spec.Allows()
Calling native code (C/C++/Rust) from .NET Use P/Invoke for shared libraries, COM interop, or C++/CLI

The Two Core Capabilities

Everything else (built-in test runner, polling, request derivation) is a small convenience layer. The real value:

  1. Spec as oracle — given any trace (requests + responses), the spec tells you whether every response was correct given the state history
  2. State-graph-based test generation — the spec simulates the system, explores reachable states, and algorithms extract high-coverage test sequences

Both work from any language via trace validation and JSON export.

Trace-Based Conformance Testing

The Pattern

  1. System runs (any language) and produces a trace: operation name + request + response per step
  2. A small .NET validator walks the trace through spec.Allows()
  3. The spec checks each response against expected behavior given current state

Trace Format

The spec doesn't prescribe a format. A simple JSON array works:

[
  { "operation": "CreateAccount", "request": { "AccountId": "alice" }, "response": { "StatusCode": 201, "Balance": 0 } },
  { "operation": "Deposit", "request": { "AccountId": "alice", "Amount": 100 }, "response": { "StatusCode": 200, "Balance": 100 } }
]

Read the full file on GitHub · 192 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. 3d ago First seen · 192 lines · 66 tokens per session scan A 13b8551d5153

Subscribe to this mod's changes

accordant-cross-language is a skill published in the GitHub repository microsoft/accordant (58 stars, last pushed 15d ago), licensed MIT. It adds 66 tokens to every session and 1,611 once invoked, about $0.0003 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 2026-08-30.

Related

Other skills, from other repositories

keploy-docs

Guide for contributing to the Keploy documentation site at github.com/keploy/docs. Invoke when a change in keploy/keploy introduces, removes, or alters user-visible behavior (new CLI flag, changed default, new command, new configuration field, new on-disk format) and the docs need to catch up — or when the user asks…

keploy/keploy · 116 tokens

keploy-pr-workflow

Guide for creating PRs and issues on keploy repositories — PR format, customer-data hygiene, commit conventions, sign-off. Invoke when the user asks to open, update, or review a pull request or issue, when preparing a commit that will land in main, or whenever a change is about to leave the local machine.

keploy/keploy · 71 tokens

keploy-e2e-test

End-to-end verification of a change to keploy/keploy using keploy's own record/replay against a real sample application. Use whenever the user asks to test a change, verify a fix, prove that a modification works in practice, add e2e coverage for a PR, reproduce a bug against a sample app, or wire a behavior into CI.…

keploy/keploy · 118 tokens

implementing-api-security-testing-with-42crunch

Implement comprehensive API security testing using the 42Crunch platform to perform static audit and dynamic conformance scanning of OpenAPI specifications.

xalgorix/xalgorix · 36 tokens

API Test Suite Generator

Automatically generate comprehensive API test suites from OpenAPI specifications covering CRUD operations, error handling, authentication, pagination, and edge cases.

PramodDutta/qaskills · 29 tokens

AI Test Generation Patterns

Systematic patterns for prompting AI coding agents to generate high-quality tests including prompt engineering for test creation, coverage-driven generation, mutation-aware testing, and review checklists for AI-generated test code.

PramodDutta/qaskills · 43 tokens