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.
npx agentmods add skills/microsoft/accordant/overviewnpx skills add microsoft/accordant --skill overviewgit clone --depth 1 https://github.com/microsoft/accordantWhat 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 | $0.00033 | $0.00963 |
| Opus 5 | $0.00016 | $0.00481 |
| Sonnet 5 | $0.00007 | $0.00193 |
| Haiku 4.5 | $0.00003 | $0.00096 |
Grade A, and why
accordant-overview 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.
How it starts
The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Accordant Overview
Accordant is a model-based testing framework for .NET. You write a spec — executable code that captures what your system should do — and Accordant generates tests, validates responses, and finds bugs.
When to Use Accordant
Accordant excels when:
- Your system is stateful (databases, caches, queues, sessions)
- You have many operations that interact with shared state
- You want to test operation sequences (not just individual calls)
- You need to find race conditions in concurrent code
- You want a single source of truth for behavior (not scattered assertions)
Core Concepts
The Spec
A spec is executable code defining what your system should do:
var spec = new Spec<BankState>();
spec.Operation<string, ApiResult<decimal>>("CreateAccount", (accountId, state) =>
{
if (state.Accounts.ContainsKey(accountId))
return Expect.That<ApiResult<decimal>>(r => r.IsConflict).SameState();
return Expect.That<ApiResult<decimal>>(r => r.IsSuccess && r.Data == 0)
.ThenState<BankState>(s => s.Accounts[accountId] = 0);
});
State
State is what the system "remembers" between operations. Keep it minimal — only what's needed to define correct behavior:
[State]
public partial class BankState
{
public Dictionary<string, decimal> Accounts { get; set; } = new();
}
Operations
An operation represents an atomic action — API call, method invocation, command. Each operation has:
- Apply: What should happen (the spec logic)
- Execute: What actually happens (calls the real system)
Test Generation
Accordant explores operation sequences by simulating the spec, then runs generated tests against your real system:
var testCases = spec.GenerateTests(initialState, inputs, options);
var results = await spec.RunTests(context, initialState, testCases, executionOptions);
The Typical Workflow
- Define State — What does the system track?
- Define Operations — What can happen to that state?
- Bind to Real System — Connect spec operations to actual API calls
- Generate & Run Tests — Let Accordant explore and validate
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.
- 2d ago First seen · 122 lines · 33 tokens per session scan A e57696d7dea3
accordant-overview is a skill published in the GitHub repository microsoft/accordant (58 stars, last pushed 14d ago), licensed MIT. It adds 33 tokens to every session and 963 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 2026-08-30.
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-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-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.…
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.
API Test Suite Generator
Automatically generate comprehensive API test suites from OpenAPI specifications covering CRUD operations, error handling, authentication, pagination, and edge cases.
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.