Accordant is a .NET framework that turns executable behavioral specifications into generated tests for checking software implementations. It helps developers verify that real systems follow defined rules across many operations and state changes.
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 skills add microsoft/accordant --skill troubleshootinggit clone --depth 1 https://github.com/microsoft/accordantWrote 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/skills/microsoft/accordant/troubleshooting)<a href="https://agentmods.dev/skills/microsoft/accordant/troubleshooting"><img src="https://agentmods.dev/badge/skills/microsoft/accordant/troubleshooting/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/skills/microsoft/accordant/troubleshooting"><img src="https://agentmods.dev/badge/skills/microsoft/accordant/troubleshooting.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Memory Poisoning · line 41 Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.Fix: Protect agent memory and state from modification by untrusted content. Use read-only memory for critical instructions and validate all state changes.
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 | $0.00029 | $0.02586 |
| Opus 5.5 | $0.00012 | $0.01034 |
| Sonnet 5.5 | $0.00006 | $0.00517 |
| Haiku 4.5 | $0.00003 | $0.00259 |
Grade A, and why
accordant-troubleshooting 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 — 402 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Troubleshooting Accordant
This skill covers common mistakes, debugging techniques, and how to fix typical issues.
Test Failures
"No matching expected outcome"
The response doesn't match any Expect.That() predicate.
Diagnosis:
// Check what the spec expects vs what you got
var (isValid, message, _) = spec.Allows(operation, request, actualResponse, stateProfile);
Console.WriteLine(message); // Shows which expectation failed and why
Common causes:
- Predicate too strict: Response has extra fields or slightly different values
- Wrong state: The spec thinks it's in state A, but the system is in state B
- Missing error case: You didn't handle an error condition in Apply
Fix:
// Add explanation to predicates for better debugging
Expect.That<ApiResult<User>>(
r => r.IsSuccess && r.Data.Name == expectedName,
$"Expected success with name '{expectedName}', got status={r?.StatusCode}, name='{r?.Data?.Name}'")
"State mismatch after operation"
Tracked state diverges from actual system state.
Common causes:
- Forgot to reset state: Previous test left data behind
- Missing ThenState: Operation modifies state but spec uses
.SameState() - Wrong state update: ThenState modifies wrong fields
Fix:
// Ensure BeforeEachAsync properly resets
var results = await spec.RunTests(context, initialState, testCases, new TestExecutionOptions
{
BeforeEachAsync = async _ =>
{
// Actually verify reset worked
await client.DeleteAll();
var count = await client.GetCount();
if (count != 0) throw new Exception("Reset failed!");
}
});
Tests Pass Individually, Fail in Sequence
Common causes:
- Shared mutable state in test fixtures
- Incomplete reset between tests
- Timing issues with async operations
Fix:
// Create fresh client for each test
var results = await spec.RunTests(context, initialState, testCases, new TestExecutionOptions
{
BeforeEachAsync = async ctx =>
{
// Fresh client, fresh start
var httpClient = _factory.CreateClient();
ctx.Context.Register(new ApiClient(httpClient));
await ResetDatabase();
}
});
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 · 402 lines · 29 tokens per session scan A 45bb06b778fa
accordant-troubleshooting is a skill published in the GitHub repository microsoft/accordant (69 stars, last pushed 1mo ago), licensed MIT. It adds 29 tokens to every session and 2,586 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 2026-08-30.
Other skills, from other repositories
GitHub Copilot Testing Patterns
Effective patterns for using GitHub Copilot to generate, refactor, and maintain test code including prompt engineering for test generation, Copilot Chat for debugging, inline suggestions for assertions, and workspace context optimization.
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
deck-retro
Run a fully local agent-deck retrospective over the user's own transcripts, Recall index and logs. Use when a user wants to find recurring failures or take their own finding from investigation through synthetic reproduction, a user-filed issue, a test-first fix and contributor PR handoff. Also use for weekly usage…
incident-response-incident-response
Coordinate production incident triage, mitigation, investigation, recovery, and follow-up. Use when responding to outages or other incidents that require structured operational coordination.