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 dgambhir01/ado-testcraft --skill generategit clone --depth 1 https://github.com/dgambhir01/ado-testcraftWrote 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/dgambhir01/ado-testcraft/generate)<a href="https://agentmods.dev/skills/dgambhir01/ado-testcraft/generate"><img src="https://agentmods.dev/badge/skills/dgambhir01/ado-testcraft/generate.svg" alt="Measured on agentmods" 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 | $0.00030 | $0.01215 |
| Opus 5 | $0.00015 | $0.00607 |
| Sonnet 5 | $0.00006 | $0.00243 |
| Haiku 4.5 | $0.00003 | $0.00121 |
Grade A, and why
generate 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 8d 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generate Test Cases from ADO User Story
Instructions
The user will provide an Azure DevOps User Story ID (e.g. 12345) or a full ADO URL.
Step 0 — Pre-flight checks (before any MCP call)
Validate input format first.
- If the input is a plain integer (e.g.
12345), use it directly as the work item ID. - If the input is a URL, extract the numeric ID from either of these formats:
https://dev.azure.com/{org}/{project}/_workitems/edit/{id}https://{org}.visualstudio.com/{project}/_workitems/edit/{id}
- If the input is neither a numeric ID nor a recognised ADO URL, stop immediately:
"That doesn't look like a valid ADO work item ID or URL. Please provide a numeric ID (e.g.
12345) or a full Azure DevOps work item URL."
Validate MCP availability.
Confirm the Azure DevOps MCP server is connected. If it is not available, stop:
"The Azure DevOps MCP server is not connected. Run
/ado-testcraft:setupto configure your credentials, then restart Claude Code."
Resolve the project name from the environment.
Read the ADO_PROJECT environment variable using a shell tool and remember the value — you will pass it as the project parameter on every MCP tool call to avoid being prompted on each invocation.
- Windows (PowerShell):
$env:ADO_PROJECT - macOS / Linux (Bash):
echo $ADO_PROJECT
If the returned value is empty, stop:
"ADO_PROJECT environment variable is not set. Run
/ado-testcraft:setupfor step-by-step configuration."
Step 1 — Fetch and validate the work item
Use the Azure DevOps MCP to fetch the work item by ID. Always pass the project parameter with the value resolved in Step 0 — do not let the MCP server elicit it. Always fetch fresh data — never reuse work item data from a previous invocation in the same conversation. Work item state can change between calls.
If the fetch fails or the ID does not exist, stop:
"Could not fetch work item [ID]. Please verify the ID is correct and that your PAT has Work Items (Read) scope."
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.
- 8d ago First seen · 119 lines · 30 tokens per session scan A ba1b2f328590
generate is a skill published in the GitHub repository dgambhir01/ado-testcraft (1 stars, last pushed 2mo ago), licensed MIT. It adds 30 tokens to every session and 1,215 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.
Other skills, from other repositories
no-silent-pass
Write Python whose failures are visible and checks that actually fire — distinct sentinels for success and error, filters that narrow to nothing without reading as "all clear", output never discarded on a non-zero exit, and selftest cases proven red before they are trusted (mutate the fix, mutate it the other way too…
live-preview
Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.
validate-album
Validates album directory structure, file locations, and content integrity. Use before release or whenever the user wants to check an album's structural health.
api-testing
HTTP API testing for TypeScript (Supertest) and Python (httpx, pytest). Test REST APIs, GraphQL, request/response validation, authentication, and error handling.
bun-jest-migration
Use when migrating from Jest to Bun's test runner, import compatibility, mocks, and config.
bun-test-mocking
Use for mock functions in Bun tests, spyOn, mock.module, implementations, and test doubles.