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 setupgit 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/setup)<a href="https://agentmods.dev/skills/dgambhir01/ado-testcraft/setup"><img src="https://agentmods.dev/badge/skills/dgambhir01/ado-testcraft/setup/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/dgambhir01/ado-testcraft/setup"><img src="https://agentmods.dev/badge/skills/dgambhir01/ado-testcraft/setup.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 | $0.00045 | $0.01070 |
| Opus 5.5 | $0.00018 | $0.00428 |
| Sonnet 5.5 | $0.00009 | $0.00214 |
| Haiku 4.5 | $0.00005 | $0.00107 |
Grade A, and why
setup 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 2mo 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Set Up ado-testcraft Credentials
Instructions
Detect the user's platform, check whether credentials are already set, then output the exact terminal commands they need to paste. Never ask the user to type their PAT into the chat — always use placeholders they replace in the terminal.
Step 1 — Detect operating system
Run $env:OS via PowerShell.
- Returns
Windows_NT→ Windows. Proceed to the Windows block in Step 3. - Returns empty or errors → macOS or Linux. Run
unamevia Bash.- Returns
Darwin→ macOS - Returns
Linux→ Linux
- Returns
Step 2 — Check current credential state
Read the three variables with the platform-appropriate shell:
Windows (PowerShell):
"ADO_ORG=$($env:ADO_ORG)"; "ADO_PROJECT=$($env:ADO_PROJECT)"; if ($env:ADO_PAT) { "ADO_PAT=[set]" } else { "ADO_PAT=[not set]" }
macOS / Linux (Bash):
echo "ADO_ORG=${ADO_ORG}"; echo "ADO_PROJECT=${ADO_PROJECT}"; [ -n "$ADO_PAT" ] && echo "ADO_PAT=[set]" || echo "ADO_PAT=[not set]"
Show the user a clear credential status summary, masking the PAT:
Current credential state:
ADO_ORG: [value, or ⚠️ not set]ADO_PROJECT: [value, or ⚠️ not set]ADO_PAT: [✅ set, or ⚠️ not set]
If all three are already set, say:
✅ All credentials are configured. Test with
/ado-testcraft:generate <story-id>. To update any value, paste the replacement commands below into a terminal and restart Claude Code.
Then still show the setup commands in Step 3 for reference and to support credential updates.
Step 3 — Output platform-specific setup commands
Windows
Tell the user to open PowerShell (not Command Prompt) and paste these commands, replacing the placeholder values:
[System.Environment]::SetEnvironmentVariable("ADO_ORG", "your-org-name", "User")
[System.Environment]::SetEnvironmentVariable("ADO_PROJECT", "your-project-name", "User")
[System.Environment]::SetEnvironmentVariable("ADO_PAT", "your-pat-here", "User")
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.
- 2mo ago First seen · 110 lines · 45 tokens per session scan A b94462e9129c
setup is a skill published in the GitHub repository dgambhir01/ado-testcraft (1 stars, last pushed 4mo ago), licensed MIT. It adds 45 tokens to every session and 1,070 once invoked, about $0.0002 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.
setup compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| setupdgambhir01/ado-testcraft | Skill | 1 | 4mo ago | MIT | A | 45 | Claude Code |
| refactoring-the-assembled-uiAleksandarBisevac/claude-plugins | Skill | 4 | 2d ago | MIT | A | 189 | Claude Code |
| running-resumable-sync-jobsAleksandarBisevac/claude-plugins | Skill | 4 | 2d ago | MIT | A | 102 | Claude Code |
| choosing-what-to-optimizeAleksandarBisevac/claude-plugins | Skill | 4 | 2d ago | MIT | A | 145 | Claude Code |
| reproducing-ci-locallyAleksandarBisevac/claude-plugins | Skill | 4 | 2d ago | MIT | A | 130 | Claude Code |
| verifying-external-behaviorAleksandarBisevac/claude-plugins | Skill | 4 | 2d ago | MIT | A | 138 | Claude Code |
| writing-javascriptAleksandarBisevac/claude-plugins | Skill | 4 | 2d ago | MIT | A | 163 | Claude Code |