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 ahmadharis/agentskills --skill azure-work-completegit clone --depth 1 https://github.com/ahmadharis/agentskillsWrote 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/ahmadharis/agentskills/azure-work-complete)<a href="https://agentmods.dev/skills/ahmadharis/agentskills/azure-work-complete"><img src="https://agentmods.dev/badge/skills/ahmadharis/agentskills/azure-work-complete/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/ahmadharis/agentskills/azure-work-complete"><img src="https://agentmods.dev/badge/skills/ahmadharis/agentskills/azure-work-complete.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 | $0.00077 | $0.01291 |
| Opus 5 | $0.00039 | $0.00646 |
| Sonnet 5 | $0.00015 | $0.00258 |
| Haiku 4.5 | $0.00008 | $0.00129 |
Grade A, and why
azure-work-complete 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Azure DevOps Full Cycle Workflow
Orchestrates the complete development cycle: pick up a work item, implement it, review the code, create a PR, and clean up. Designed to run autonomously with minimal user intervention.
Invocation
| Mode | Command | Behavior |
|---|---|---|
| Single run | /azure-work-complete |
Run one full cycle |
| Continuous | /loop 30m /azure-work-complete |
Repeat on a schedule (session-scoped, 3-day max) |
Context in loop mode: Each
/loopiteration runs in the same session. If context grows large, use/compactbetween cycles or run in headless mode (claude -p "/azure-work-complete") for full isolation per cycle.
Step 1: Pick Up a Work Item
Invoke the azure-work skill in browse mode (no arguments).
The skill will list open work items. Automatically pick the first item from the list — do not prompt the user for selection.
If the list is too large: If azure-work indicates there are too many items to display, or returns an error about result limits, or the list appears truncated, re-run the WIQL query from azure-work and pipe the output through jq to take only the first 5 results:
az boards query --wiql "SELECT [System.Id], [System.Title], [System.State], [System.WorkItemType] FROM WorkItems WHERE ..." --org "https://dev.azure.com/$ADO_ORG" --project "$ADO_PROJECT" -o json | jq '.[:5]'
WIQL does not support TOP N or LIMIT. Result limiting must be done client-side.
Then pick the first item from the reduced list.
If no items are returned: Stop the cycle and report: "No open work items found. Cycle complete." If running in a loop, cancel the scheduled task — use CronList to find the task ID, then CronDelete to remove it. Report: "All work items complete. Loop cancelled."
Step 2: Implement the Work Item
The azure-work skill handles the full implementation:
- Reads work item details and attachments
- Creates a feature branch
- Updates work item state
- Brainstorms or implements directly (based on complexity)
- Runs verification checks
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 147 lines · 77 tokens per session scan A 12cea660441b
azure-work-complete is a skill published in the GitHub repository ahmadharis/agentskills (2 stars, last pushed 5mo ago), licensed MIT. It adds 77 tokens to every session and 1,291 once invoked, about $0.0004 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
gsd-quick
Execute a quick task with GSD guarantees (atomic commits, state tracking) but skip optional agents.
gsd-quick-batch
Batch several /gsd:quick-shaped tasks together — planned, dispatched, and merged as one run.
gh-issues
Fetch GitHub issues, spawn sub-agents to implement fixes and open PRs, then monitor and address PR review comments. Usage: /gh-issues [owner/repo] [--label bug] [--limit 5] [--milestone v1.0] [--assignee @me] [--fork user/repo] [--watch] [--interval 5] [--reviews-only] [--cron] [--dry-run] [--model glm-5]…
gsd-pause-work
Create context handoff when pausing work mid-phase.
gsd-ship
Create PR, run review, and prepare for merge after verification passes.
mcore-split-pr
Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.