Azure Developer CLI (azd) is a command-line tool for building, deploying, and operating applications on Azure. Developers use it to move through application workflows such as coding, building, deployment, and monitoring with Azure templates and resources. Its catalogue entries help AI agents work with azd and Azure application projects.
Borrowing it
Nothing to install: this file belongs to Azure/azure-dev. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Azure/azure-dev/main/.github/skills/azd-code-reviewer/SKILL.mdgit clone --depth 1 https://github.com/Azure/azure-devWrote 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/azure/azure-dev/azd-code-reviewer)<a href="https://agentmods.dev/skills/azure/azure-dev/azd-code-reviewer"><img src="https://agentmods.dev/badge/skills/azure/azure-dev/azd-code-reviewer/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/azure/azure-dev/azd-code-reviewer"><img src="https://agentmods.dev/badge/skills/azure/azure-dev/azd-code-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Prompt Injection · line 58 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 | $0.00078 | $0.00941 |
| Opus 5.5 | $0.00031 | $0.00376 |
| Sonnet 5.5 | $0.00016 | $0.00188 |
| Haiku 4.5 | $0.00008 | $0.00094 |
Grade A, and why
azd-code-reviewer 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code review
Reviews GitHub PRs by applying a panel of specialist review lenses to the diff, filtering for high-signal findings, and returning structured comments for the host to post.
Operating environment
This skill usually runs inside an automated review harness (e.g., Copilot Code Review). It assumes:
- The diff and PR context are already provided by the harness. In an interactive invocation without that context, use read-only
gitandghcommands to discover the current branch diff and PR metadata. Do not change branches or the worktree. - No interactive user. No
ask the userflows, no walkthroughs, no "want to proceed?" gates. The skill produces findings and returns them. - No build or test execution. Test code is reviewed statically.
- The harness handles posting. The skill returns structured findings; the harness creates the review.
If the host is interactive (e.g., a chat agent invoking the skill manually), the same workflow still works — interactive steps simply don't apply.
Workflow
Step 1: Read the diff and PR context
Use whatever PR metadata, diff, and changed-file list the harness provides. In an interactive invocation where these are missing, discover them with read-only git and gh commands. If supplementary context such as linked issues or prior review comments is available, use it.
Step 2: Detect review cases
If added files are under a top-level path in cli/azd/extensions/ that did not exist before the PR, load new-extension.md and apply its onboarding review. An added extension.yaml is enough to trigger the new-extension review because a dependency-only extension pack may have no module or entry point.
Step 3: Apply review lenses
Load reviewers.md and apply each of the 9 fixed lenses to the diff. Then scan the changed files for the domain signals listed in reviewers.md and apply matching domain lenses. Each lens produces zero or more findings in the structured format defined in reviewers.md.
What ships with it
3 files 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.
- 1mo ago First seen · 63 lines · 78 tokens per session scan A 7edd91e897ba
azd-code-reviewer is a skill published in the GitHub repository Azure/azure-dev (570 stars, last pushed today), licensed MIT. It adds 78 tokens to every session and 941 once invoked, about $0.0003 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
hunk-launch-video
Produces Hunk videos by driving the real TUI headlessly in a PTY, compositing captioned 1080p frames in Chromium, and encoding with ffmpeg. Use for feature demos, workflow explainers, announcements, launch videos, and full-release roundups.
hunk-release
Prepares, publishes, verifies, and curates Hunk releases. Use for release metadata, benchmarks, tags, publishing, release videos, backports, or recovery.
cosmos-pre-commit-validation
Run pre-commit checks for a specific set of crates. Use this when validating changes under sdk/cosmos before committing or during code review.
shadow-verify
Dispatch a parallel adversarial verifier wave after any high-stakes sub-agent investigation (code reviews, audits, findings reports, large refactors, gap analyses) — or whenever a sub-agent asserts a claim with high-confidence language, since confidence is a trigger, not a verdict. Use when sub-agent output will drive…
code-review
Reviewing code for defects: diff-first reading, severity classification, evidence over inference, finding caps, and terminal verdicts. Use when reviewing a diff, PR, or patch, or auditing someone else's work.
responding-to-review
Answering review findings: verify each claim before implementing, no performative agreement, per-item fix/reject/defer with evidence, one batched remediation round. Use when responding to review or remediation rounds.