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 RobinNorberg/oh-my-copilot --skill omc-ado-auto-reviewgit clone --depth 1 https://github.com/RobinNorberg/oh-my-copilotWrote 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/robinnorberg/oh-my-copilot/omc-ado-auto-review)<a href="https://agentmods.dev/skills/robinnorberg/oh-my-copilot/omc-ado-auto-review"><img src="https://agentmods.dev/badge/skills/robinnorberg/oh-my-copilot/omc-ado-auto-review/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/robinnorberg/oh-my-copilot/omc-ado-auto-review"><img src="https://agentmods.dev/badge/skills/robinnorberg/oh-my-copilot/omc-ado-auto-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00101 | $0.03176 |
| Opus 5 | $0.00051 | $0.01588 |
| Sonnet 5 | $0.00020 | $0.00635 |
| Haiku 4.5 | $0.00010 | $0.00318 |
Grade A, and why
omc-ado-auto-review 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 — 424 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OMC ADO Auto Review
Automatically review Azure DevOps pull requests where the current user is assigned as a reviewer. Reads .omg/config.json for connection settings, discovers pending PRs, fetches diffs, spawns a code-reviewer agent to analyse changes, and posts structured inline comments back to each PR.
When this skill is invoked, immediately execute the workflow below. Do not only restate or summarize these instructions back to the user.
Trigger Patterns
- "auto review"
- "auto-review prs"
- "review my assigned prs"
- "automated pr review"
- "omc-ado-auto-review"
Step 1: Load Configuration
Read .omg/config.json:
node -e "const f=require('fs');try{process.stdout.write(f.readFileSync('.omg/config.json','utf8'))}catch{console.log('NOT_FOUND')}"
Extract from the ado key:
org— full org URL (e.g.https://dev.azure.com/contoso)project— ADO project namerepo— repository name
Also read optional ado.autoReview settings (apply defaults when absent):
| Setting | Default | Purpose |
|---|---|---|
severityThreshold |
"MEDIUM" |
Minimum severity to post as inline comment |
autoVote |
false |
Automatically cast a vote after review |
maxFilesPerReview |
50 |
Cap on number of files analysed per PR |
excludePatterns |
["*.lock", "*.min.js", "*.generated.*"] |
Glob patterns for files to skip |
If config is NOT_FOUND or missing the ado key: tell the user to run /oh-my-copilot:omc-ado-setup first and stop.
Step 2: Identify Current User
Resolve the current user's identity so PRs can be filtered by reviewer assignment.
MCP (preferred):
mcp__azure-devops__core_get_identity_ids
→ identities: ["{currentUserEmail}"]
az CLI fallback:
az ad signed-in-user show -o json 2>&1
Extract and store:
userId— the ADO identity GUIDuserEmail— the user's email address (used for az CLI fallback filtering)
If neither succeeds, prompt the user to run az login and stop.
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 · 424 lines · 101 tokens per session scan A 7d4fa1da5a07
omc-ado-auto-review is a skill published in the GitHub repository RobinNorberg/oh-my-copilot (5 stars, last pushed 5d ago), licensed MIT. It adds 101 tokens to every session and 3,176 once invoked, about $0.0005 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 2026-09-04.
Other skills, from other repositories
pr-review
Multi-dimensional review of a PR or feature branch in microsoft/win-dev-skills. Activate on "review my PR / changes / branch", "vet before pushing", "PR review", "is this ready to merge". Fans out parallel sub-agents over skill content, the skill-vs-tool boundary (solution hierarchy), tool correctness…
winui-code-review
Code quality review for WinUI 3 apps — MVVM compliance, x:Bind correctness, accessibility, theming, security, and performance. Use before committing to catch issues that the compiler and UI tests won't find.
verify
Answer "is this shippable / done?" with evidence before a commit or PR — fires on "verify", "is this done", "ready to ship?", pre-commit or pre-PR. Part of the Agentsmith harness; runs the project's verify phases and never claims "passing" without showing the output (R5).
karpathy-guidelines
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code. Derived from Andrej Karpathy's LLM coding pitfalls.
verify-readme-features
Verifies that features listed in a README (or similar documentation) are actually implemented in the codebase. Use when user mentions verify features, check feature list, confirm README, validate documentation claims, or audit feature accuracy. Helps catch stale, missing, or inaccurate feature descriptions.
lead-review
Autonomous comprehensive review. Once-through pipeline over /review-health, /review-arch, /review-security, /review-perf, /review-a11y, /review-test, /review-release. Operator-configurable ticket creation at startup — when ON, auto-approves sub-skill ticket proposals per the orchestrator-family contract; when OFF…