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 ntorga/agent-starter-kit --skill code-quality-reviewgit clone --depth 1 https://github.com/ntorga/agent-starter-kitWrote 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/ntorga/agent-starter-kit/code-quality-review)<a href="https://agentmods.dev/skills/ntorga/agent-starter-kit/code-quality-review"><img src="https://agentmods.dev/badge/skills/ntorga/agent-starter-kit/code-quality-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/ntorga/agent-starter-kit/code-quality-review"><img src="https://agentmods.dev/badge/skills/ntorga/agent-starter-kit/code-quality-review.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 | $0.00014 | $0.01164 |
| Opus 5 | $0.00007 | $0.00582 |
| Sonnet 5 | $0.00003 | $0.00233 |
| Haiku 4.5 | $0.00001 | $0.00116 |
Grade A, and why
code-quality-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 2d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
A code review without a checklist drifts toward gut feeling — the reviewer catches what they notice and misses what they don't. This skill turns the project's coding rules into a repeatable procedure. It tells the reviewer what to inspect and in what order.
Procedure
-
Initialize the progress file. Create
.memory/reviews/review-quality-<timestamp>.md:# Quality Review Progress ## Status - Last updated: <timestamp> - Overall: In Progress ## Phases - [ ] 1. Collect applicable rules - [ ] 2. Walk work against rules - [ ] 3. Verify style proximity - [ ] 4. Dedup findings ## Files - [ ] <path> - [ ] <path> ## Findings -
Collect the applicable rules. Load all files from
rules/code/. Also load any applicable rules (e.g.,rules/git.md). Classify each rule's statements by RFC language:- MUST / MUST NOT / SHALL / SHALL NOT — violations are always Blockers. No exceptions.
- SHOULD / SHOULD NOT — violations require justification visible in the code (a comment earned under
rules/code/general.md§ Comments, a design note, or a.context.mdentry). If the justification is clear, it is a Warning. If absent or unclear, it is a Blocker.
Language-to-severity mapping:
- MUST violation → always Blocker.
- SHOULD violation without visible justification → Blocker.
- SHOULD violation with documented justification → Warning.
If the codebase uses a specific language with a dedicated rule file, include that file. If the language has no dedicated file, apply only
rules/code/general.md. One pass-routing exception — severity rules are unchanged: the behavior-over-implementation rule inrules/code/general.md§ Testing is a test-proof question — hand it to the coherence pass per the Guardrails; do not classify it here.Mark phase 1 as
[x]in the progress file. -
Walk the work against every rule and classify findings. Check each statement in each loaded rule file against the changed code or plan. Do not skip or paraphrase rules — the rules are the source of truth. Classify each issue found:
- Blocker — MUST violation, unjustified SHOULD violation, readability violation (cryptic code is always a blocker). Must be fixed.
- Warning — justified SHOULD deviation, minor inconsistency. Should be addressed.
- Note — style suggestion beyond what rules mandate. No action required.
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.
- 2d ago First seen · 87 lines · 14 tokens per session scan A 969d224875e7
code-quality-review is a skill published in the GitHub repository ntorga/agent-starter-kit (142 stars, last pushed 2d ago), licensed MIT. It adds 14 tokens to every session and 1,164 once invoked, about $0.0001 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 2026-09-13.
Other skills, from other repositories
pragma-code-review
A code-review guide written in Chinese. It reviews code across correctness, architectural boundaries, risk, and verification.
safe-refactor
Refactor checklist with guardrails.
agent-framework-py-release
Use when cutting a Python release for the microsoft/agent-framework monorepo. Triggers on "bump py versions", "cut a python release", "prepare release PR for python", "release py packages", "bump python to X.Y.Z", or similar requests to bump Python package versions and prepare a release PR. Handles all four lifecycle…
foundry-hosted-agent-validation
Step-by-step process for validating a Python Foundry hosted agent sample (under python/samples/04-hosting/foundry-hosted-agents/) end to end — running it locally (native runtime and azd ai agent run) and after deploying it to an Azure AI Foundry project with azd. Use this when asked to validate a hosted agent sample.
build-and-test
How to build and test .NET projects in the Agent Framework repository. Use this when verifying or testing changes.
python-feature-lifecycle
Guidance for package and feature lifecycle in the Agent Framework Python codebase, including stage meanings, feature-stage decorators, feature enums, and how to move APIs from one stage to the next.