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 vasilyu1983/AI-Agents-public --skill software-code-reviewgit clone --depth 1 https://github.com/vasilyu1983/AI-Agents-publicWrote 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/vasilyu1983/ai-agents-public/software-code-review)<a href="https://agentmods.dev/skills/vasilyu1983/ai-agents-public/software-code-review"><img src="https://agentmods.dev/badge/skills/vasilyu1983/ai-agents-public/software-code-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/vasilyu1983/ai-agents-public/software-code-review"><img src="https://agentmods.dev/badge/skills/vasilyu1983/ai-agents-public/software-code-review.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 Excessive Agency · line 168 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00037 | $0.03678 |
| Opus 5 | $0.00018 | $0.01839 |
| Sonnet 5 | $0.00007 | $0.00736 |
| Haiku 4.5 | $0.00004 | $0.00368 |
Grade A, and why
software-code-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 9d 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 — 256 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review
This skill is for reviewing existing changes. It routes the agent to the right checklist, review mode, and platform workflow without turning SKILL.md into a tool catalog.
Quick Reference
| Task | Use | Primary Reference |
|---|---|---|
| General PR or diff review | Baseline review flow and severity rubric | references/operational-playbook.md |
| AI-generated or agent-created changes | Human-in-the-loop review rules and platform controls | references/automation-tools.md |
| Building or tuning an AI review tool/integration | Pre-review deterministic gate, size-gated planning pass, self-refutation filter pass | references/deterministic-vs-llm-routing.md |
| Backend/API review | Error handling, contracts, persistence, operability | assets/backend-api/api-review.md |
| Frontend review | Accessibility, responsive behavior, Core Web Vitals | assets/web-frontend/frontend-review.md |
| Mobile review | Platform patterns, lifecycle, permissions, UX | assets/mobile/mobile-review.md |
| Infrastructure review | CI/CD, IaC, secrets, deploy safety | assets/infrastructure/infrastructure-review.md |
| Smart contract review | Access control, reentrancy, unsafe assumptions | assets/blockchain/crypto-review.md |
| Data / ML review | Pipelines, experiments, models, deployment | assets/data-ml/data-pipeline-review.md |
When to Use This Skill
Use this skill when the primary task is to:
- review a PR, merge request, or diff
- find correctness, security, reliability, or maintainability issues
- assess test gaps and regression risk
- critique AI-generated or agent-created changes before merge
- recommend small, behavior-preserving refactors
What ships with it
29 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.
- agents/openai.yaml 340 B
- assets/backend-api/api-review.md 3.4 KB
- assets/blockchain/crypto-review.md 8.6 KB
- assets/core/pull-request-description-template.md 503 B
- assets/core/review-checklist-judgment.md 1.5 KB
- assets/core/review-comment-guidelines.md 952 B
- assets/data-ml/data-pipeline-review.md 9.8 KB
- assets/data-ml/experiment-tracking-review.md 10 KB
- assets/data-ml/ml-deployment-review.md 11 KB
- assets/data-ml/ml-model-review.md 7.7 KB
- assets/infrastructure/infrastructure-review.md 3.2 KB
- assets/mobile/mobile-review.md 3.0 KB
- assets/web-frontend/frontend-review.md 3.0 KB
- data/sources.json 25 KB
- learnings.consolidated.md 596 B
- learnings.md 1.3 KB
- references/adversarial-review-protocol.md 6.3 KB
- references/automation-tools.md 12 KB
- references/code-review-metrics.md 18 KB
- references/complexity-only-review-pass.md 4.8 KB
- references/deterministic-vs-llm-routing.md 7.8 KB
- references/dotnet-efcore-crypto-rules.md 4.8 KB
- references/implementing-effective-code-reviews-checklist.md 2.5 KB
- references/large-pr-review-strategies.md 20 KB
- references/looks-good-to-me-checklist.md 2.1 KB
- references/operational-playbook.md 14 KB
- references/psychological-safety-guide.md 19 KB
- references/review-checklist-comprehensive.md 14 KB
- references/security-focused-review-guide.md 18 KB
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.
- 9d ago First seen · 256 lines · 37 tokens per session scan A 0e1fa7ac7f3a
software-code-review is a skill published in the GitHub repository vasilyu1983/AI-Agents-public (87 stars, last pushed 10d ago), licensed MIT. It adds 37 tokens to every session and 3,678 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
code-review-excellence
Master effective code review practices to provide constructive feedback, catch bugs early, and foster knowledge sharing while maintaining team morale. Use when reviewing pull requests, establishing review standards, or mentoring developers.
multi-reviewer-patterns
Coordinate parallel code reviews across multiple quality dimensions with finding deduplication, severity calibration, and consolidated reporting. Use this skill when organizing multi-reviewer code reviews, calibrating finding severity, or consolidating review results.
babysit
Watch an open PR — fix failing CI, handle the straightforward review comments, and drive it to a mergeable state. Claude Code analog of Cursor's built-in /babysit. Use after opening a PR when the user wants the agent to shepherd it without re-prompting.
make-pr-easy-to-review
Prepare PRs for review by cleaning noisy history, improving PR descriptions, and adding reviewer guidance without changing code behavior. Use for "make this easy to review", "tidy this PR", "clean up commits", or "annotate the diff".
spawn-reviewers
Spawn and collect the reviewer fleet at stage20spawnreviewers. Consumes spawn.json.spec (the authoritative spawn spec from derive-spawn-spec / derive-static-spec), resolves CODEINTELALLOWED, builds per-agent prompts from the per-agent template + role suffixes (Bug Hunter A/B, Unified Auditor, Domain Critics, Impact…
no-comments
Spawn the comment-sicko subagent, fix accepted findings, and offer encodings for claimed constraints.