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 agentmods add skills/cosmicstack-labs/mercury-agent-skills/code-reviewnpx skills add cosmicstack-labs/mercury-agent-skills --skill code-reviewgit clone --depth 1 https://github.com/cosmicstack-labs/mercury-agent-skillsWrote 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/cosmicstack-labs/mercury-agent-skills/code-review)<a href="https://agentmods.dev/skills/cosmicstack-labs/mercury-agent-skills/code-review"><img src="https://agentmods.dev/badge/skills/cosmicstack-labs/mercury-agent-skills/code-review.svg" alt="Measured on agentmods" 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 | $0.00019 | $0.03234 |
| Opus 5 | $0.00010 | $0.01617 |
| Sonnet 5 | $0.00004 | $0.00647 |
| Haiku 4.5 | $0.00002 | $0.00323 |
Grade A, and why
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 6d 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 — 358 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review
Systematic code review methodology for consistent, effective, and humane reviews that improve both code and team culture.
Core Principles
1. Review the Author, Not Just the Code
Every review is a human interaction. The goal is shared understanding and team growth, not ego or gatekeeping. Be constructive, specific, and kind.
2. Catch Problems Early, Fix Them Forever
A bug caught in review costs 10x less than one caught in production. Use each review as an opportunity to add automated checks so the same issue never needs a human review again.
3. Balance Depth with Velocity
Deep reviews catch more issues but slow delivery. Shallow reviews miss things. Adapt depth to risk: security-critical code gets exhaustive review; trivial config changes get a quick skim.
4. Automate Everything You Can
If a reviewer can point out a formatting issue, a lint violation, or a missing test — that check should be automated. Human attention is for design, logic, and tradeoffs.
Code Review Scoring Rubric
| Dimension | 1 (Poor) | 3 (Adequate) | 5 (Excellent) |
|---|---|---|---|
| Correctness | Obvious bugs missed | Catches logic errors | Identifies edge cases + security issues |
| Constructiveness | "This is wrong" comments | Points to specific lines | Suggests alternatives + explains reasoning |
| Speed | Reviews take >5 days | Reviews within 48 hours | Reviews within 4 hours (same day) |
| Depth | Skims only formatting | Checks logic + tests | Reviews design, security, performance, test coverage |
| Automation | No CI checks | Linting + basic tests | Pre-commit hooks, auto-review bots, coverage gates |
| Consistency | Every review is different | Team has some standards | Defined checklist, shared expectations, documented norms |
Target: 4+ in every dimension for a mature review culture.
Actionable Guidance
The PR Checklist
Use this as a template. Adapt to your stack and team norms.
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.
- 6d ago First seen · 358 lines · 19 tokens per session scan A 5474df758160
code-review is a skill published in the GitHub repository cosmicstack-labs/mercury-agent-skills (471 stars, last pushed 11d ago), licensed MIT. It adds 19 tokens to every session and 3,234 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 2026-08-30.
Other skills, from other repositories
modern-saas-builder
Founder-minded senior product engineer and SaaS architect skill. Use when building, planning, architecting, validating, designing, testing, securing, deploying, or monetizing modern SaaS products, micro-SaaS, web apps, AI agents, Web3/Base applications, agent commerce, or Telegram bots/Mini Apps. Always active when…
gke-reliability
Improves GKE workload reliability, using PDBs, health probes, and topology spread constraints. Use when configuring GKE workload reliability, setting up PDBs, or configuring GKE health probes (liveness, readiness, startup). Don't use for disaster recovery setup or full cluster backups (use gke-backup-dr instead).
gke-workload-security
Audits, configures, and hardens workload-level security controls for Google Kubernetes Engine (GKE) applications and namespaces. Covers running cluster security audits (auditcluster.sh), configuring Workload Identity Federation (impersonation, KSA/GSA binding, and pod setup), enforcing Network Policies (default-deny…
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
atlas-obscura
Search Atlas Obscura for weird, wonderful, and hidden gem places near any destination. Find the interesting stuff, not boring plaques. Search by coordinates, get full details with descriptions and images.
cf-validate
Валидация конфигурации 1С. Используй после создания или модификации конфигурации для проверки корректности.