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 armanzeroeight/fastagent-plugins --skill code-review-practicesgit clone --depth 1 https://github.com/armanzeroeight/fastagent-pluginsWrote 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/armanzeroeight/fastagent-plugins/code-review-practices)<a href="https://agentmods.dev/skills/armanzeroeight/fastagent-plugins/code-review-practices"><img src="https://agentmods.dev/badge/skills/armanzeroeight/fastagent-plugins/code-review-practices/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/armanzeroeight/fastagent-plugins/code-review-practices"><img src="https://agentmods.dev/badge/skills/armanzeroeight/fastagent-plugins/code-review-practices.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 | $0.00051 | $0.02058 |
| Opus 5.5 | $0.00020 | $0.00823 |
| Sonnet 5.5 | $0.00010 | $0.00412 |
| Haiku 4.5 | $0.00005 | $0.00206 |
Grade A, and why
code-review-practices 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 — 416 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review Practices
This skill provides guidance for conducting effective, constructive code reviews that improve code quality and team collaboration.
Review Mindset
Goals of code review:
- Catch bugs and issues early
- Share knowledge across the team
- Maintain code quality standards
- Improve code maintainability
- Foster learning and growth
Not goals:
- Assert dominance or superiority
- Enforce personal preferences
- Block progress unnecessarily
- Nitpick without value
What to Review
1. Correctness
Does the code work as intended?
- Logic is sound
- Edge cases are handled
- Error conditions are managed
- Requirements are met
2. Design and Architecture
Does it fit the system?
- Follows existing patterns
- Appropriate abstractions
- Reasonable complexity
- Scalable approach
3. Readability
Can others understand it?
- Clear naming
- Logical organization
- Appropriate comments
- Consistent style
4. Testing
Is it adequately tested?
- Tests exist for new code
- Edge cases covered
- Tests are maintainable
- Integration points tested
5. Security
Are there security concerns?
- Input validation
- Authentication/authorization
- Sensitive data handling
- Known vulnerabilities
6. Performance
Will it perform well?
- No obvious bottlenecks
- Efficient algorithms
- Resource usage reasonable
- Scalability considered
Review Process
1. Understand Context
Before reviewing code:
- Read PR description and linked issues
- Understand the problem being solved
- Check CI/CD results
- Note any special considerations
2. Review at Appropriate Level
High-level first:
- Overall approach
- Architecture decisions
- Major design choices
Then details:
- Implementation specifics
- Edge cases
- Code style
3. Provide Actionable Feedback
Good feedback:
- Specific and clear
- Explains the "why"
- Suggests solutions
- Prioritizes issues
Example:
Consider using a Set instead of an array here for O(1) lookups.
With the current implementation, the nested loop creates O(n²)
complexity which could be problematic with large datasets.
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 · 416 lines · 51 tokens per session scan A 05bffd4b7064
code-review-practices is a skill published in the GitHub repository armanzeroeight/fastagent-plugins (29 stars, last pushed 3mo ago), licensed MIT. It adds 51 tokens to every session and 2,058 once invoked, about $0.0002 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
adk-review
Reviews the uncommitted changes in an adk-python working tree and reports correctness, design, public-API stability, test, sample and documentation gaps as a prioritized findings report, fixing them only when asked. Use when the user asks to review local changes, wants a self-review before opening a pull request, asks…
code-review-skill
Reviews code with feedback tailored to the developer's profile in session state.
learn-from-sage
Detection-gap (miss) analysis for Code Review Sage. Learn from shipped fixes, acted-on human comments, and design outcomes to close reviewer blind spots. Inline during review stages a candidate; a human triggers a one-shot AI consolidation into the live ruleset.
review-fix-signoff-loop
Use when writing Agent Relay or Ricky workflows that must loop review, fix, and validation with fresh agent context until independent signoff agents, typically Claude and Codex, both agree the work is comprehensively complete. Covers fresh-context iterations, repairable gates, dual reviewer verdict contracts…
ha-code-review
Hope-native review of uncommitted, staged, commit, branch, or PR changes: discover concrete regressions, independently verify candidates, and report actionable findings first without speculative noise.
plugin-quality
A review guide for checking Zhin.js plugins before release. It covers plugin structure, feature declarations, resource cleanup, message sending, and security.