SkillKit is a package manager for AI coding-agent skills that installs skills from many sources and translates them between the different formats used by coding agents. It helps developers share skills across agents such as Claude Code, Cursor, Copilot, and Codex.
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 rohitg00/skillkit --skill structured-reviewgit clone --depth 1 https://github.com/rohitg00/skillkitWrote 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/rohitg00/skillkit/structured-review)<a href="https://agentmods.dev/skills/rohitg00/skillkit/structured-review"><img src="https://agentmods.dev/badge/skills/rohitg00/skillkit/structured-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/rohitg00/skillkit/structured-review"><img src="https://agentmods.dev/badge/skills/rohitg00/skillkit/structured-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 137 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 | $0.00112 | $0.01186 |
| Opus 5.5 | $0.00045 | $0.00474 |
| Sonnet 5.5 | $0.00022 | $0.00237 |
| Haiku 4.5 | $0.00011 | $0.00119 |
Grade A, and why
structured-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 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 — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Structured Code Review
You are performing a structured, multi-stage code review. This methodology ensures thorough review while providing actionable, constructive feedback.
Core Principle
Review in stages. Each stage has a specific focus. Don't mix concerns.
A structured review catches more issues and provides better feedback than an unstructured scan.
Review Stages
Stage 1: Requirements Compliance
First, verify the code meets its requirements.
Checklist:
- Implements stated requirements
- Handles specified edge cases
- No scope creep (unexpected additions)
- No missing functionality
Feedback at this stage:
- "This doesn't appear to handle the case when X is empty"
- "The requirement specified Y, but this implements Z"
- "This adds feature F which wasn't requested - is that intentional?"
Stage 2: Correctness
Next, verify the code works correctly.
Checklist:
- Logic is sound
- No obvious bugs
- Error paths are handled
- No unfinished code (TODOs without tickets)
Feedback at this stage:
- "This will throw if
useris null" - "The loop exits early before processing all items"
- "What happens when the API call fails?"
Stage 3: Code Quality
Then, evaluate code quality and maintainability.
Checklist:
- Clear naming
- Reasonable function/method length
- No unnecessary complexity
- Follows project conventions
- Appropriate abstractions
Feedback at this stage:
- "Could you rename
datatouserProfilefor clarity?" - "This function is doing three things - consider splitting"
- "We use camelCase for variables in this project"
Stage 4: Testing
Evaluate test coverage and quality.
Checklist:
- New code has tests
- Tests cover main paths and edge cases
- Tests are readable and maintainable
- Tests don't test implementation details
Feedback at this stage:
- "Please add a test for the error case"
- "This test will break if we change the implementation"
- "Consider using a parameterized test for these cases"
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 · 178 lines · 112 tokens per session scan A cdedab8780f6
structured-code-review is a skill published in the GitHub repository rohitg00/skillkit (1,556 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 112 tokens to every session and 1,186 once invoked, about $0.0004 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
Code Review Excellence
Master code review best practices with constructive feedback patterns, quality assurance standards, review checklists, security considerations, and collaborative improvement techniques for high-quality software delivery.
receiving-code-review
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation.
code-review-quality
Conduct context-driven code reviews focusing on quality, testability, and maintainability. Use when reviewing code, providing feedback, or establishing review practices.
stage-coach
Consume CocoSentinel per-stage external coach requests and produce stage quality scores.
code-review
Use to judge a concrete diff, branch, or GitHub PR on its own merits with no rsc-SDD spec/plan chain to key off — the spec-less giving pass behind /code-review: only findings you can defend, one verdict, read-only unless --comment or --fix. NOT the SDD gate keyed to 02-DOCS/wiki/sdd/ that also processes incoming…
code-review-expert
Expert-level code review focusing on quality, security, performance, and maintainability. Use this skill for conducting thorough code reviews, identifying issues, and providing constructive feedback.