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 syhya/mlsys26-flashinfer-contest --skill code-analysisgit clone --depth 1 https://github.com/syhya/mlsys26-flashinfer-contestWrote 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/syhya/mlsys26-flashinfer-contest/code-analysis)<a href="https://agentmods.dev/skills/syhya/mlsys26-flashinfer-contest/code-analysis"><img src="https://agentmods.dev/badge/skills/syhya/mlsys26-flashinfer-contest/code-analysis/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/syhya/mlsys26-flashinfer-contest/code-analysis"><img src="https://agentmods.dev/badge/skills/syhya/mlsys26-flashinfer-contest/code-analysis.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 | $0.00024 | $0.03708 |
| Opus 5.5 | $0.00010 | $0.01483 |
| Sonnet 5.5 | $0.00005 | $0.00742 |
| Haiku 4.5 | $0.00002 | $0.00371 |
Grade A, and why
code-analysis scanned grade A with 1 finding 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
result = subprocess.run([ How it starts
The opening of the file, as written. The whole thing — 636 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Analysis & Bug Hunting Skill
This skill provides systematic approaches for analyzing code, identifying issues, and proposing fixes.
Purpose
Use this skill when your task involves:
- Finding bugs in existing code
- Code quality review
- Performance optimization suggestions
- Security vulnerability detection
- Refactoring recommendations
- Best practices enforcement
Key Capabilities
1. Bug Detection
- Logic errors (off-by-one, null checks, etc.)
- Type mismatches and conversion issues
- Resource leaks (file handles, connections)
- Concurrency issues (race conditions, deadlocks)
- Exception handling gaps
- Edge case failures
2. Code Quality Issues
- Code duplication
- Overly complex functions
- Poor naming conventions
- Missing documentation
- Inconsistent formatting
- Dead code
3. Performance Problems
- Inefficient algorithms (O(n²) where O(n) possible)
- Unnecessary loops or operations
- Memory leaks
- Excessive I/O operations
- Missing caching opportunities
- Database query inefficiencies
4. Security Vulnerabilities
- SQL injection risks
- XSS vulnerabilities
- Insecure authentication
- Exposed secrets/credentials
- Insufficient input validation
- Path traversal risks
Bug Hunting Workflow
Phase 1: Code Understanding
1. Read all files to understand codebase structure
2. Identify entry points and main workflows
3. Map dependencies between components
4. Note external dependencies and APIs used
Phase 2: Issue Detection
1. Static analysis (read code carefully)
2. Look for common bug patterns
3. Check error handling coverage
4. Validate input/output handling
5. Review edge cases
Phase 3: Issue Documentation
For each issue found, document:
- Location: file:line_number
- Severity: Critical / High / Medium / Low
- Category: Bug / Performance / Security / Quality
- Description: What's wrong
- Impact: What could go wrong
- Recommendation: How to fix it
- Code example: Before and after
Phase 4: Fix Implementation
1. Prioritize by severity
2. Implement fixes one at a time
3. Preserve existing functionality
4. Add comments explaining changes
5. Ensure backward compatibility (if needed)
What ships with it
7 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.
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 · 636 lines · 24 tokens per session scan A 93359b13bb54
code-analysis is a skill published in the GitHub repository syhya/mlsys26-flashinfer-contest (23 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 24 tokens to every session and 3,708 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
network-exam-practice
Use this skill whenever the user wants computer network exam preparation, final review, 408-style networking practice, chapter quizzes, subnetting calculations, routing table problems, TCP sequence/ACK questions, protocol analysis, answer grading, or mistake diagnosis.
oracle
Use the @steipete/oracle CLI to bundle a prompt plus the right files and get a second-model review (API or browser) for debugging, refactors, design checks, or cross-validation.
doubt-driven-development
Subjects every non-trivial decision to a fresh-context adversarial review before it stands. Use when you want every assumption cross-examined before proceeding, when stress-testing a plan for hidden failure modes, when correctness matters more than speed, when working in unfamiliar code, when stakes are high…
check
Reviews diffs, PRs, release readiness, and publishing follow-through. Use when asked to review, triage issues or PRs, or ship. Not for debugging root causes or prose.
ego-lite-simplify
Find and implement evidence-backed simplifications in the ego-lite repository. Use when reviewing the codebase for dead code, duplicated state or APIs, speculative abstractions, unnecessary compatibility layers, hand-written infrastructure, excessive tests or documentation, or when the user asks to reduce code size or…
safe-refactoring
Execute behavior-preserving or intentionally scoped refactors safely. Use this for multi-file renames, component/service extraction, state-management changes, API migrations, concurrency refactors, or any request where unrelated user work and subtle contracts must be preserved.