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 ArabelaTso/Skills-4-SE --skill semantic-bug-detectorgit clone --depth 1 https://github.com/ArabelaTso/Skills-4-SEWrote 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/arabelatso/skills-4-se/semantic-bug-detector)<a href="https://agentmods.dev/skills/arabelatso/skills-4-se/semantic-bug-detector"><img src="https://agentmods.dev/badge/skills/arabelatso/skills-4-se/semantic-bug-detector/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/arabelatso/skills-4-se/semantic-bug-detector"><img src="https://agentmods.dev/badge/skills/arabelatso/skills-4-se/semantic-bug-detector.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 248 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 | $0.00106 | $0.02673 |
| Opus 5 | $0.00053 | $0.01337 |
| Sonnet 5 | $0.00021 | $0.00535 |
| Haiku 4.5 | $0.00011 | $0.00267 |
Grade A, and why
semantic-bug-detector 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 — 387 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Semantic Bug Detector
Detect bugs where code behavior doesn't match its intended purpose.
Overview
This skill analyzes code to find semantic bugs—errors where the implementation contradicts the intent expressed through names, comments, and documentation. Unlike syntax errors or type errors, semantic bugs are logically valid code that does the wrong thing.
How to Use
Provide code with any of:
- Function/variable names that express intent
- Comments describing what code should do
- Docstrings specifying behavior
- Documentation stating requirements
The skill will:
- Infer intended behavior from these sources
- Analyze actual implementation
- Identify mismatches
- Report semantic bugs with explanations
Detection Workflow
Step 1: Extract Intent
Gather intent signals from multiple sources:
Names: is_even, get_last_n_elements, calculate_average
- Infer expected behavior from naming conventions
- Identify predicates (is_, has_, can_)
- Recognize operations (get_, set_, calculate_)
Comments: // Returns first n elements, # Check if x is positive
- Parse inline comments
- Extract stated purpose
- Identify boundary specifications
Docstrings:
"""Calculate the average of a list of numbers.
Returns the sum divided by the count."""
- Parse structured documentation
- Extract preconditions and postconditions
- Identify range specifications
Step 2: Analyze Implementation
Examine actual code behavior:
Control flow: Conditions, loops, branches Operations: Arithmetic, logical, comparison operators Boundaries: Array indices, range limits Edge cases: Empty input, null values, zero divisors
Step 3: Compare Intent vs Implementation
Check for common mismatches:
Off-by-one errors: Using n+1 when should use n
Inverted logic: Returning opposite boolean value
Wrong operator: Using * when should use /
Boundary errors: Inclusive when should be exclusive
Missing checks: Not handling empty/null input
What ships with it
1 file 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.
- 9d ago First seen · 387 lines · 106 tokens per session scan A 8977aa19261e
semantic-bug-detector is a skill published in the GitHub repository ArabelaTso/Skills-4-SE (252 stars, last pushed 22d ago), licensed Apache-2.0. It adds 106 tokens to every session and 2,673 once invoked, about $0.0005 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
perf-profiler
A performance investigation guide that uses repeatable measurements and profiling evidence to find where software spends time or resources. Profiling records runtime activity such as CPU use, memory use, database work, or network delays.
log-analyzer
A log-analysis helper that reads application and system logs to find unusual patterns and likely causes. Logs are records of events such as errors, requests, warnings, and service activity.
trace
Trace Elixir call trees from entry points via mix xref. Use when debugging data flow, planning signature changes, or understanding how a bug reaches code.
code-review-web
Review web application code for bugs, security issues, performance problems, and stack-specific anti-patterns. Use this skill whenever the user wants to review code, debug a production issue, investigate a build failure, audit security, or check a PR before merging. Triggers on code review, review my code, debug…
bim-consistency-checker
Check BIM model consistency: naming conventions, parameter completeness, spatial relationships, and data integrity across model elements.
022-root-cause-analysis
Use when a framed problem needs root-cause investigation rather than a symptom-level fix, applying Five Whys, Fishbone (Ishikawa), Current Reality Tree, and constraint identification. This should trigger when an issue's Root Cause Analysis point of view needs evaluation, or when a maintainer directly asks to find the…