Claude Scholar is a semi-automated research assistant for academic research and software development, supporting literature review, coding, experiments, reporting, writing, and project knowledge management. Computer science and AI researchers use it across the research workflow with several coding-agent platforms; the catalogue contains its skills, commands, agents, hooks, plugin, and instruction.
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 Galaxy-Dawn/claude-scholar --skill bug-detectivegit clone --depth 1 https://github.com/Galaxy-Dawn/claude-scholarWrote 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/galaxy-dawn/claude-scholar/bug-detective)<a href="https://agentmods.dev/skills/galaxy-dawn/claude-scholar/bug-detective"><img src="https://agentmods.dev/badge/skills/galaxy-dawn/claude-scholar/bug-detective/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/galaxy-dawn/claude-scholar/bug-detective"><img src="https://agentmods.dev/badge/skills/galaxy-dawn/claude-scholar/bug-detective.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
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 →
- high Tool Misuse · line 158 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 161 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- high Tool Misuse · line 161 Tool calls are chained to bypass individual safety checks or escalate capabilities beyond what any single tool call would allow.Fix: Limit tool chaining depth and validate the output of each tool before passing it to the next. Require explicit user approval for multi-step chains.
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 | $0.00075 | $0.02114 |
| Opus 5 | $0.00037 | $0.01057 |
| Sonnet 5 | $0.00015 | $0.00423 |
| Haiku 4.5 | $0.00007 | $0.00211 |
Grade C, and why
bug-detective scanned grade C 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 11d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf $dir/* # If dir is empty, deletes all files in current directory How it starts
The opening of the file, as written. The whole thing — 308 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bug Detective
A systematic debugging workflow for investigating and resolving code errors, exceptions, and failures. Provides structured debugging methods and common error pattern recognition.
Core Philosophy
Debugging is a scientific problem-solving process that requires:
- Understand the problem - Clearly define symptoms and expected behavior
- Gather evidence - Collect error messages, logs, stack traces
- Form hypotheses - Infer possible causes based on evidence
- Verify hypotheses - Confirm or eliminate causes through experiments
- Resolve the issue - Apply fixes and verify
Debugging Workflow
Step 1: Understand the Problem
Before starting to debug, clarify the following information:
Required information to collect:
- Complete error message content
- Exact location of the error (filename and line number)
- Reproduction steps (how to trigger the error)
- Expected behavior vs actual behavior
- Environment info (OS, versions, dependencies)
Question template:
1. What is the exact error message?
2. Which file and line does the error occur at?
3. How can this issue be reproduced? Provide detailed steps.
4. What was the expected result? What actually happened?
5. What recent changes might have introduced this issue?
Step 2: Analyze Error Type
Choose a debugging strategy based on error type:
| Error Type | Characteristics | Debugging Method |
|---|---|---|
| Syntax Error | Code cannot be parsed | Check syntax, bracket matching, quotes |
| Import Error | ModuleNotFoundError | Check module installation, path config |
| Type Error | TypeError | Check data types, type conversions |
| Attribute Error | AttributeError | Check if object attribute exists |
| Key Error | KeyError | Check if dictionary key exists |
| Index Error | IndexError | Check list/array index range |
| Null Reference | NoneType/NullPointerException | Check if variable is None |
| Network Error | ConnectionError/Timeout | Check network connection, URL, timeout settings |
| Permission Error | PermissionError | Check file permissions, user permissions |
| Resource Error | FileNotFoundError | Check if file path exists |
What ships with it
8 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.
- examples/debugging-workflow.py 6.2 KB runs code
- examples/debugging-workflow.sh 8.6 KB runs code
- examples/error-handling-patterns.py 8.5 KB runs code
- references/common-patterns.md 5.5 KB
- references/debugging-tools.md 405 B
- references/javascript-errors.md 490 B
- references/python-errors.md 5.5 KB
- references/shell-errors.md 3.5 KB
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.
- 11d ago First seen · 308 lines · 75 tokens per session scan C ab228dd490b6
bug-detective is a skill published in the GitHub repository Galaxy-Dawn/claude-scholar (5,419 stars, last pushed 14d ago), licensed MIT. It adds 75 tokens to every session and 2,114 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
tfx-find
A codebase search tool for quickly locating files, functions, classes, variables, text, and project structure. A codebase is the collection of source files that make up a software project.
do-it-code-quality
Use when designing, changing, or debugging code to locate causal ownership and close the affected behavior.
debug
Debug a stubborn bug with a deterministic reproduction, hypothesis ledger, one-variable fixes, and a regression test. Use after the first obvious look fails, reproduction is unclear, or a fix attempt failed. Not for routine obvious failures; use for "ไล่บั๊ก".
bisect
Pinpoint the first bad commit for a reproducible regression in a safe temporary worktree. Use when HEAD is bad, a known revision is good, and one unattended command distinguishes them; handles flaky endpoints and git-bisect skip exit 125.
bug-finder
Hunt for previously unknown correctness defects in an existing repository by deriving invariants, prioritizing high-risk surfaces, generating concrete bug candidates, and proving or retiring them with bounded evidence. Use when the user asks to find bugs, hidden defects, races, lifecycle failures, data-loss paths, or…
codebase-improvement-planner
Discover and prioritize evidence-backed opportunities to improve an existing codebase when no specific change has been chosen yet, then recommend the highest-value next upgrade and optionally execute an approved bounded maintenance slice. Use when the user asks what should be improved, modernized, simplified…