aiskillstore/marketplace / skills/89jobrien/tool-presets
tool-presets
VerifiedStandardized tool set definitions for Claude Code agents ensuring consistent tool access across similar agent types
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 2.0 KB |
| analysis.md | markdown | 610 B |
| dev-tools.md | markdown | 635 B |
| file-ops.md | markdown | 699 B |
| orchestration.md | markdown | 704 B |
| research.md | markdown | 657 B |
| skill-report.json | config | 24.1 KB |
skill-report.json
View on GitHub{
"schema_version": "2.0",
"meta": {
"generated_at": "2026-07-05T14:07:20.778Z",
"slug": "89jobrien-tool-presets",
"source_url": "https://github.com/89jobrien/steve/tree/main/steve/skills/tool-presets",
"source_ref": "main",
"model": "codex",
"analysis_version": "3.0.0",
"source_type": "community",
"content_hash": "a1d26498ab5b9b980bdb256ef42fa2fb5b10cb42f7821b7427e53437c99a6b0c",
"tree_hash": "ed742ef669d04cd49701fb3a33028b97b0c22140222905c6ed50495e0d490bb9",
"provenance": {
"model_effective": "codex",
"fallback_chain": [
{
"agent": "codex",
"outcome": "success"
}
],
"analysis_version": "3.0.0"
}
},
"skill": {
"name": "tool-presets",
"description": "Standardized tool preset references for Claude Code agents across development, file operations, analysis, research, and coordination roles.",
"summary": "Provides reusable Claude Code tool preset guidance for agent definitions.",
"icon": "📦",
"version": "1.0.2",
"author": "Joseph OBrien",
"license": "MIT",
"category": "coding",
"tags": [
"claude-code",
"tool-presets",
"agent-configuration",
"developer-workflows",
"permissions"
],
"supported_tools": [
"claude",
"codex",
"claude-code"
],
"risk_factors": [
"external_commands"
]
},
"security_audit": {
"risk_level": "low",
"is_blocked": false,
"safe_to_publish": true,
"analysis_status": "ok",
"summary": "The static analyzer flagged Markdown backticks in SKILL.md as Ruby or shell execution. All static findings are documentation formatting or inline preset names, not executable code, but the full-stack preset should be used with least-privilege review.",
"remediation": [
{
"issue": "Broad full-stack preset guidance",
"suggestion": "Add a short least-privilege warning before recommending all tools for comprehensive agents.",
"severity": "low"
}
],
"risk_factor_evidence": [
{
"factor": "external_commands",
"evidence": [
{
"file": "SKILL.md",
"line_start": 20,
"line_end": 20
},
{
"file": "SKILL.md",
"line_start": 21,
"line_end": 21
},
{
"file": "SKILL.md",
"line_start": 22,
"line_end": 22
},
{
"file": "SKILL.md",
"line_start": 23,
"line_end": 23
},
{
"file": "SKILL.md",
"line_start": 24,
"line_end": 24
},
{
"file": "SKILL.md",
"line_start": 25,
"line_end": 25
},
{
"file": "SKILL.md",
"line_start": 31,
"line_end": 38
},
{
"file": "SKILL.md",
"line_start": 38,
"line_end": 42
},
{
"file": "SKILL.md",
"line_start": 42,
"line_end": 48
},
{
"file": "SKILL.md",
"line_start": 48,
"line_end": 54
},
{
"file": "SKILL.md",
"line_start": 54,
"line_end": 60
},
{
"file": "SKILL.md",
"line_start": 60,
"line_end": 66
},
{
"file": "SKILL.md",
"line_start": 66,
"line_end": 72
},
{
"file": "SKILL.md",
"line_start": 72,
"line_end": 81
},
{
"file": "SKILL.md",
"line_start": 81,
"line_end": 82
},
{
"file": "SKILL.md",
"line_start": 82,
"line_end": 83
},
{
"file": "SKILL.md",
"line_start": 83,
"line_end": 84
},
{
"file": "SKILL.md",
"line_start": 84,
"line_end": 85
}
]
}
],
"static_findings": [
{
"id": "external_commands:SKILL.md:20:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 20,
"line_end": 20,
"snippet": "| `dev-tools` | Read, Write, Edit, Bash | Development/coding agents |"
},
{
"id": "external_commands:SKILL.md:21:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 21,
"line_end": 21,
"snippet": "| `file-ops` | Read, Write, Edit, Grep, Glob | File manipulation agents |"
},
{
"id": "external_commands:SKILL.md:22:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 22,
"line_end": 22,
"snippet": "| `analysis` | Read, Grep, Glob, Bash | Code analysis agents |"
},
{
"id": "external_commands:SKILL.md:23:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 23,
"line_end": 23,
"snippet": "| `research` | Read, Write, WebSearch, WebFetch | Research agents |"
},
{
"id": "external_commands:SKILL.md:24:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 24,
"line_end": 24,
"snippet": "| `orchestration` | Read, Write, Edit, Task, TodoWrite | Coordinator agents |"
},
{
"id": "external_commands:SKILL.md:25:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 25,
"line_end": 25,
"snippet": "| `full-stack` | All tools | Comprehensive agents |"
},
{
"id": "external_commands:SKILL.md:31:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 31,
"line_end": 38,
"snippet": "```yaml"
},
{
"id": "external_commands:SKILL.md:38:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 38,
"line_end": 42,
"snippet": "```"
},
{
"id": "external_commands:SKILL.md:42:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 42,
"line_end": 48,
"snippet": "### When to use `dev-tools`"
},
{
"id": "external_commands:SKILL.md:48:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 48,
"line_end": 54,
"snippet": "### When to use `file-ops`"
},
{
"id": "external_commands:SKILL.md:54:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 54,
"line_end": 60,
"snippet": "### When to use `analysis`"
},
{
"id": "external_commands:SKILL.md:60:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 60,
"line_end": 66,
"snippet": "### When to use `research`"
},
{
"id": "external_commands:SKILL.md:66:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 66,
"line_end": 72,
"snippet": "### When to use `orchestration`"
},
{
"id": "external_commands:SKILL.md:72:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 72,
"line_end": 81,
"snippet": "### When to use `full-stack`"
},
{
"id": "external_commands:SKILL.md:81:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 81,
"line_end": 82,
"snippet": "- `dev-tools.md` - Development tools preset"
},
{
"id": "external_commands:SKILL.md:82:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 82,
"line_end": 83,
"snippet": "- `file-ops.md` - File operations preset"
},
{
"id": "external_commands:SKILL.md:83:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 83,
"line_end": 84,
"snippet": "- `analysis.md` - Code analysis preset"
},
{
"id": "external_commands:SKILL.md:84:ruby-shell-backtick-execution",
"category": "external_commands",
"severity": "medium",
"pattern": "Ruby/shell backtick execution",
"file": "SKILL.md",
"line_start": 84,
"line_end": 85,
"snippet": "- `research.md` - Research tools preset"
}
],
"finding_verdicts": [
{
"id": "external_commands:SKILL.md:20:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.97,
"reason": "Line 20 is a Markdown table row that uses backticks for the dev-tools preset name. It documents Bash as an included tool but does not execute a command."
},
{
"id": "external_commands:SKILL.md:21:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "Line 21 is a Markdown table row using inline code formatting for a preset name. There is no shell, Ruby, or dynamic command execution syntax."
},
{
"id": "external_commands:SKILL.md:22:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.97,
"reason": "Line 22 is documentation for the analysis preset and lists Bash as a permitted tool. The backticks are Markdown formatting, not executable code."
},
{
"id": "external_commands:SKILL.md:23:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "Line 23 is a Markdown table entry for the research preset. It contains inline code formatting only and no command invocation."
},
{
"id": "external_commands:SKILL.md:24:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "Line 24 is a Markdown table entry for the orchestration preset. The backticks mark text as inline code and do not trigger shell execution."
},
{
"id": "external_commands:SKILL.md:25:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.96,
"reason": "Line 25 documents a full-stack preset using inline Markdown backticks. It is broad permission guidance, but it is not Ruby or shell execution."
},
{
"id": "external_commands:SKILL.md:31:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "Lines 31-38 are a fenced YAML example for agent frontmatter. The triple backticks delimit a documentation block and do not execute code."
},
{
"id": "external_commands:SKILL.md:38:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.99,
"reason": "Lines 38-42 close the Markdown code fence and introduce a selection guide. The backticks are Markdown syntax rather than a shell construct."
},
{
"id": "external_commands:SKILL.md:42:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "Line 42 is a Markdown heading with an inline preset name. It does not contain Ruby, shell syntax, or command execution."
},
{
"id": "external_commands:SKILL.md:48:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "Line 48 is a Markdown heading for the file-ops preset. The backticks are used only to format the preset label."
},
{
"id": "external_commands:SKILL.md:54:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "Line 54 is a Markdown heading naming the analysis preset. There is no executable instruction or dynamic command string."
},
{
"id": "external_commands:SKILL.md:60:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "Line 60 is a Markdown heading for the research preset. It uses inline code formatting only and has no command execution path."
},
{
"id": "external_commands:SKILL.md:66:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "Line 66 is a Markdown heading for the orchestration preset. The detected backticks are harmless inline documentation formatting."
},
{
"id": "external_commands:SKILL.md:72:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.97,
"reason": "Line 72 is a Markdown heading for the full-stack preset. It does not execute commands, although the broad preset deserves least-privilege review."
},
{
"id": "external_commands:SKILL.md:81:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "Line 81 is a reference list item naming dev-tools.md with Markdown inline code formatting. It is not a command or executable expression."
},
{
"id": "external_commands:SKILL.md:82:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "Line 82 is a reference list item naming file-ops.md. The backticks are only Markdown formatting around a file name."
},
{
"id": "external_commands:SKILL.md:83:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "Line 83 is a reference list item naming analysis.md. It contains no shell command, Ruby code, or executable content."
},
{
"id": "external_commands:SKILL.md:84:ruby-shell-backtick-execution",
"verdict": "false_positive",
"confidence": 0.98,
"reason": "Line 84 is a reference list item naming research.md with inline Markdown formatting. It is not an external command."
}
],
"semantic_findings": [
{
"title": "Broad Tool Access Guidance",
"description": "SKILL.md describes the full-stack preset as all tools for comprehensive agents. This can lead to over-permissioned agents if users copy it without review.",
"severity": "low",
"locations": [
{
"file": "SKILL.md",
"line_start": 25,
"line_end": 25
},
{
"file": "SKILL.md",
"line_start": 72,
"line_end": 75
}
],
"confidence": 0.68,
"confidence_reasoning": "The broad access guidance is explicit, but the skill is documentation and does not grant tools automatically. The risk depends on downstream agent configuration choices."
}
],
"critical_findings": [],
"high_findings": [],
"medium_findings": [],
"low_findings": [
{
"title": "Broad Tool Access Guidance",
"description": "SKILL.md describes the full-stack preset as all tools for comprehensive agents. This can lead to over-permissioned agents if users copy it without review.",
"locations": [
{
"file": "SKILL.md",
"line_start": 25,
"line_end": 25
},
{
"file": "SKILL.md",
"line_start": 72,
"line_end": 75
}
],
"review_kind": "security",
"source_category": "semantic",
"source_severity": "low",
"confidence": 0.68,
"confidence_reasoning": "The broad access guidance is explicit, but the skill is documentation and does not grant tools automatically. The risk depends on downstream agent configuration choices."
}
],
"dangerous_patterns": [],
"files_scanned": 6,
"total_lines": 242,
"audit_model": "codex",
"audited_at": "2026-07-05T14:07:20.778Z",
"agent_auto_install_policy": "allowed",
"manual_install_policy": "allowed"
},
"content": {
"user_title": "Standardize Claude Code Tool Presets",
"value_statement": "Agent tool access can vary across similar roles, creating inconsistent workflows. This skill documents reusable Claude Code presets for development, analysis, research, and coordination agents.",
"seo_keywords": [
"Claude",
"Codex",
"Claude Code",
"tool presets",
"agent tools",
"developer agents",
"code analysis",
"research agents",
"workflow orchestration",
"Claude skills"
],
"actual_capabilities": [
"Lists six named tool presets and their included tool sets.",
"Explains when to choose development, file operations, analysis, research, orchestration, and full-stack presets.",
"Provides a frontmatter example for applying a preset pattern to an agent definition.",
"Documents separate reference files for development, file operations, analysis, research, and orchestration presets.",
"Identifies example agent roles that fit each detailed preset."
],
"limitations": [
"Does not enforce permissions or update agent files automatically.",
"Does not include executable scripts or runtime validation.",
"Full-stack guidance is broad and should be reviewed before use.",
"Preset names still require tool names to be copied into each agent definition."
],
"use_cases": [
{
"title": "Configure Developer Agents",
"description": "Choose consistent tool access for agents that write code, run tests, and handle build tasks.",
"target_user": "AI tool builders"
},
{
"title": "Document Agent Standards",
"description": "Create a shared reference for teams that maintain several Claude Code agent definitions.",
"target_user": "Platform teams"
},
{
"title": "Review Tool Access",
"description": "Compare preset choices before granting Bash, web access, write access, or coordination tools.",
"target_user": "Engineering leads"
}
],
"prompt_templates": [
{
"title": "Choose a Preset",
"scenario": "Beginner setup for one new agent",
"prompt": "I am creating a Claude Code agent for documentation updates. Use the tool-presets skill to recommend the best preset and explain why."
},
{
"title": "Apply a Preset",
"scenario": "Add a preset pattern to an agent definition",
"prompt": "Use the tool-presets skill to update my agent plan with the right tools for code refactoring without shell execution."
},
{
"title": "Compare Access Levels",
"scenario": "Select between similar presets",
"prompt": "Compare dev-tools, file-ops, and analysis for a code review agent. Recommend the least privileged preset that still supports the work."
},
{
"title": "Design an Agent Matrix",
"scenario": "Advanced team standardization",
"prompt": "Use the tool-presets skill to build a permission matrix for developer, reviewer, researcher, and coordinator agents across our team."
}
],
"output_examples": [
{
"input": "Select a preset for an agent that edits documentation and searches files.",
"output": "Recommended preset: file-ops. It supports reading, writing, editing, and search without shell execution."
},
{
"input": "Compare dev-tools and analysis for a static review agent.",
"output": "Use analysis when the agent needs read-only search plus diagnostic commands. Use dev-tools only when the agent must modify code."
},
{
"input": "Plan presets for a research coordinator.",
"output": [
"Research worker: research preset for web and source gathering.",
"Coordinator: orchestration preset for task planning and delegation.",
"Reviewer: analysis preset for checking source material and results."
]
}
],
"best_practices": [
"Select the least capable preset that can complete the agent task.",
"Review Bash, WebSearch, WebFetch, and Task access before copying a preset.",
"Document the reason for each preset choice in the agent definition."
],
"anti_patterns": [
"Assigning full-stack to every agent for convenience.",
"Giving Bash access to agents that only need read-only analysis.",
"Treating preset documentation as permission enforcement."
],
"faq": [
{
"question": "Does this skill execute commands?",
"answer": "No. It is documentation for choosing tool sets and does not run commands by itself."
},
{
"question": "Which tools does the dev-tools preset include?",
"answer": "It includes Read, Write, Edit, and Bash for agents that need development and test workflows."
},
{
"question": "When should I use file-ops?",
"answer": "Use file-ops for file edits, search, refactoring, and documentation updates that do not need shell execution."
},
{
"question": "Is full-stack safe for every agent?",
"answer": "No. Full-stack is broad and should be reserved for agents that truly need all capabilities."
},
{
"question": "Can Codex use this skill?",
"answer": "Yes. The report marks support for Claude, Codex, and Claude Code, but the content is written around Claude Code tool names."
},
{
"question": "Does the skill validate my agent configuration?",
"answer": "No. It provides preset guidance. You still need to review the final tool list before use."
}
]
},
"file_structure": [
{
"name": "analysis.md",
"type": "file",
"path": "analysis.md",
"lines": 31
},
{
"name": "dev-tools.md",
"type": "file",
"path": "dev-tools.md",
"lines": 31
},
{
"name": "file-ops.md",
"type": "file",
"path": "file-ops.md",
"lines": 31
},
{
"name": "orchestration.md",
"type": "file",
"path": "orchestration.md",
"lines": 32
},
{
"name": "research.md",
"type": "file",
"path": "research.md",
"lines": 31
},
{
"name": "SKILL.md",
"type": "file",
"path": "SKILL.md",
"lines": 86
}
]
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |