permission-management
Central authority for Claude Code permissions. Covers permission system (tiered model, read-only, bash, file modification), permission rules (allow, ask, deny), rule precedence, permission modes (default, acceptEdits, plan, bypassPermissions), tool-specific permission rules (Bash patterns, Read/Edit patterns, WebFetch domains, MCP tools), /permissions command, and additionalDirectories. Assists with configuring permission rules, understanding permission modes, and troubleshooting permission issues. Delegates 100% to docs-management skill for official documentation.
What this skill does
# Permission Management Skill ## MANDATORY: Invoke docs-management First > **STOP - Before providing ANY response about Claude Code permissions:** > > 1. **INVOKE** `docs-management` skill > 2. **QUERY** for the user's specific topic > 3. **BASE** all responses EXCLUSIVELY on official documentation loaded > > **Skipping this step results in outdated or incorrect information.** ### Verification Checkpoint Before responding, verify: - [ ] Did I invoke docs-management skill? - [ ] Did official documentation load? - [ ] Is my response based EXCLUSIVELY on official docs? If ANY checkbox is unchecked, STOP and invoke docs-management first. --- ## Overview Central authority for Claude Code permissions. This skill uses **100% delegation to docs-management** - it contains NO duplicated official documentation. **Architecture:** Pure delegation with keyword registry. All official documentation is accessed via docs-management skill queries. ## When to Use This Skill **Keywords:** permissions, allow rules, deny rules, ask rules, permission modes, defaultMode, acceptEdits, bypassPermissions, plan mode, tool permissions, Bash permissions, Read permissions, Edit permissions, WebFetch permissions, MCP permissions, additionalDirectories, /permissions **Use this skill when:** - Configuring permission rules - Understanding permission modes - Setting up tool-specific permissions - Troubleshooting permission issues - Adding additional working directories - Understanding rule precedence ## Keyword Registry for docs-management Queries Use these keywords when querying docs-management skill for official documentation: ### Permission System | Topic | Keywords | | --- | --- | | Overview | "permission system", "tiered permissions", "approval required" | | Configuration | "configuring permissions", "/permissions command" | | Rule Types | "allow rules", "ask rules", "deny rules" | | Precedence | "rule precedence", "deny > ask > allow" | ### Permission Modes > ⚠️ **STALENESS WARNING:** Do NOT hardcode permission mode names or values. > Query docs-management for the authoritative list of permission modes. | Topic | Query Pattern | What You'll Find | | --- | --- | --- | | All Modes | "iam.md permission modes" | Complete list of available modes | | Mode Behavior | "iam.md defaultMode acceptEdits" | Mode descriptions and effects | | Mode Configuration | "iam.md configuring permission mode" | How to set modes | ### Tool-Specific Rules > ⚠️ **STALENESS WARNING:** Do NOT hardcode tool names or pattern syntax. > Query docs-management for the authoritative list of tools and permission patterns. | Topic | Query Pattern | What You'll Find | | --- | --- | --- | | Bash Rules | "iam.md Bash permissions pattern matching" | Bash permission syntax | | File Rules | "iam.md Read Edit permissions gitignore" | File permission patterns | | Path Patterns | "iam.md path pattern types" | Absolute, home, relative patterns | | WebFetch Rules | "iam.md WebFetch domain permissions" | Domain pattern syntax | | MCP Rules | "iam.md MCP permissions mcp__server" | MCP tool permission syntax | ### Security Considerations (v2.1.6+) > ⚠️ **SECURITY:** These topics cover security-sensitive permission behaviors. > Query docs-management for the authoritative guidance. | Topic | Query Pattern | What You'll Find | | --- | --- | --- | | Wildcard + Shell Operators | "iam.md wildcard rules shell operators compound commands" | SECURITY FIX (v2.1.7): Wildcard rules matching compound commands | | Line Continuation Bypass | "iam.md permission bypass line continuation" | SECURITY FIX (v2.1.6): Shell line continuation escape prevention | ### Working Directories | Topic | Keywords | | --- | --- | | Additional Dirs | "additionalDirectories", "--add-dir" | | Working Directory | "working directories", "file access scope" | ## Quick Decision Tree **What do you want to do?** 1. **Set up allow rules** -> Query docs-management: "allow rules", "auto-approve" 2. **Set up deny rules** -> Query docs-management: "deny rules", "prevent usage" 3. **Set up ask rules** -> Query docs-management: "ask rules", "confirmation required" 4. **Change permission mode** -> Query docs-management: "permission modes", "defaultMode" 5. **Configure Bash permissions** -> Query docs-management: "Bash permissions", "Bash pattern matching" 6. **Configure file permissions** -> Query docs-management: "Read Edit permissions", "gitignore-style" 7. **Add working directories** -> Query docs-management: "additionalDirectories", "--add-dir" 8. **Configure MCP permissions** -> Query docs-management: "MCP permissions", "mcp__server" ## Topic Coverage ### Permission System Topics - Tiered permission model (read-only, bash, file modification) - Allow rules (auto-approve) - Ask rules (confirmation required) - Deny rules (prevent usage) - Rule precedence (deny > ask > allow) - Permission rule format ### Permission Modes Topics - default mode (standard prompting) - acceptEdits mode (auto-accept file edits) - plan mode (analyze only, no modifications) - bypassPermissions mode (skip all prompts) ### Tool Permission Rules - Bash permission patterns (exact match, prefix match) - Bash pattern limitations - Read and Edit gitignore-style patterns - Path pattern types (absolute, home, relative) - WebFetch domain permissions - MCP tool permissions (no wildcards) - Hooks for custom permission evaluation ### Working Directories Topics - additionalDirectories configuration - --add-dir CLI flag - Scope of file access ## Troubleshooting Quick Reference | Issue | Keywords for docs-management | | --- | --- | | Permission too restrictive | "allow rules", "auto-approve" | | Permission too permissive | "deny rules", "prevent usage" | | Wrong mode active | "permission modes", "defaultMode" | | MCP tools blocked | "MCP permissions", "mcp__server" | | Can't access files | "additionalDirectories", "--add-dir" | ## Related Skills - **sandbox-configuration** - For sandboxing and isolation - **enterprise-security** - For managed policies - **settings-management** - For general configuration ## Version History - **v1.1.0** (2026-01-16): Security fixes keyword registry - Added Security Considerations section (v2.1.6+) - Added wildcard + shell operators security fix keywords (v2.1.7) - Added line continuation bypass security fix keywords (v2.1.6) - **v1.0.0** (2025-11-30): Initial release (split from security-meta) - Focused on permissions only - Pure delegation architecture - Comprehensive keyword registry --- ## Last Updated **Date:** 2026-01-16 **Model:** claude-opus-4-5-20251101
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.