plugin-settings
Configure per-project plugin settings via .claude/plugin-name.local.md files. Use when building plugins with user-configurable behavior, storing agent state, or controlling hooks.
What this skill does
# Plugin Settings Pattern
Per-project plugin configuration using `.claude/plugin-name.local.md` files with YAML frontmatter for structured settings and markdown body for additional context.
## When to Use This Skill
| Use plugin settings when... | Use alternatives when... |
|-----------------------------|--------------------------|
| Plugin needs per-project configuration | Settings are global (use `~/.claude/settings.json`) |
| Hooks need runtime enable/disable control | Hook behavior is always-on |
| Agent state persists between sessions | State is ephemeral within a session |
| Users customize plugin behavior per-project | Plugin has no configurable behavior |
| Configuration includes prose/prompts alongside structured data | All config is purely structured (use `.json`) |
## File Structure
### Location
```
project-root/
└── .claude/
└── plugin-name.local.md # Per-project, user-local settings
```
### Format
```markdown
---
enabled: true
mode: standard
max_retries: 3
allowed_extensions: [".js", ".ts", ".tsx"]
---
# Additional Context
Markdown body for prompts, instructions, or documentation
that hooks and agents can read and use.
```
### Naming Convention
- Use `.claude/plugin-name.local.md` format
- Match the plugin name exactly from `plugin.json`
- The `.local.md` suffix signals user-local (not committed to git)
### Gitignore
Add to project `.gitignore`:
```gitignore
.claude/*.local.md
```
## Reading Settings
### From Shell Scripts (Hooks)
Use the standard frontmatter extraction pattern from `.claude/rules/shell-scripting.md`:
```bash
#!/bin/bash
set -euo pipefail
STATE_FILE=".claude/my-plugin.local.md"
# Quick exit if not configured
[[ -f "$STATE_FILE" ]] || exit 0
# Extract field using standard pattern
extract_field() {
local file="$1" field="$2"
head -50 "$file" | grep -m1 "^${field}:" | sed 's/^[^:]*:[[:space:]]*//' | tr -d '\r'
}
plugin_enabled=$(extract_field "$STATE_FILE" "enabled")
[[ "$plugin_enabled" == "true" ]] || exit 0
plugin_mode=$(extract_field "$STATE_FILE" "mode")
```
### Extract Markdown Body
```bash
# Get content after the closing --- frontmatter delimiter
BODY=$(awk '/^---$/{i++; next} i>=2' "$STATE_FILE")
```
### From Skills and Agents
Skills and agents read settings with the Read tool:
```markdown
1. Check if `.claude/my-plugin.local.md` exists
2. Read the file and parse YAML frontmatter
3. Apply settings to current behavior
4. Use markdown body as additional context/prompt
```
## Common Patterns
### Pattern 1: Toggle-Based Hook Activation
Control hook activation without editing `hooks.json`:
```bash
#!/bin/bash
set -euo pipefail
STATE_FILE=".claude/security-scan.local.md"
[[ -f "$STATE_FILE" ]] || exit 0
extract_field() {
local file="$1" field="$2"
head -50 "$file" | grep -m1 "^${field}:" | sed 's/^[^:]*:[[:space:]]*//' | tr -d '\r'
}
scan_enabled=$(extract_field "$STATE_FILE" "enabled")
[[ "$scan_enabled" == "true" ]] || exit 0
# Hook logic runs only when enabled
```
### Pattern 2: Agent State Between Sessions
Store agent task state for multi-session work:
```markdown
---
agent_name: auth-implementation
task_number: 3.5
pr_number: 1234
enabled: true
---
# Current Task
Implement JWT authentication for the REST API.
Coordinate with auth-agent on shared types.
```
### Pattern 3: Configuration-Driven Validation
```markdown
---
validation_level: strict
max_file_size: 1000000
allowed_extensions: [".js", ".ts", ".tsx"]
---
```
```bash
validation_level=$(extract_field "$STATE_FILE" "validation_level")
case "$validation_level" in
strict) run_strict_checks ;;
standard) run_standard_checks ;;
*) run_standard_checks ;; # Default
esac
```
## Implementation Checklist
When adding settings to a plugin:
1. Design settings schema (fields, types, defaults)
2. Create template in plugin README
3. Add `.claude/*.local.md` to `.gitignore`
4. Implement parsing using `extract_field` pattern
5. Use quick-exit pattern (`[[ -f "$STATE_FILE" ]] || exit 0`)
6. Provide sensible defaults when file is missing
7. Document that changes require Claude Code restart (hooks only)
## Best Practices
| Practice | Details |
|----------|---------|
| Quick exit | Check file existence first, exit 0 if absent |
| Sensible defaults | Provide fallback values when settings file is missing |
| Use `extract_field` | Standard frontmatter extraction from `shell-scripting.md` |
| Validate values | Check numeric ranges, enum membership |
| File permissions | Settings files should be user-readable only (`chmod 600`) |
| Restart notice | Document that hook-related changes need a Claude Code restart |
## Agentic Optimizations
| Context | Command |
|---------|---------|
| Check settings exist | `[[ -f ".claude/plugin.local.md" ]]` |
| Extract single field | `head -50 file \| grep -m1 "^field:" \| sed 's/^[^:]*:[[:space:]]*//'` |
| Extract body | `awk '/^---$/{i++; next} i>=2' file` |
| Quick enable check | `[[ "$(extract_field file enabled)" == "true" ]]` |
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.