Agent skill
plugin-settings
Per-project plugin configuration via .local.md files — covers the .claude/plugin-name.local.md pattern for storing user-configurable settings with YAML frontmatter and markdown body. Use when implementing plugin settings, reading YAML frontmatter from hooks, creating configuration-driven behavior, managing agent state files, or adding per-project plugin configuration. Covers file structure, parsing techniques, common patterns (temporarily active hooks, agent state management, configuration-driven behavior), security considerations, and best practices.
Install this agent skill to your Project
npx add-skill https://github.com/Jamie-BitFlight/claude_skills/tree/main/plugins/plugin-creator/skills/plugin-settings
SKILL.md
Plugin Settings Pattern
Plugins store user-configurable settings in .claude/plugin-name.local.md files within the project directory. YAML frontmatter provides structured configuration; the markdown body carries prompts or additional context.
When to Use This Pattern
flowchart TD
Start(["Plugin needs user-configurable behavior"]) --> Q1{What kind of state?}
Q1 -->|"Per-project configuration<br>(validation level, enabled/disabled, limits)"| Settings["Use .claude/plugin-name.local.md<br>YAML frontmatter for config values"]
Q1 -->|"Agent coordination state<br>(task assignment, session tracking)"| AgentState["Use .claude/plugin-name.local.md<br>Frontmatter for metadata<br>Body for task description"]
Q1 -->|"Hook activation control<br>(enable/disable without editing hooks.json)"| HookControl["Use .claude/plugin-name.local.md<br>enabled: true/false field"]
Q1 -->|"Loop iteration state<br>(iteration counter, completion promise)"| LoopState["Use .claude/plugin-name.local.md<br>Frontmatter tracks loop state<br>Body is the prompt to loop"]
Settings --> Location
AgentState --> Location
HookControl --> Location
LoopState --> Location
Location["File location — .claude/plugin-name.local.md<br>Lifecycle — user-managed, gitignored<br>Structure — YAML frontmatter + markdown body<br>Consumers — hooks, skills, agents"]
File Structure
---
enabled: true
setting1: value1
numeric_setting: 42
list_setting: ["item1", "item2"]
---
# Additional Context
Markdown body for prompts, task descriptions,
additional instructions, or documentation.
Reading Settings
From Hooks (Bash)
The standard pattern for reading settings in hooks follows three steps — check existence, parse frontmatter, extract fields.
#!/bin/bash
set -euo pipefail
STATE_FILE=".claude/my-plugin.local.md"
# Quick exit if not configured
if [[ ! -f "$STATE_FILE" ]]; then
exit 0
fi
# Parse YAML frontmatter (between --- markers)
FRONTMATTER=$(sed -n '/^---$/,/^---$/{ /^---$/d; p; }' "$STATE_FILE")
# Extract fields
ENABLED=$(echo "$FRONTMATTER" | grep '^enabled:' | sed 's/enabled: *//' | sed 's/^"\(.*\)"$/\1/')
if [[ "$ENABLED" != "true" ]]; then
exit 0
fi
From Skills and Agents
Skills and agents read settings with the Read tool, then parse YAML frontmatter inline.
Check for plugin settings at `.claude/my-plugin.local.md`.
If present, parse YAML frontmatter and adapt behavior according to:
- enabled field controls whether the plugin is active
- mode field selects processing behavior (strict, standard, lenient)
Extracting the Markdown Body
Content after the closing --- marker is the body.
BODY=$(awk '/^---$/{i++; next} i>=2' "$FILE")
Common Implementation Patterns
Pattern 1 — Temporarily Active Hooks
Control hook activation via settings file instead of editing hooks.json (which requires restart).
STATE_FILE=".claude/security-scan.local.md"
if [[ ! -f "$STATE_FILE" ]]; then
exit 0
fi
FRONTMATTER=$(sed -n '/^---$/,/^---$/{ /^---$/d; p; }' "$STATE_FILE")
ENABLED=$(echo "$FRONTMATTER" | grep '^enabled:' | sed 's/enabled: *//')
if [[ "$ENABLED" != "true" ]]; then
exit 0
fi
# Run hook logic only when enabled
Pattern 2 — Agent State Management
Store agent-specific state and task assignments.
---
agent_name: auth-agent
task_number: 3.5
pr_number: 1234
coordinator_session: team-leader
enabled: true
dependencies: ["Task 3.4"]
---
# Task Assignment
Implement JWT authentication for the API.
Hooks read this to coordinate agents.
AGENT_NAME=$(echo "$FRONTMATTER" | grep '^agent_name:' | sed 's/agent_name: *//')
COORDINATOR=$(echo "$FRONTMATTER" | grep '^coordinator_session:' | sed 's/coordinator_session: *//')
tmux send-keys -t "$COORDINATOR" "Agent $AGENT_NAME completed task" Enter
Pattern 3 — Configuration-Driven Behavior
Settings drive validation strictness, file size limits, and allowed extensions.
LEVEL=$(echo "$FRONTMATTER" | grep '^validation_level:' | sed 's/validation_level: *//')
case "$LEVEL" in
strict) ;; # Maximum validation
standard) ;; # Balanced validation
lenient) ;; # Minimal validation
esac
Creating Settings Files
flowchart TD
Start(["Add settings to a plugin"]) --> S1["Design settings schema<br>— which fields, types, defaults"]
S1 --> S2["Create template in plugin README<br>— document the .local.md format"]
S2 --> S3["Add .gitignore entry<br>— .claude/*.local.md"]
S3 --> S4["Implement parsing in hooks/skills<br>— use quick-exit pattern"]
S4 --> S5["Provide sensible defaults<br>— when settings file is absent"]
S5 --> S6["Document restart requirement<br>— changes need session restart"]
Best Practices
File naming — use .claude/plugin-name.local.md format. The .local suffix signals user-local, gitignored files.
Gitignore — add to project .gitignore:
.claude/*.local.md
.claude/*.local.json
Defaults — provide sensible defaults when the settings file does not exist.
if [[ ! -f "$STATE_FILE" ]]; then
ENABLED=true
MODE=standard
else
# Parse from file
fi
Validation — validate field values before use.
if ! [[ "$MAX" =~ ^[0-9]+$ ]] || [[ $MAX -lt 1 ]] || [[ $MAX -gt 100 ]]; then
echo "Invalid max_value in settings (must be 1-100)" >&2
MAX=10
fi
Atomic updates — use temp file + atomic move to prevent corruption.
TEMP_FILE="${FILE}.tmp.$$"
sed "s/^field: .*/field: $NEW_VALUE/" "$FILE" > "$TEMP_FILE"
mv "$TEMP_FILE" "$FILE"
Restart requirement — settings changes require Claude Code session restart. Document this in the plugin README.
Security Considerations
Sanitize user input when writing settings files.
SAFE_VALUE=$(echo "$USER_INPUT" | sed 's/"/\\"/g')
Validate file paths stored in settings to prevent path traversal.
if [[ "$FILE_PATH" == *".."* ]]; then
echo "Invalid path in settings (path traversal)" >&2
exit 2
fi
Permissions — settings files should be readable by user only (chmod 600), not committed to git, not shared between users.
Deep Reference
For detailed parsing techniques (field extraction, body parsing, atomic updates, edge cases, yq integration), read Parsing Techniques Reference.
For production examples showing complete settings file lifecycles in real plugins, read Real-World Examples.
Related Skills
- For hook authoring patterns that consume settings files, use
/plugin-creator:hooks-guide - For component selection guidance (when to use hooks vs skills vs agents), use
/plugin-creator:component-patterns - For the legacy commands format that can create settings files, use
/plugin-creator:command-development
SOURCE: Adapted from Anthropic plugin-dev plugin skills/plugin-settings/ (8 files, ~545 lines). Accessed 2026-03-24.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
ccc
This skill should be used when code search is needed (whether explicitly requested or as part of completing a task), when indexing the codebase after changes, or when the user asks about ccc, cocoindex-code, or the codebase index. Trigger phrases include 'search the codebase', 'find code related to', 'update the index', 'ccc', 'cocoindex-code'.
agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.
delegate
Quick delegation template for sub-agent prompts. Use when assigning work to a sub-agent, before invoking the Agent tool, or when preparing prompts for specialized agents. Provides the WHERE-WHAT-WHY framework. For comprehensive delegation guidance, activate the agent-orchestration how-to-delegate skill.
swarm-spawning
Spawn agents and teammates in Claude Code swarms. Use when choosing between subagents vs teammates, selecting agent types (Explore, Plan, general-purpose, plugin agents), configuring spawn backends (in-process, tmux, iterm2), or setting environment variables for spawned agents.
knowledge-explorer
Manage the research/ knowledge base (KB) of tool and library research entries. Use when browsing KB topics, adding new research entries, updating existing entries with dated revisions, fetching GitHub repo metadata into a draft KB entry, or migrating old-format entries to skill-spec frontmatter. Triggers on tasks like "what do we have on X", "add this to the KB", "update the KB entry for Y", "fetch github info for owner/repo", or "migrate old entries".
design-anti-patterns
Enforce anti-AI UI design rules based on the Uncodixfy methodology. Use when generating HTML, CSS, React, Vue, Svelte, or any frontend UI code. Prevents "Codex UI" — the generic AI aesthetic of soft gradients, floating panels, oversized rounded corners, glassmorphism, hero sections in dashboards, and decorative copy. Applies constraints from Linear/Raycast/Stripe/GitHub design philosophy: functional, honest, human-designed interfaces. Triggers on: UI generation, dashboard building, frontend component creation, CSS styling, landing page design, or any task producing visual interface code.
Didn't find tool you were looking for?