Skip to content
FSS Knowledge Base

Claude Code

Section titled “Claude Code”

Primary AI development tool. Power user workflow: task-driven delegation with structured plans and verification.

Quick Reference

Section titled “Quick Reference”
ActionCommand/Shortcut
Initialize project memory/init
Clear context/clear
Compact conversation/compact
Enter Plan ModeShift+Tab twice
Switch modelAlt+P (Windows)
Add memory on the flyType # then instruction
Check usage/usage
Check status line/statusline
Run insights/insights
Name session/session name
Resume session/session resume name

Key Workflows

Section titled “Key Workflows”
  • Plan Mode First: always separate planning from coding for non-trivial work
  • Checkpoints + /rewind: fearless experimentation with quick rollbacks
  • Context Hygiene: /clear and /compact to maintain clarity
  • Named Sessions: /session name for easy resume
  • Human-Guided Git: manual control over history, let Claude focus on edits
  • Short Sessions: ~40 messages or one feature per session as soft limit

Setup

Section titled “Setup”

Installation

Section titled “Installation”

Max Reasoning Config

Section titled “Max Reasoning Config”

In ~/.claude/settings.json:

{
  "env": {
    "CLAUDE_CODE_MAX_OUTPUT_TOKENS": "64000",
    "MAX_THINKING_TOKENS": "31999"
  }
}

Config References

Section titled “Config References”
  • Global CLAUDE.md: ~/.claude/CLAUDE.md
  • Monorepo CLAUDE.md: d:\FSS\Websites\monorepo\CLAUDE.md
  • Setup docs: d:\FSS\Websites\monorepo\docs\CLAUDE_CODE_SETUP.md
  • MCP config: d:\FSS\Websites\monorepo\docs\MCP_CONFIGURATION.md

Memory System

Section titled “Memory System”

Four Scopes (highest to lowest priority)

Section titled “Four Scopes (highest to lowest priority)”
  1. Enterprise: C:\Program Files\ClaudeCode\CLAUDE.md — org-wide policy
  2. Project: ./CLAUDE.md or ./.claude/CLAUDE.md — team-shared
  3. Project rules: ./.claude/rules/*.md — modular, topic-specific
  4. User: ~/.claude/CLAUDE.md — personal preferences across all projects
  5. Project local: ./CLAUDE.local.md — personal project-specific (auto-gitignored)

Auto Memory

Section titled “Auto Memory”
  • CC maintains MEMORY.md per project: \\wsl$\Ubuntu-24.04\home\ta\.claude\projects\...\memory\MEMORY.md
  • Automatically read at start of every conversation

CLAUDE.md Best Practices

Section titled “CLAUDE.md Best Practices”
  • Keep under 100 lines (context efficiency)
  • Use as roadmap to docs, not the docs itself — use @path/to/file imports
  • Always use absolute paths in references
  • Add subdirectory CLAUDE.md for module-specific rules
  • Include: verification requirements, planning instructions, deployment architecture
  • Schedule monthly audits: delete stale, add missing
  • Hot reload only works for skills; CLAUDE.md changes require session restart

Import Syntax

Section titled “Import Syntax”
See @README for project overview and @package.json for npm commands.
@docs/git-instructions.md
@~/.claude/my-project-instructions.md

Advanced Strategies

Section titled “Advanced Strategies”

Thinking Levels

Section titled “Thinking Levels”
LevelUse For
thinkQuick fixes, moderate complexity
think hardDesign decisions, optimization
think harderArchitectural decisions
ultrathinkDebugging hell, race conditions

Model Selection

Section titled “Model Selection”
  • Haiku 4.5: sprinter — simple tasks, implementation (much cheaper)
  • Sonnet 4.5: steady builder — standard development
  • Opus 4.5: careful reviewer — complex refactors, architecture

Subagents

Section titled “Subagents”
  • Parallelize development: spawn specialized agents for backend, frontend, tests
  • Each works in isolated context window
  • Parent agent coordinates and runs integration tests

Hooks

Section titled “Hooks”

Shell commands that auto-run at lifecycle events:

  • PreToolUse: auto-format before tool runs
  • PostToolUse: trigger tests after code changes
  • Stop: finalize tasks, send notifications
  • Exit code 2: block Claude from editing protected files
  • Scoping hierarchy: global -> project -> skill -> sub-agent
  • Async hooks: run in background, ~3x faster workflows

Skills and Commands (Merged)

Section titled “Skills and Commands (Merged)”
  • Simple commands: single .md in .claude/commands/
  • Complex skills: directory in .claude/skills/skill-name/ with SKILL.md, scripts, templates
  • Skills auto-reload on SKILL.md changes
  • Invoke with /skill-name
  • See 02_Skills for full skills ecosystem

Plugins

Section titled “Plugins”
  • Combine /commands with MCP servers
  • Marketplace available for community plugins
  • CCPlugins: 24 predefined commands extending CC CLI

CC /insights Report Summary (2026-02-05)

Section titled “CC /insights Report Summary (2026-02-05)”

3,336 messages across 439 sessions over 31 days

What’s Working

Section titled “What’s Working”
  • Task-driven workflow with structured backlists
  • Confirm-then-implement planning discipline
  • Multi-language infrastructure orchestration (Python, TS, YAML, JSON)
  • 276 commits (9/day shipping cadence)

Key Friction Points

Section titled “Key Friction Points”
  1. Claude claims “done” without verifying — deployment bugs missed
  2. Wrong approach on config/deployment — lacks persistent context
  3. No CLAUDE.md guardrails — no rules about deployment architecture, testing

Priority Actions from Insights

Section titled “Priority Actions from Insights”
  1. Add verification rules to CLAUDE.md: “Never claim done without testing”
  2. Set up hooks for post-edit deployment validation
  3. Create /taskfix skill encoding the full fix-verify workflow
  4. Use headless mode for automated task-list fixes
  5. Implement verify-before-done protocol
  6. Per-item verification (fix -> test -> next) instead of batch

Suggested CLAUDE.md Additions

Section titled “Suggested CLAUDE.md Additions”
## Workflow Rules
- After implementing changes, verify by running deployment/build scripts and checking output. Never claim "done" without testing.
- When working from task list, do final grep pass for remaining old/replaced values.


## Deployment and Config
- For config changes (YAML, JSON, shell), diff final file contents after editing. Check for: domain names, provider names, URLs, environment-specific values.

Resources

Section titled “Resources”