AI Tool Integrations

AI Tool Integrations¶
Context works with any AI tool that can read files. This guide covers setup for popular AI coding assistants.
Claude Code (Full Integration)¶
Claude Code has the deepest integration with automatic context loading and session persistence.
Automatic Setup¶
Running ctx init automatically configures Claude Code:
This creates:
| File/Directory | Purpose |
|---|---|
.context/ |
All context files |
.claude/hooks/ |
Auto-save scripts |
.claude/settings.local.json |
Hook configuration |
CLAUDE.md |
Bootstrap instructions |
How It Works¶
graph TD
A[Session Start] --> B[Claude reads CLAUDE.md]
B --> C[PreToolUse hook runs]
C --> D[ctx agent loads context]
D --> E[Work happens]
E --> F[Session End]
F --> G[SessionEnd hook saves snapshot]
- Session start: Claude reads
CLAUDE.md, which tells it to check.context/ - During session:
PreToolUsehook runsctx agent --budget 4000before each tool use - Session end:
SessionEndhook saves context snapshot to.context/sessions/ - Next session: Claude sees previous sessions and continues with context
Generated Configuration¶
.claude/settings.local.json:
{
"hooks": {
"PreToolUse": [
{
"matcher": ".*",
"hooks": [
{
"type": "command",
"command": "ctx agent --budget 4000 2>/dev/null || true"
}
]
}
],
"SessionEnd": [
{
"hooks": [
{
"type": "command",
"command": ".claude/hooks/auto-save-session.sh"
}
]
}
]
}
}
Customizing Token Budget¶
Edit the PreToolUse command to change the token budget:
Verifying Setup¶
- Start a new Claude Code session
- Ask: "Do you remember?"
- Claude should cite specific context:
- Current tasks from
.context/TASKS.md - Recent decisions or learnings
- Previous session topics from
.context/sessions/
Troubleshooting¶
| Issue | Solution |
|---|---|
| Context not loading | Check ctx is in PATH: which ctx |
| No sessions saved | Verify .claude/settings.local.json has SessionEnd hook |
| Hook errors | Check script permissions: chmod +x .claude/hooks/*.sh |
| Missing sessions dir | Create it: mkdir -p .context/sessions |
Manual Context Load¶
If hooks aren't working, manually load context:
Slash Commands¶
ctx init installs slash commands to .claude/commands/. These are shortcuts
you can invoke in Claude Code with /command-name.
Context Commands¶
| Command | Description |
|---|---|
/ctx-status |
Show context summary (tasks, decisions, learnings) |
/ctx-agent |
Get AI-optimized context packet |
/ctx-save |
Save current session to .context/sessions/ |
/ctx-reflect |
Review session and suggest what to persist |
Adding Context¶
| Command | Description |
|---|---|
/ctx-add-task |
Add a task to TASKS.md |
/ctx-add-learning |
Add a learning to LEARNINGS.md |
/ctx-add-decision |
Add a decision with context/rationale/consequences |
/ctx-archive |
Archive completed tasks |
Session History¶
| Command | Description |
|---|---|
/ctx-recall |
Browse AI session history |
/ctx-journal-enrich |
Enrich a journal entry with frontmatter/tags |
/ctx-journal-summarize |
Generate summary of sessions over a time period |
Blogging¶
Blogging is a Better Way of Creating Release Notes
The blogging workflow can also double as generating release notes:
AI reads your git commit history and creates a "narrative", which is essentially what a release note is for.
| Command | Description |
|---|---|
/ctx-blog |
Generate blog post from recent activity |
/ctx-blog-changelog |
Generate blog post from commit range with theme |
Development¶
| Command | Description |
|---|---|
/ctx-loop |
Generate a Ralph Loop iteration script |
/ctx-prompt-audit |
Analyze session logs for vague prompts |
Usage Examples¶
/ctx-status
/ctx-add-learning "Token refresh requires explicit cache invalidation"
/ctx-journal-enrich twinkly-stirring-kettle
/ctx-journal-summarize last week
Slash commands support partial matching where applicable (e.g., session slugs).
Cursor IDE¶
Cursor can use context files through its system prompt or by reading files directly.
Setup¶
Configuration¶
Add to Cursor settings (.cursor/settings.json):
// split to multiple lines for readability
{
"ai.systemPrompt": "Read .context/TASKS.md and
.context/CONVENTIONS.md before responding.
Follow rules in .context/CONSTITUTION.md.",
}
Usage¶
- Open your project in Cursor
- Context files are available in the file tree
- Reference them in prompts: "Check .context/DECISIONS.md for our approach to..."
Manual Context Injection¶
For more control, paste context directly:
# Get AI-ready packet
ctx agent --budget 4000 | pbcopy # macOS
ctx agent --budget 4000 | xclip # Linux
Paste into Cursor's chat.
Aider¶
Aider works well with context files through its --read flag.
Setup¶
Configuration¶
Create .aider.conf.yml:
read:
- .context/CONSTITUTION.md
- .context/TASKS.md
- .context/CONVENTIONS.md
- .context/DECISIONS.md
Usage¶
# Start Aider (reads context files automatically)
aider
# Or specify files explicitly
aider --read .context/TASKS.md --read .context/CONVENTIONS.md
With Watch Mode¶
Run ctx watch alongside Aider to capture context updates:
# Terminal 1: Run Aider
aider 2>&1 | tee /tmp/aider.log
# Terminal 2: Watch for context updates
ctx watch --log /tmp/aider.log
GitHub Copilot¶
Copilot reads open files for context. Keep context files open or reference them in comments.
Setup¶
Usage Patterns¶
Pattern 1: Keep context files open
Open .context/CONVENTIONS.md in a split pane. Copilot will reference it.
Pattern 2: Reference in comments
// See .context/CONVENTIONS.md for naming patterns
// Following decision in .context/DECISIONS.md: Use PostgreSQL
function getUserById(id: string) {
// Copilot now has context
}
Pattern 3: Paste context into Copilot Chat
Paste output into Copilot Chat for context-aware responses.
Windsurf IDE¶
Windsurf supports custom instructions and file-based context.
Setup¶
Configuration¶
Add to Windsurf settings:
// Split to multiple lines for readability
{
"ai.customInstructions": "Always read .context/CONSTITUTION.md first.
Check .context/TASKS.md for current work.
Follow patterns in .context/CONVENTIONS.md."
}
Usage¶
Context files appear in the file tree. Reference them when chatting:
- "What's in our task list?" → AI reads
.context/TASKS.md - "What convention do we use for naming?" → AI reads
.context/CONVENTIONS.md
Generic Integration¶
For any AI tool that can read files, use these patterns:
Manual Context Loading¶
# Get full context
ctx load
# Get AI-optimized packet
ctx agent --budget 8000
# Get specific file
cat .context/TASKS.md
System Prompt Template¶
You are working on a project with persistent context in .context/
Before responding:
1. Read .context/CONSTITUTION.md - NEVER violate these rules
2. Check .context/TASKS.md for current work
3. Follow .context/CONVENTIONS.md patterns
4. Reference .context/DECISIONS.md for architectural choices
When you learn something new, note it for .context/LEARNINGS.md
When you make a decision, document it for .context/DECISIONS.md
Automated Updates¶
If your AI tool outputs to a log, use ctx watch:
# Watch log file for context-update commands
your-ai-tool 2>&1 | tee /tmp/ai.log &
ctx watch --log /tmp/ai.log
The AI can emit updates like:
<context-update type="learning">Important thing learned today</context-update>
<context-update type="complete">implement caching</context-update>
Context Update Commands¶
The ctx watch command parses update commands from AI output. Use this format:
Supported Types¶
| Type | Target File | Required Attributes |
|---|---|---|
task |
TASKS.md | None |
decision |
DECISIONS.md | context, rationale, consequences |
learning |
LEARNINGS.md | context, lesson, application |
convention |
CONVENTIONS.md | None |
complete |
TASKS.md | None |
Simple Format (tasks, conventions, complete)¶
<context-update type="task">Implement rate limiting</context-update>
<context-update type="convention">Use kebab-case for files</context-update>
<context-update type="complete">rate limiting</context-update>
Structured Format (learnings, decisions)¶
Learnings and decisions support structured attributes for better documentation:
Learning with full structure:
<context-update type="learning"
context="Debugging Claude Code hooks"
lesson="Hooks receive JSON via stdin, not environment variables"
application="Use jq to parse: COMMAND=$(echo $INPUT | jq -r .tool_input.command)"
>Hook Input Format</context-update>
Decision with full structure:
<context-update type="decision"
context="Need a caching layer for API responses"
rationale="Redis is fast, well-supported, and team has experience"
consequences="Must provision Redis infrastructure; team training on Redis patterns"
>Use Redis for caching</context-update>
If attributes are omitted, placeholders are inserted that should be updated manually.
Legacy Format (still supported)¶
Simple format without attributes still works but creates placeholder text:
<context-update type="learning">Mock functions must be hoisted</context-update>
<context-update type="decision">Use PostgreSQL for primary database</context-update>