Context Compressor Skill
Core principle: Compress aggressively, decompress only when needed.
Compression Strategies
Strategy 1: Summary Mode
When: You've fully understood a file and may need to reference it later.
How:
## File Summary: src/auth/login.ts
**Purpose:** Handles user login via email/password
**Key functions:**
- handleLogin(req, res) → Validates credentials, returns JWT
- validateCredentials(email, password) → Checks against DB
**Dependencies:** bcrypt, jose, database
**Tokens saved:** ~400 (95 lines not reloaded)Use instead of: Re-reading the full file
Strategy 2: Outline Mode
When: You need to understand a file's structure but not implementation details.
How:
## Outline: src/services/payment.ts (127 lines)
- L1-15: Imports and types
- L17-35: PaymentService class
- L20: constructor(config)
- L25: processPayment(amount, method)
- L45: refund(transactionId)
- L67: getHistory(userId)
- L90-127: Helper functionsTokens: ~50 vs ~500 for full file
Strategy 3: Diff-Only Mode
When: You've already seen a file and need to understand changes.
How:
## Changes to: src/config.ts
Added:
- L45: TOKEN_BUDGET_THRESHOLD = 0.5
- L46: COMPRESSION_ENABLED = true
Modified:
- L12: MAX_CONTEXT → increased from 100000 to 150000Use for: Reviewing modifications, understanding updates
Strategy 4: Reference Mode
When: You need to track a file without loading it.
How:
## References
| File | Last Seen | Summary | Load If |
|------|-----------|---------|---------|
| auth.ts | Task 2 | Login handling | Auth bugs |
| db.ts | Task 1 | Postgres client | DB errors |
| utils.ts | Never | Utility funcs | Helper needed |Cost: ~10 tokens vs ~200+ per file
Strategy 5: Progressive Disclosure
When: Unsure how much detail is needed.
Process:
- Start with outline (Level 1)
- If insufficient, load key functions (Level 2)
- If still stuck, load related code (Level 3)
- Full file only as last resort (Level 4)
L1: Outline → "I see handleLogin at L25"
L2: Function → "handleLogin validates then calls createToken"
L3: Related → "createToken uses jose.sign with HS256"
L4: Full → Only for complex debuggingCompression Triggers
Automatic Compression Points
| Trigger | Action |
|---|---|
| After understanding a file | Create summary |
| Switching tasks | Compress previous context |
| Budget at 50% | Aggressive outline mode |
| Budget at 70% | Summary-only mode |
| End of wave | Full compression pass |
Decompression Protocol
When you need details from compressed context:
- Check summary first — Often sufficient
- Load specific section — If summary incomplete
- Full load as last resort — And re-compress after
## Decompression Log
| File | Reason | Level | Tokens |
|------|--------|-------|--------|
| auth.ts | Debug login | L2 (func) | +150 |
| db.ts | Check query | L3 (snippet) | +50 |Compression Format Templates
Summary Template
## 📦 [filename]
**Purpose:** [one line]
**Key exports:** [list]
**Dependencies:** [list]
**Patterns:** [notable patterns used]
**Watch for:** [gotchas or edge cases]Outline Template
## 📋 [filename] (N lines)
- L[start]-[end]: [section name]
- L[n]: [key item]
- L[n]: [key item]Diff Template
## Δ [filename]
**+** [additions]
**-** [removals]
**~** [modifications]Integration
Works with:
token-budget— Triggers compression at thresholdscontext-fetch— Provides input for compressioncontext-health-monitor— Monitors compression effectiveness
Anti-Patterns
❌ Keeping full files in mental context — Compress after understanding ❌ Re-reading instead of referencing — Use summaries ❌ Loading full file for one function — Use outline + target ❌ Skipping compression "to save time" — Costs more later
*Part of GSD v1.6 Token Optimization. See docs/token-optimization-guide.md for examples.*