Workflow Modes

Snipara offers two workflow modes optimized for different task complexities. Choose LITE for quick fixes, FULL for complex features.

Token Savings: LITE mode uses ~3-5K tokens. FULL mode uses ~8-15K tokens but provides session continuity and memory.

Quick Decision

Ask yourself these 4 questions:

QuestionIf Yes
Will this take multiple sessions?+1 toward FULL
Does it affect 5+ files?+1 toward FULL
Am I making architectural decisions?+1 toward FULL
Will others need to understand this later?+1 toward FULL

Score 0-1 = LITE mode | Score 2+ = FULL mode

LITE Mode (Default)

Use for bug fixes, small features, single-session work, and tasks where you know exactly which files to modify.

LITE MODE WORKFLOW
──────────────────

1. rlm_context_query("your task")     # Get relevant context
2. Read specific files                 # Direct file access
3. Make changes                        # Edit code
4. Run tests locally                   # pnpm test / pytest

Token budget: ~3-5K from Snipara

LITE Mode Example

rlm_context_query(query="fix null check authentication")
# Read the specific file
# Edit to add null check
pnpm test

FULL Mode (Complex Features)

Use for multi-day features, architectural changes, team coordination, and documentation-heavy work that spans multiple sessions.

FULL MODE WORKFLOW
──────────────────

PHASE 1: CONTEXT GATHERING
├── rlm_shared_context()              # Team standards
├── rlm_recall("feature area")        # Past decisions
└── rlm_context_query(max_tokens=8000)# Deep context

PHASE 2: PLANNING
├── rlm_plan("feature description")   # Execution plan
├── rlm_decompose("feature")          # Break into tasks
└── rlm_remember(type="decision")     # Store key choices

PHASE 3: DOCUMENTATION (if needed)
├── Create spec locally
├── rlm_upload_document()             # Store for queries
└── rlm_store_summary()               # Pre-compute

PHASE 4: IMPLEMENTATION (per sub-task)
├── rlm_inject("current context")     # Session context
├── rlm_multi_query([...])            # Batch queries
├── execute_python(code)              # Test logic
└── Edit files locally                # Actual changes

PHASE 5: PERSIST (end of session)
├── rlm_remember(type="learning")     # Store gotchas
└── rlm_remember(type="context")      # Where you left off

Token budget: ~8-15K from Snipara

FULL Mode Example

# Phase 1: Context
rlm_shared_context(categories=["BEST_PRACTICES"])
rlm_recall(query="rate limiting decisions")
rlm_context_query(query="API middleware", max_tokens=8000)
# Phase 2: Plan
rlm_plan(query="implement rate limiting for API")
rlm_remember(type="decision", content="Using Redis sliding window")
# Phase 4: Implement
rlm_inject(context="Working on rate limiting, Redis backend")
rlm_multi_query(queries=[{query: "Redis patterns"}, ...])
# Phase 5: End session
rlm_remember(type="context", content="Completed middleware, next: tests")

Mode Selection Examples

TaskModeWhy
Fix typo in READMELITESingle file, obvious change
Fix null check in auth.tsLITEKnown file, small fix
Add loading spinnerLITESingle component
Add rate limiting to APIFULLMulti-file, architectural
Refactor auth to JWTFULLBreaking change, multi-file
New billing integrationFULLNew feature, external API
Multi-tenant supportFULLArchitectural, multi-session

Session Continuity (FULL Mode)

FULL mode enables work that spans multiple sessions through the memory system.

Starting a New Session

rlm_recall(query="feature-name progress status")
rlm_context_query(query="feature-name")

Ending a Session

rlm_remember(
  type="context",
  content="Feature X: Completed steps 1-3. Next: implement Y. Blocker: Z"
)

Tools Reference

NeedToolMode
Quick answerrlm_askBoth
Deep contextrlm_context_queryBoth
Past decisionsrlm_recallFULL
Team standardsrlm_shared_contextFULL
Plan complex workrlm_planFULL
Break down taskrlm_decomposeFULL
Save decisionrlm_rememberFULL
Batch queriesrlm_multi_queryFULL
Test logicexecute_pythonFULL