Self Improving Intent Security Agent

npx skills add nishantapatil3/self-improving-intent-security-agent

mkdir -p .agent/{intents,violations,learnings,audit}

./scripts/scaffold-run.sh examples/my-demo customer_feedback medium

## [INT-YYYYMMDD-XXX] task_name

**Created**: ISO-8601 timestamp
**Risk Level**: low | medium | high
**Status**: active | completed | violated

### Goal
What you want to achieve (single clear objective)

### Constraints
- Boundary 1 (e.g., "Only modify files in ./src")
- Boundary 2 (e.g., "Do not make network calls")
- Boundary 3 (e.g., "Preserve existing test coverage")

### Expected Behavior
- Pattern 1 (e.g., "Read files before modifying")
- Pattern 2 (e.g., "Run tests after changes")
- Pattern 3 (e.g., "Create backups of modified files")

### Context
- Relevant files: path/to/file.ext
- Environment: development | staging | production
- Previous attempts: INT-20250115-001 (if retry)

---

Intent: "Process customer feedback files"
Constraints: ["Only read ./feedback", "No file modifications"]

Action: "delete ./feedback/temp.txt"
Validation:
  - Goal Alignment: ❌ Deleting isn't "processing"
  - Constraint Check: ❌ Violates "no modifications"
  - Behavior Match: ❌ Not expected for this task
  - Authorization: ✓ (but blocked by other checks)

Result: BLOCKED → Log violation → Consider rollback

## [VIO-YYYYMMDD-XXX] violation_type

**Logged**: ISO-8601 timestamp
**Severity**: low | medium | high | critical
**Intent**: INT-20250115-001
**Status**: pending_review

### What Happened
Action that was attempted

### Validation Failures
- Goal Alignment: [reason]
- Constraint Check: [which constraint violated]
- Behavior Match: [how it deviated]

### Action Taken
- [ ] Action blocked
- [ ] Checkpoint rollback
- [ ] Alert sent
- [ ] Execution halted

### Root Cause
Why the agent attempted this (if analyzable)

### Prevention
How to prevent this in the future

### Metadata
- Related Intent: INT-20250115-001
- Action Type: file_delete | api_call | command_execution
- Risk Level: high
- See Also: VIO-20250110-002 (if recurring)

---

## [ANO-YYYYMMDD-XXX] anomaly_type

**Detected**: ISO-8601 timestamp
**Severity**: low | medium | high
**Intent**: INT-20250115-001

### Anomaly Details
What unusual behavior was detected

### Evidence
- Metric that triggered alert
- Baseline vs. actual values
- Timeline of deviation

### Assessment
Why this is anomalous

### Response Taken
- [ ] Continued with monitoring
- [ ] Applied constraints
- [ ] Rolled back
- [ ] Halted execution

---

## [LRN-YYYYMMDD-XXX] category

**Logged**: ISO-8601 timestamp
**Intent**: INT-20250115-001
**Outcome**: success | failure | partial

### What Was Learned
Pattern or insight discovered

### Evidence
- Success rate: 95%
- Execution time: 2.3s
- Actions taken: 15
- Checkpoints: 3

### Strategy Impact
How this affects future executions

### Application Scope
- Tasks: file_processing, data_transformation
- Risk Levels: low, medium
- Conditions: when X and Y are true

### Safety Check
- Complexity: low | medium | high
- Performance: baseline_comparison
- Risk: assessment

### Metadata
- Category: pattern | optimization | error_handling | security
- Confidence: low | medium | high
- Sample Size: N tasks observed
- Pattern-Key: file.batch_processing (if recurring)

---

const checkpoint = await agent.checkpoint.create({
  intent: currentIntent,
  reason: "Before bulk file operations"
});

// Happens automatically, but can also trigger manually:
await agent.rollback.restore(checkpointId, {
  reason: "Detected constraint violation",
  notify: true
});

## [RBK-YYYYMMDD-XXX] checkpoint_id

**Executed**: ISO-8601 timestamp
**Intent**: INT-20250115-001
**Trigger**: automatic | manual

### Reason
Why rollback was necessary

### Actions Reversed
- Action 1 (reversed successfully)
- Action 2 (reversed successfully)
- Action 3 (reversal failed - manual intervention needed)

### Checkpoint Restored
- Checkpoint: CHK-20250115-001
- Created: 2025-01-15T10:00:00Z
- Actions since checkpoint: 15

### Status
- [ ] Fully restored
- [ ] Partially restored (see notes)
- [ ] Manual intervention required

---

## [STR-YYYYMMDD-XXX] strategy_name

**Created**: ISO-8601 timestamp
**Domain**: file_processing | api_interaction | error_handling
**Status**: testing | adopted | rejected | superseded

### Approach
What this strategy does differently

### Performance
- Baseline: 85% success, 3.2s avg
- Candidate: 92% success, 2.1s avg
- Improvement: +7% success, -34% time

### A/B Test Results
- Test Tasks: 50
- Candidate Used: 5 tasks
- Wins: 4, Losses: 1, Ties: 0

### Safety Validation
- Complexity: within limits (complexity: 45/100)
- Permissions: no expansion
- Risk: acceptable (no high-risk changes)

### Adoption Decision
- [ ] Adopt (outperforms baseline)
- [ ] Reject (underperforms baseline)
- [ ] Extend testing (inconclusive)

---

## File Modification Constraints
- Only modify files within `./src` directory
- Other directories are read-only unless explicitly authorized

## File Processing Strategy
- Use batch processing (10 files per batch)
- Create checkpoint before each batch
- Enables fast rollback on errors