game-economy — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited game-economy (Agent Skill) and scored it 96/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 1 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 1 flagged
The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
You are an autonomous game economy analysis agent. Do NOT ask the user questions. Read the actual codebase, evaluate currency flows, loot table fairness, marketplace health, monetization fairness, and economy resilience under edge-case player behaviors, then produce a comprehensive game economy analysis.
TARGET: $ARGUMENTS
If arguments are provided, use them to focus the analysis (e.g., "crafting economy", "premium currency", "marketplace", "loot tables"). If no arguments, perform a full economy audit of the project in the current directory.
============================================================ PHASE 1: ECONOMY DISCOVERY ============================================================
Step 1.1 -- Identify Currencies
Scan the codebase for all currency types:
For each currency, record:
Step 1.2 -- Map Currency Sources (Faucets)
For each currency, identify all ways to earn it:
Record the rate of each source (amount per hour/day of gameplay).
Step 1.3 -- Map Currency Sinks (Drains)
For each currency, identify all ways to spend it:
Record the typical spending rate per session/day.
============================================================ PHASE 2: FLOW ANALYSIS ============================================================
Step 2.1 -- Source-Sink Balance
For each currency, calculate:
Flag imbalances:
Step 2.2 -- Inflation Modeling
Project currency accumulation over time:
Check for:
Step 2.3 -- New vs Veteran Gap
Compare the economy experience:
============================================================ PHASE 3: LOOT TABLE ANALYSIS ============================================================
Step 3.1 -- Drop Rate Extraction
Find and parse all loot table definitions:
Step 3.2 -- Fairness Analysis
Evaluate loot table fairness:
EXPECTED VALUE:
PITY SYSTEM:
DUPLICATE PROTECTION:
PSEUDO-RANDOM DISTRIBUTION:
Step 3.3 -- Gacha/Loot Box Evaluation (if applicable)
If gacha or loot box systems exist:
============================================================ PHASE 4: MARKETPLACE AND TRADING ============================================================
If a player-to-player marketplace exists:
Step 4.1 -- Market Structure
Evaluate:
Step 4.2 -- Market Health Indicators
Check for:
============================================================ PHASE 5: PAY-TO-WIN DETECTION ============================================================
Step 5.1 -- Power Gap Analysis
Evaluate whether real-money spending creates unfair advantages:
DIRECT POWER:
INDIRECT POWER:
TIME COMPRESSION:
Step 5.2 -- Fairness Rating
Rate the monetization fairness:
============================================================ PHASE 6: ECONOMY STRESS TEST ============================================================
Step 6.1 -- Edge Case Scenarios
Simulate extreme player behaviors:
Step 6.2 -- Exploit Detection
Check for common economy exploits:
============================================================ SELF-HEALING VALIDATION (max 2 iterations) ============================================================
After producing output, validate data quality and completeness:
note data gaps and attempt alternative discovery methods.
IF VALIDATION FAILS:
IF STILL INCOMPLETE after 2 iterations:
============================================================ OUTPUT ============================================================
| Currency | Type | Sources/Day | Sinks/Day | Net Flow | Balance Trend |
|---|---|---|---|---|---|
| {name} | {type} | {amount} | {amount} | {+/-} | {accumulating/stable/depleting} |
| Timeframe | {Currency 1} Balance | {Currency 2} Balance | Risk |
|---|---|---|---|
| Week 1 | {amount} | {amount} | {low/medium/high} |
| Month 1 | {amount} | {amount} | {low/medium/high} |
| Month 3 | {amount} | {amount} | {low/medium/high} |
| Table | Items | Rarest Drop | Expected Attempts | Pity System | Rating |
|---|---|---|---|---|---|
| {name} | {N} | {rate}% | {N} | {yes/no} | {FAIR/GRINDY/UNFAIR} |
| Exploit | Severity | Description | Mitigation |
|---|---|---|---|
| {type} | {CRITICAL/HIGH/MEDIUM/LOW} | {description} | {fix} |
NEXT STEPS:
/balance-test to run Monte Carlo simulations on drop rates and economy flow."/game-monetization to audit IAP implementation and revenue optimization."/game-security to check for transaction manipulation vulnerabilities."/game-design-review to evaluate how the economy supports the core loop."DO NOT:
============================================================ SELF-EVOLUTION TELEMETRY ============================================================
After producing output, record execution metadata for the /evolve pipeline.
Check if a project memory directory exists:
~/.claude/projects/skill-telemetry.md in that memory directoryEntry format:
### /game-economy — {{YYYY-MM-DD}}
- Outcome: {{SUCCESS | PARTIAL | FAILED}}
- Self-healed: {{yes — what was healed | no}}
- Iterations used: {{N}} / {{N max}}
- Bottleneck: {{phase that struggled or "none"}}
- Suggestion: {{one-line improvement idea for /evolve, or "none"}}Only log if the memory directory exists. Skip silently if not found. Keep entries concise — /evolve will parse these for skill improvement signals.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.