Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add arbazkhan971/godmode --skill scenariogit clone --depth 1 https://github.com/arbazkhan971/godmodeWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/arbazkhan971/godmode/scenario)<a href="https://agentmods.dev/skills/arbazkhan971/godmode/scenario"><img src="https://agentmods.dev/badge/skills/arbazkhan971/godmode/scenario/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/arbazkhan971/godmode/scenario"><img src="https://agentmods.dev/badge/skills/arbazkhan971/godmode/scenario.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 139 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- medium MCP Rug Pull · line 95 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00022 | $0.01329 |
| Opus 5 | $0.00011 | $0.00665 |
| Sonnet 5 | $0.00004 | $0.00266 |
| Haiku 4.5 | $0.00002 | $0.00133 |
Grade A, and why
scenario scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Activate When
/godmode:scenario, "edge cases", "failure modes"- "what could go wrong?", "break this", "stress test"
- Before shipping features with user input or APIs
- After build when no edge case coverage exists
Workflow
1. Read the Design
Read spec, plan, and code. Trace the data flow:
Input -> Validation -> Transform -> Logic -> Persist
-> Side Effects -> Response
For each stage list:
- External calls: API endpoints, DB queries, file I/O
- State mutations: created, updated, deleted
- Side effects: emails, webhooks, cache invalidation
- Trust boundaries: where untrusted data enters
Print: [scenario:read] Feature: {name} | {N} calls | {N} mutations | {N} side effects | {N} boundaries
2. Identify Feature Scope
Entry points: API routes, CLI, UI events, cron, queues
Dependencies: services, DBs, caches, third-party APIs
Data shapes: input schemas, output schemas, models
3. Explore All 12 Dimensions
For EACH dimension, generate 2-5 specific scenarios. Every scenario MUST reference a code path (file:line).
| # | Dimension | What to explore |
|---|---|---|
| 1 | Invalid Input | SQL injection, XSS, >64KB strings |
| 2 | Boundary | 0, -1, MAX_INT+1, empty, null |
| 3 | Concurrency | Race conditions, double-submit |
| 4 | Network | Timeout, partial response, DNS |
| 5 | Data Integrity | Orphans, constraint violations |
| 6 | Auth | Expired tokens, privilege escalation |
| 7 | Time | Timezone, DST, leap seconds, TTL |
| 8 | Scale | 10x load, large payloads, N+1 |
| 9 | Failure | Crash mid-write, OOM, disk full |
| 10 | Migration | Schema change, data backfill |
| 11 | User Error | Double-click, back button, paste |
| 12 | Config | Missing env var, wrong region |
IF dimension truly N/A: one-sentence justification. "N/A" alone is not acceptable.
4. Score Every Scenario
- Likelihood (L): 1-5 (impossible to inevitable)
- Impact (I): 1-5 (cosmetic to system down)
- Score = L x I
CRITICAL: Score >= 20 (e.g., L=5 x I=4)
HIGH: Score 12-19
MEDIUM: Score 6-11
LOW: Score 1-5
Minimum valid score is 1. Zero is invalid.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 6d ago First seen · 158 lines · 22 tokens per session scan A c5bd2e35858c
scenario is a skill published in the GitHub repository arbazkhan971/godmode (26 stars, last pushed 12d ago), licensed MIT. It adds 22 tokens to every session and 1,329 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
reality-verification
This skill should be used when the user asks to "verify a fix", "reproduce failure", "diagnose issue", "check BEFORE/AFTER state", "VF task", "reality check", "check test quality", "mock-only tests", or needs guidance on verifying fixes by reproducing failures before and after implementation, or detecting mock-heavy…
triage-issue
Bug triage: explores codebase for root cause, files GitHub issue with TDD fix plan. Triggers: triage, investigate bug, fix plan, root cause, file issue, bug report.
squid-triage-issue
Bug intake — localise the suspected code, capture a deterministic reproducer, and emit a groomed bug task with a regression-test acceptance criterion, ready for /squid-implement-task or the full pipeline.
diagnose
A disciplined workflow for investigating software that behaves incorrectly, crashes, produces wrong output, or fails intermittently. It first requires a repeatable command that can demonstrate the reported problem before testing possible causes.
qa-investigation
Investigate a specific test failure to its root cause and document the why. Detects whether a failing test is flaky (intermittent) or a deterministic bug during reproduction. Use when a test fails and you need the real cause, not just to make it green. Execution layer, not strategy review. Keywords: flaky test…
regression-test
Classify an iOS/Swift bug into its Apple-specific root-cause class (force unwrap, try!, fatalError, MainActor isolation, App Group mismatch, lifecycle) and sweep for sibling instances of that class. Complements a generic TDD/debugging skill (e.g. superpowers:test-driven-development, superpowers:systematic-debugging)…