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 pproenca/dot-skills --skill ios-chaos-monkeygit clone --depth 1 https://github.com/pproenca/dot-skillsWrote 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/pproenca/dot-skills/ios-chaos-monkey)<a href="https://agentmods.dev/skills/pproenca/dot-skills/ios-chaos-monkey"><img src="https://agentmods.dev/badge/skills/pproenca/dot-skills/ios-chaos-monkey/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/pproenca/dot-skills/ios-chaos-monkey"><img src="https://agentmods.dev/badge/skills/pproenca/dot-skills/ios-chaos-monkey.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 Privilege Escalation · line 92 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- medium Rogue Agent · line 90 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00086 | $0.02138 |
| Opus 5 | $0.00043 | $0.01069 |
| Sonnet 5 | $0.00017 | $0.00428 |
| Haiku 4.5 | $0.00009 | $0.00214 |
Grade A, and why
ios-chaos-monkey 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 5d 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
iOS Chaos Monkey — Crash-Hunter Best Practices
Adversarial crash-hunting guide for iOS and Swift applications. Contains 47 rules across 8 categories, prioritized by crash severity. Every rule follows TDD: dangerous code first, a failing test that proves the bug, then the fix that makes the test pass.
Clinic Architecture Contract (iOS 26 / Swift 6.2)
All guidance in this skill assumes the clinic modular MVVM-C architecture:
- Feature modules import
Domain+DesignSystemonly (neverData, never sibling features) - App target is the convergence point and owns
DependencyContainer, concrete coordinators, and Route Shell wiring Domainstays pure Swift and defines models plus repository,*Coordinating,ErrorRouting, andAppErrorcontractsDataowns SwiftData/network/sync/retry/background I/O and implements Domain protocols- Read/write flow defaults to stale-while-revalidate reads and optimistic queued writes
- ViewModels call repository protocols directly (no default use-case/interactor layer)
When to Apply
Reference these guidelines when:
- Hunting data races, deadlocks, and concurrency crashes in Swift
- Auditing memory management for retain cycles and use-after-free
- Reviewing async/await code for cancellation and continuation leaks
- Stress-testing file I/O and CoreData/SwiftData persistence layers
- Writing proof-of-crash tests before implementing fixes
Rule Categories by Priority
| Priority | Category | Impact | Prefix |
|---|---|---|---|
| 1 | Data Races & Thread Safety | CRITICAL | race- |
| 2 | Memory Corruption & Leaks | CRITICAL | mem- |
| 3 | Deadlocks & Thread Starvation | HIGH | dead- |
| 4 | Async/Await & Structured Concurrency | HIGH | async- |
| 5 | File I/O & Persistence Corruption | MEDIUM-HIGH | io- |
| 6 | Collection & State Mutation | MEDIUM | mut- |
| 7 | Resource Exhaustion | MEDIUM | exhaust- |
| 8 | Objective-C Interop Traps | LOW-MEDIUM | objc- |
Quick Reference
What ships with it
50 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- assets/templates/_template.md 723 B
- metadata.json 1.3 KB
- references/_sections.md 2.4 KB
- references/async-actor-hop-starvation.md 2.8 KB
- references/async-continuation-leak.md 3.4 KB
- references/async-detached-task-leak.md 2.5 KB
- references/async-missing-cancellation.md 2.4 KB
- references/async-task-group-error.md 3.3 KB
- references/async-unsafe-sendable.md 3.2 KB
- references/dead-actor-reentrancy.md 3.3 KB
- references/dead-mainactor-blocking.md 2.5 KB
- references/dead-queue-hierarchy.md 2.6 KB
- references/dead-recursive-lock.md 2.5 KB
- references/dead-semaphore-in-async.md 3.1 KB
- references/dead-sync-on-main.md 2.2 KB
- references/exhaust-file-descriptor-leak.md 4.1 KB
- references/exhaust-memory-warning-ignored.md 3.0 KB
- references/exhaust-thread-explosion.md 4.0 KB
- references/exhaust-unbounded-task-spawn.md 3.9 KB
- references/exhaust-urlsession-leak.md 3.3 KB
- references/io-concurrent-file-write.md 2.9 KB
- references/io-coredata-cross-thread.md 3.1 KB
- references/io-filemanager-race.md 3.6 KB
- references/io-keychain-thread-safety.md 4.2 KB
- references/io-plist-concurrent-mutation.md 2.5 KB
- references/io-swiftdata-background.md 3.3 KB
- references/mem-async-task-self-capture.md 3.1 KB
- references/mem-closure-retain-cycle.md 2.7 KB
- references/mem-combine-sink-retain.md 2.8 KB
- references/mem-delegate-strong-reference.md 3.1 KB
- references/mem-notification-observer-leak.md 2.7 KB
- references/mem-timer-retain-cycle.md 2.9 KB
- references/mem-unowned-crash.md 2.9 KB
- references/mut-enum-future-cases.md 3.0 KB
- references/mut-enumerate-and-mutate.md 2.9 KB
- references/mut-force-unwrap.md 2.8 KB
- references/mut-index-out-of-bounds.md 2.7 KB
- references/mut-kvo-dealloc-crash.md 3.3 KB
- references/objc-bridge-type-mismatch.md 2.9 KB
- references/objc-dynamic-dispatch.md 3.7 KB
- references/objc-nsnull-in-json.md 2.8 KB
- references/objc-unrecognized-selector.md 2.3 KB
- references/race-array-concurrent-append.md 2.0 KB
- references/race-bool-flag.md 4.0 KB
- references/race-closure-capture-mutation.md 2.4 KB
- references/race-delegate-nilification.md 3.8 KB
- references/race-dictionary-concurrent-write.md 2.1 KB
- references/race-lazy-initialization.md 2.4 KB
- references/race-property-access.md 2.8 KB
- references/race-singleton-initialization.md 2.7 KB
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.
- 5d ago First seen · 131 lines · 86 tokens per session scan A 7dc6c7b9cb5c
ios-chaos-monkey is a skill published in the GitHub repository pproenca/dot-skills (205 stars, last pushed 24d ago), licensed MIT. It adds 86 tokens to every session and 2,138 once invoked, about $0.0004 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
systematic-debugging
4-phase root cause debugging: understand bugs before fixing.
build-test
Run the project's build / typecheck / lint / test commands and emit the build.passing + tests.passing signals devloop convergence reads.
behavior-contract
Bug condition/postcondition formalization as testable Behavior Contracts. Defines invariants that must be preserved across fixes.
nw-bugfix
Bug fix workflow: root cause analysis → user review → regression test + fix via TDD.
test-first-bugs
Enforces a test-driven bug-fixing workflow. Use when a user reports a bug, failing code, an error, or asks to fix something.
refactoring-patterns
Systematic refactoring techniques, code smell elimination, pattern extraction, and legacy modernization.