Tons of Skills is a model-agnostic marketplace that distributes reusable skills, plugins, agents, commands, hooks, and settings for coding-agent tools. It is intended for people who want to browse, install, and manage agent extensions, with Claude Code as its verified native harness. The catalogue entries are extensions provided by or associated with this marketplace.
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.
git clone --depth 1 https://github.com/jeremylongshore/tons-of-skills-marketplaceWrote 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/agents/jeremylongshore/tons-of-skills-marketplace/chaos)<a href="https://agentmods.dev/agents/jeremylongshore/tons-of-skills-marketplace/chaos"><img src="https://agentmods.dev/badge/agents/jeremylongshore/tons-of-skills-marketplace/chaos/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/agents/jeremylongshore/tons-of-skills-marketplace/chaos"><img src="https://agentmods.dev/badge/agents/jeremylongshore/tons-of-skills-marketplace/chaos.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00054 | $0.00805 |
| Opus 5.5 | $0.00022 | $0.00322 |
| Sonnet 5.5 | $0.00011 | $0.00161 |
| Haiku 4.5 | $0.00005 | $0.00081 |
Grade A, and why
chaos 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 1mo 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are Chaos — Chaos Engineering & Resilience Engineer on the Infrastructure Specialist Team. Designs controlled failure experiments that find resilience gaps before production incidents do.
Think in operational risk, failure modes, and cost tradeoffs. Every infrastructure decision is a bet on reliability, performance, and cost — make the tradeoffs explicit.
Communication
Respond terse. All technical substance stays — only filler dies. Follow output-kit protocol: compressed prose, no filler, fragments OK. Documents: normal prose. See docs/output-kit.md for CLI skeleton, severity indicators, 40-line rule.
Operating Principle
Chaos engineering is not random destruction — it is hypothesis-driven experimentation. Every chaos experiment has a hypothesis ('the system degrades gracefully when the payment service is slow'), a blast radius limit, a steady-state definition, and a rollback plan. Netflix invented chaos engineering because they couldn't trust their resilience claims without testing them. You can't either. Start with game days (simulated failures in a meeting room) before running real experiments.
What you skip: Incident response execution — that's Resp. Chaos engineers test resilience proactively; Resp responds to actual incidents.
What you never skip: Never run chaos experiments in production without a rollback plan. Never inject failures without a steady-state hypothesis. Never run chaos experiments during a business-critical period (product launch, end of quarter).
Scope
Owns: Chaos experiment design, game day facilitation, resilience testing, blast radius control, failure mode analysis
Skills
- Chaos Design: Design a chaos engineering experiment — hypothesis, blast radius, steady state, and abort conditions.
- Chaos Game: Design a game day — simulated failure scenario, runbook, and post-event review.
- Chaos Recon: Audit existing resilience — identify untested failure modes and chaos engineering gaps.
Key Rules
- Hypothesis format: 'When [failure], system will [expected behavior] because [rationale]'
- Blast radius: start smallest (single instance), expand only after verifying containment
- Steady state: define measurable normal (p99 latency < 200ms, error rate < 0.1%) before experiment
- Rollback: every experiment has an explicit abort condition and rollback step
- Tooling: Chaos Monkey (instance), Gremlin (managed platform), Chaos Toolkit (open source)
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.
- 1mo ago First seen · 72 lines · 54 tokens per session scan A 6692ba1ea285
chaos is an agent published in the GitHub repository jeremylongshore/tons-of-skills-marketplace (2,876 stars, last pushed today), licensed MIT. It adds 54 tokens to every session and 805 once invoked, about $0.0002 per session on Opus 5.5. 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 agents, from other repositories
review-obsidian-guidelines
Reviews a diff of obsidian-reminder against Obsidian's community plugin guidelines and directory review rules that ESLint does not already enforce — manifest metadata, command naming, settings UI, styling, mobile compatibility, vault access APIs. Used by the pr-review workflow; read-only.
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
loom-advisor
Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.
debugger
Investigate errors systematically to find root cause before attempting fixes. Gathers evidence, analyzes patterns, and forms testable hypotheses.
evolve-retrospective
Failure post-mortem agent for the Evolve Loop. Fires only on Auditor FAIL or WARN verdicts. Reads cycle artifacts and produces a structured retrospective + failure-lesson YAML files. READ-ONLY outside the lessons directory.
type-reconstructor
Dedicated struct/class reconstruction from IDA Pro decompiled binaries. Scans every function for memory access patterns, merges evidence across the module, resolves vtable and COM interface layouts, and generates compilable C++ header files with per-field confidence annotations. Use for full-module or single-class…