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 agentmods add skills/casper-studios/casper-marketplace/code-stylenpx skills add Casper-Studios/casper-marketplace --skill code-stylegit clone --depth 1 https://github.com/Casper-Studios/casper-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/skills/casper-studios/casper-marketplace/code-style)<a href="https://agentmods.dev/skills/casper-studios/casper-marketplace/code-style"><img src="https://agentmods.dev/badge/skills/casper-studios/casper-marketplace/code-style.svg" alt="Measured on agentmods" 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 | $0.00067 | $0.00676 |
| Opus 5 | $0.00034 | $0.00338 |
| Sonnet 5 | $0.00013 | $0.00135 |
| Haiku 4.5 | $0.00007 | $0.00068 |
Grade A, and why
code-style 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 4d 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 — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Style
This skill keeps code explicit, linear, and honest about state, failure, ownership, and side effects. Its directives favor enforceable invariants, narrow boundaries, simple abstractions, and sans-I/O decision logic.
Treat each directive as a language-agnostic semantic requirement. Adapt its TypeScript example to the target language's native syntax, type system, resource-management mechanisms, and compiler checks.
References
Read as many linked references as are relevant to the current task before writing or reviewing code.
- When a condition needs mental negation to understand, express the permitted state through affirmative conditions.
- Keep the successful path readable by rejecting invalid or exceptional cases early with guard clauses.
- Make decisions visible at their point of effect; avoid implicit behavior that conceals valid values or control flow.
- Reserve conditional expressions for selecting one of two simple values, not for hidden effects.
- Make contradictory field combinations unrepresentable by enforcing invariants.
- When an internal guarantee is broken, fail impossible states instead of continuing with invented state.
- Prevent new finite-state members from silently inheriting a fallback through exhaustive decisions.
- Handle and record each failure once at its decision-owning error boundary, preserving unrelated errors and their original causes.
- Keep one-off or cosmetic indirection out of the design with simple abstractions.
- Ensure a resource never escapes uninitialized or unreleased by binding ownership to lifetime.
- When a lower layer normalizes external data, preserve caller-relevant information so continuation, retry, filtering, fallback, and other policy choices remain with the caller.
- Let consumers control continuation and stopping by exposing lazy pagination.
- Convert untrusted external payloads into trusted values at the first controlled boundary.
- Keep required absence explicit; reject fabricated defaults unless the domain defines the exact value.
- Keep consumer APIs intentional and side-effect-free with narrow public surfaces.
- Put decisions in a pure core and keep I/O in the imperative shell.
What ships with it
18 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.
- agents/openai.yaml 157 B
- LICENSE.txt 16 KB
- references/affirmative-conditions.md 720 B
- references/conditional-expressions.md 934 B
- references/enforce-invariants.md 1.2 KB
- references/exhaustive-decisions.md 863 B
- references/explicit-over-implicit.md 802 B
- references/fail-impossible-states.md 1.1 KB
- references/guard-clauses.md 943 B
- references/lazy-pagination.md 1.0 KB
- references/narrow-error-boundaries.md 2.3 KB
- references/narrow-public-surfaces.md 924 B
- references/no-fabricated-defaults.md 992 B
- references/preserve-information.md 925 B
- references/pure-core-imperative-shell.md 1.2 KB
- references/resources-own-lifetimes.md 963 B
- references/simple-abstractions.md 1.1 KB
- references/validate-at-boundaries.md 1.1 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.
- 4d ago First seen · 36 lines · 67 tokens per session scan A da4ae1748b20
code-style is a skill published in the GitHub repository Casper-Studios/casper-marketplace (12 stars, last pushed 18d ago), licensed MPL-2.0. It adds 67 tokens to every session and 676 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…