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 jxoesneon/Ciel --skill modern-js-runtimesgit clone --depth 1 https://github.com/jxoesneon/CielWrote 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/jxoesneon/ciel/modern-js-runtimes)<a href="https://agentmods.dev/skills/jxoesneon/ciel/modern-js-runtimes"><img src="https://agentmods.dev/badge/skills/jxoesneon/ciel/modern-js-runtimes/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/jxoesneon/ciel/modern-js-runtimes"><img src="https://agentmods.dev/badge/skills/jxoesneon/ciel/modern-js-runtimes.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 | $0.00020 | $0.00420 |
| Opus 5.5 | $0.00008 | $0.00168 |
| Sonnet 5.5 | $0.00004 | $0.00084 |
| Haiku 4.5 | $0.00002 | $0.00042 |
Grade A, and why
modern-js-runtimes 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.
What it actually says
CIEL ADAPTATION: Modern JS Runtimes (Bun & Keccak)
This skill manages high-speed JS/TS development using Bun and enforces cryptographic correctness for specialized domains (Ethereum).
The Bun Stack
- All-in-One: Use Bun as the Runtime, Package Manager (
bun install), and Test Runner (bun test). - Natiive TS: Run
.tsfiles directly without a separate transpilation step. - Performance: Prefer Bun's native APIs (e.g.,
Bun.file(),Bun.serve()) over Node equivalents for hot paths.
Hashing Integrity (Ethereum)
- Hard Gate: For Ethereum contexts (selectors, signatures, storage slots), NEVER use Node's
crypto.createHash('sha3-256')(NIST SHA3). - Mandate: Use
keccak256fromethers,viem, orweb3. - Audit: Grep for
createHash.*sha3in Ethereum-related packages to find silent bugs.
Operational Standards
- Lockfiles: ALWAYS commit
bun.lock(text) orbun.lockb(binary) for reproducible installs. - Vercel: Explicitly set the runtime to Bun in project settings for 2x deployment speed.
Anti-Patterns
- Mixing Managers: Using
npmoryarnin a Bun-initialized project (corrupts lockfiles). - Amnesiac Hashing: Assuming "SHA3" means "Keccak" in JS (NIST SHA3 != Keccak-256).
- Silent Bun Failure: Ignoring Bun-specific dependency issues; fallback to Node if compatibility is broken.
What ships with it
1 file 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.
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 Changed · -13 lines 9b307b3e07b3
- 2mo ago First seen · 49 lines · 20 tokens per session scan A 21bdf31102bd
modern-js-runtimes is a skill published in the GitHub repository jxoesneon/Ciel (1 stars, last pushed 7d ago), licensed Apache-2.0. It adds 20 tokens to every session and 420 once invoked, about $0.0001 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.
modern-js-runtimes compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| modern-js-runtimesjxoesneon/Ciel | Skill | 1 | 7d ago | Apache-2.0 | A | 20 | Claude Code, Codex |
| nodejs-keccak256Jamkris/everything-gemini-code | Skill | 93 | 5mo ago | MIT | A | 51 | Claude Code, Codex |
| build-error-resolverKacper0199/Opencode-Ultrathinker | Skill | 2 | 5mo ago | none | C | 50 | Claude Code, Codex |
| starknet-jsstarknet-io/starknet.js | Skill | 1.3k | yesterday | MIT | A | 79 | Claude Code, Codex |
| adding-personhog-rpcPostHog/posthog | Skill | 41k | yesterday | none | A | 88 | Claude Code, Codex |
| viem-integrationUniswap/uniswap-ai | Skill | 236 | 2d ago | MIT | A | 69 | Claude Code |
| solanaquicknode/solana-finance-claude-plugin | Skill | 101 | yesterday | MIT | A | 76 | Claude Code |