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 PaulRBerg/agent-skills --skill cli-coingeckogit clone --depth 1 https://github.com/PaulRBerg/agent-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/paulrberg/agent-skills/cli-coingecko)<a href="https://agentmods.dev/skills/paulrberg/agent-skills/cli-coingecko"><img src="https://agentmods.dev/badge/skills/paulrberg/agent-skills/cli-coingecko/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/paulrberg/agent-skills/cli-coingecko"><img src="https://agentmods.dev/badge/skills/paulrberg/agent-skills/cli-coingecko.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00042 | $0.00895 |
| Opus 5 | $0.00021 | $0.00447 |
| Sonnet 5 | $0.00008 | $0.00179 |
| Haiku 4.5 | $0.00004 | $0.00089 |
Grade A, and why
cli-coingecko 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 9d 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CoinGecko CLI
This skill is coordination-exempt: skip the ai-coord gate for its declared work.
Use the installed CLI's machine-readable command catalog as the source of truth for supported market-data operations.
Workflow
-
Verify
cgexists and inspect non-interactive auth/tier state:command -v cg cg status -o json cg commands -o jsonDo not run interactive
cg author write config without the user's approval. -
On an explicitly requested CLI update, run
cg update --dry-run; runcg updateonly with approval. If automatic detection is wrong, pass--methodwithhomebrew,npm,go, orscript. Recheckcg versionandcg commands -o json, then record the verified version inreferences/version.txtwhen maintaining this skill. -
Select the command, flags, enum values, output formats, endpoint, auth requirement, and
paid_onlystatus fromcg commands -o json. Usecg <command> --helponly when the catalog lacks a needed detail. -
Resolve CoinGecko IDs with
cg search <term> -o jsonwhen the user supplied a name or ambiguous symbol. Do not silently treat symbols as unique. -
Preview unfamiliar or quota-sensitive requests with
--dry-run. Execute parseable queries with-o json; use--exportonly when the user requested a CSV artifact. -
If a historical-data request cannot be completed because
cgis unavailable,cg historyfails due to a CLI defect, or its response is demonstrably malformed, and a visual result can satisfy the request, immediately read references/open-historical-page.md and use its browser fallback. -
Present the requested result in the user's format. For ordinary human-readable output, use a compact table and preserve enough precision for the asset's magnitude.
Boundaries and Defaults
- Batch IDs in one request when the command supports it. On 429, respect the reported reset/backoff rather than retrying aggressively.
- Detect paid-only commands before execution. If the current tier cannot serve the request, say so and offer a supported route.
- Do not use the browser fallback for authentication, tier, rate-limit, invalid-input, or ambiguity errors. It does not satisfy requests for JSON, CSV, or other machine-readable evidence.
cgdoes not cover every CoinGecko endpoint. For unsupported contract-address prices, global stats, NFT detail, GeckoTerminal, or logo metadata, fetch the relevant current API documentation from https://docs.coingecko.com/llms.txt and state that the CLI route is unavailable.- Never expose API keys or send private wallet/account data to market-data endpoints.
What ships with it
4 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.
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.
- 9d ago First seen · 73 lines · 42 tokens per session scan A 6f725d9e3e20
cli-coingecko is a skill published in the GitHub repository PaulRBerg/agent-skills (70 stars, last pushed today), licensed MIT. It adds 42 tokens to every session and 895 once invoked, about $0.0002 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
mpp-agent
Pay HTTP 402 APIs via Machine Payments Protocol (MPP).
crypto-market-rank
Crypto market rankings and leaderboards. Query trending tokens, top searched tokens, Binance Alpha tokens, tokenized stocks, social hype sentiment ranks, smart money inflow token rankings, top meme token rankings from Pulse launchpad, and top trader PnL leaderboards. Use this skill when users ask about token rankings…
trading-signal
Subscribe and retrieve on-chain Smart Money signals. Monitor trading activities of smart money addresses, including buy/sell signals, trigger price, current price, max gain, and exit rate. Use this skill when users are looking for investment opportunities — smart money signals can serve as valuable references for…
cobie-cycle-filter
Use when evaluating crypto decisions through a Cobie-style cycle filter: common-sense risk, narrative traps, leverage humility, and avoiding obvious stupid trades.
token-pick
One token recommendation and one prediction market pick - scored, quantified, with a skip branch when signals are weak.
hyperliquid
Hyperliquid L1 perps DEX (69% market share).