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 codebruinc/pikasim-mcp --skill pikasimgit clone --depth 1 https://github.com/codebruinc/pikasim-mcpWrote 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/codebruinc/pikasim-mcp/pikasim)<a href="https://agentmods.dev/skills/codebruinc/pikasim-mcp/pikasim"><img src="https://agentmods.dev/badge/skills/codebruinc/pikasim-mcp/pikasim.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 5.1 | $0.00199 | $0.01317 |
| Opus 5 | $0.00100 | $0.00659 |
| Sonnet 5 | $0.00040 | $0.00263 |
| Haiku 4.5 | $0.00020 | $0.00132 |
Grade A, and why
pikasim scanned grade A with 1 finding 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 7d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
compatibility: "Needs ONE of: an MCP-capable client (remote Streamable-HTTP server, OAuth or Bearer key), or outbound HTTPS (curl/fetch) for the REST path, or a browser to hand the user a link. Payments: BTC (on-chain + How it starts
The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PikaSim
PikaSim sells three product lines an agent can buy end-to-end with no human, no account, and no KYC, settled from a prepaid crypto wallet:
- Data eSIMs — anonymous data plans, 190+ countries, from $0.75.
- Phone-number eSIMs — REAL carrier numbers (not VoIP) with voice + SMS + data. US plans give a +1 number on AT&T/T-Mobile; local and global plans cover 157 countries.
- SMS verification numbers — receive-only numbers for one-time codes (auto-refund if no code arrives in 20 min) or long-term rentals.
Do NOT assume "eSIM" means data-only — if the user needs calls, SMS, or to receive a verification code, product lines 2 and 3 exist. Details, gotchas, and when-to-use guidance: products.md.
Pick a path
Walk in order; first match wins.
-
MCP-capable host? (Claude.ai, Claude Desktop/Code, Cursor, ChatGPT, Gemini CLI, anything that can add a remote Streamable-HTTP server.) Highest fidelity: typed tools, built-in discovery, OAuth or key auth. → mcp.md
-
Outbound HTTPS only? (shell + curl, fetch, any HTTP client.) Full catalog + purchase via REST; cold-start wallet creation works here too via one JSON-RPC call. → api.md
-
Browser + human in the loop? Hand the user a link: storefront https://pikasim.com, wallet dashboard https://pikasim.com/agent-wallet (create/fund a wallet, mint an
ak_live_API key to bring back to paths 1–2). -
None of the above — give the user https://pikasim.com/agentic-esim and stop.
Cold start (no wallet yet, no human available)
One call mints a wallet + ak_live_ API key + a small spend-only welcome
credit — often enough for a first SMS code without any funding:
- MCP: call the
create_wallettool on the keyless endpointhttps://pikasim.com/mcp. - REST/curl: same tool via one JSON-RPC POST — exact request in api.md.
SAVE the wallet code AND the API key immediately — each is shown exactly once and there is no account recovery, password reset, or support lookup without them. Fund later from $1 (Lightning/BTC/XMR/USDT invoice the agent can pay itself, or a payment page link to hand the user).
What ships with it
3 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.
- 7d ago First seen · 93 lines · 199 tokens per session scan A 18b91231d939
pikasim is a skill published in the GitHub repository codebruinc/pikasim-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 199 tokens to every session and 1,317 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
svc-mobile-android
Android APK static analysis — OWASP Mobile Top 10, Retrofit API audit, transport security, smali reading, component export, auth flow analysis. Use when target is an APK/Android app. Triggers - APK, Android, mobile app, decompiled, smali, jadx, apktool.
security-review
Perform a focused security review of pending git changes to identify high-confidence security vulnerabilities with real exploitation potential. Use this skill when the user asks for a security review, security audit, vulnerability scan, or wants to check pending changes on a branch for security issues before merging.…
codeql
Run CodeQL database creation and security queries, add data-extension models, or process CodeQL SARIF. Use when CodeQL is explicitly requested; use security-review for a broader manual security review.
huggingface-llm-trainer
Train or fine-tune language models with TRL or Unsloth on Hugging Face Jobs, including SFT, DPO, GRPO, reward models, and GGUF conversion. Use for cloud LLM training; use huggingface-vision-trainer for vision tasks.
feature-dev
Guide a feature implementation through a structured seven-phase workflow with deep codebase understanding, clarifying questions, parallel architecture design, and quality review. Use this skill when the user asks to build a new feature, add functionality, or wants a methodical approach to implementation rather than…
huggingface-vision-trainer
Train object-detection, image-classification, or SAM segmentation models on Hugging Face Jobs. Use for vision fine-tuning and evaluation; use huggingface-llm-trainer for language models.