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 freibergergarcia/phone-a-friend --skill curiosity-enginegit clone --depth 1 https://github.com/freibergergarcia/phone-a-friendWrote 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/freibergergarcia/phone-a-friend/curiosity-engine)<a href="https://agentmods.dev/skills/freibergergarcia/phone-a-friend/curiosity-engine"><img src="https://agentmods.dev/badge/skills/freibergergarcia/phone-a-friend/curiosity-engine/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/freibergergarcia/phone-a-friend/curiosity-engine"><img src="https://agentmods.dev/badge/skills/freibergergarcia/phone-a-friend/curiosity-engine.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 | $0.00041 | $0.04325 |
| Opus 5 | $0.00020 | $0.02162 |
| Sonnet 5 | $0.00008 | $0.00865 |
| Haiku 4.5 | $0.00004 | $0.00432 |
Grade B, and why
curiosity-engine scanned grade B with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
| **Ollama** | `PROMPT_JSON="$(jq -Rs . < "$PROMPT_FILE")"; curl -s http://localhost:11434/api/chat -H "Content-Type: application/json" -d "{\"model\":\"<model>\",\"messages\":[{\"role\":\"user\",\"content\":${PROMPT_JSO Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
| **Ollama** | `PROMPT_JSON="$(jq -Rs . < "$PROMPT_FILE")"; curl -s http://localhost:11434/api/chat -H "Content-Type: application/json" -d "{\"model\":\"<model>\",\"messages\":[{\"role\":\"user\",\"content\":${PROMPT_JSO How it starts
The opening of the file, as written. The whole thing — 417 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/curiosity-engine
A structured ping-pong Q&A game between the host orchestrating model (the agent running this skill — Claude in Claude Code, the OpenCode model in OpenCode) and a backend model. Both sides MUST produce an ANSWER: and a QUESTION: every round. The game is seeded with a topic and runs for N rounds (default 3, max 6).
Execution rules
- The host model running this skill is the orchestrator. It serves the
opening question and answers each round directly. Do NOT call
phone-a-friend --to claude(or any other backend) to generate the orchestrator's questions or answers — that would relay the orchestrator role to a different model. - One backend per relay call. Never pass comma-separated values to
--to(e.g.phone-a-friend --to codex,gemini). curiosity-engineis a host slash command / Agent Skill, not a PaF CLI subcommand. Never runphone-a-friend curiosity-engine.--backendis an argument to this skill, not a PaF CLI flag. Do not pass--backendtophone-a-friend.- Inside OpenCode, prefix relay invocations with
PHONE_A_FRIEND_HOST=opencodeso PaF detects the host deterministically. - Inside Codex, prefix relay invocations with
PHONE_A_FRIEND_HOST=codexfor the same reason. Do not selectcodexas the friend backend from Codex; chooseantigravity,gemini, orollamainstead. PaF will refuse recursive Codex calls. - Suppress the working-tree diff on every binary-mode relay (see "Diff suppression" below). Curiosity rounds are seeded with self-contained prompts; the diff would be noise.
- Do NOT dump repo files or git output (
git show,git diff,git status, etc.) into the relay prompt. Curiosity rounds are seeded with self-contained prompts; if the round needs file context, repo-aware backends (antigravity, codex, gemini) can read the repo via--repo "$PWD". Forollama(no repo file access), pick a repo-aware backend instead, or ask before sending a minimal excerpt. Inlining repo content can leak uncommitted edits or committed secrets and is not needed for a Q&A rally. The opening question and round transcripts are narrative context that the orchestrator generates and inlines into the relay prompt; that is the intended use, not file dumping.
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.
- 11d ago First seen · 417 lines · 41 tokens per session scan B 9dbc5d4a6d91
curiosity-engine is a skill published in the GitHub repository freibergergarcia/phone-a-friend (10 stars, last pushed 2d ago), licensed Apache-2.0. It adds 41 tokens to every session and 4,325 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 2 findings (sends data to an external url, 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
roundtable
Convene a "round table" of multiple frontier AI models — Grok, Codex/OpenAI, GLM, MiniMax, Claude, and Gemini — to get independent perspectives on a question, optionally deliberating across rounds until a Claude chair declares consensus, then synthesize a single recommendation. Use when the user says "round table"…
gwm
Manage git worktrees across any repository with the gwm Rust binary (CLI + ratatui TUI). Use when the user asks to create / list / remove / bootstrap / switch / link worktrees, run a command across worktrees (gwm exec) or reclaim build artifacts (gwm clean), materialise a PR into a worktree (gwm review), drive a…
save-learning
Saves user instructions as persistent learnings for future sessions. Use when the user says 'remember this', 'always do X', 'from now on', 'never do Y', or gives any instruction they want persisted across sessions. Proactively suggest when the user states a preference, convention, or rule they clearly want followed in…
web-access
A method for handling difficult web tasks across search, page fetching, and a real browser. It covers sites that need login sessions, dynamic pages, anti-bot handling, or exploration before their structure is understood.
skill-creator
A skill for creating or improving reusable instructions for an agent. It covers capturing the intended workflow, writing a draft, testing it, and refining its trigger description.
packing-list
A travel-packing aid that builds a checklist from the destination's climate, trip type, length, transport, accommodation, and travelling group. It treats a city break, hike, business trip, and family holiday as different packing problems.