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/open-curiosity/gini-agent/yc-clinpx skills add Open-Curiosity/gini-agent --skill yc-cligit clone --depth 1 https://github.com/Open-Curiosity/gini-agentWrote 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/open-curiosity/gini-agent/yc-cli)<a href="https://agentmods.dev/skills/open-curiosity/gini-agent/yc-cli"><img src="https://agentmods.dev/badge/skills/open-curiosity/gini-agent/yc-cli.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 | $0.00069 | $0.02679 |
| Opus 5 | $0.00034 | $0.01340 |
| Sonnet 5 | $0.00014 | $0.00536 |
| Haiku 4.5 | $0.00007 | $0.00268 |
Grade C, and why
yc-cli scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -fsSL https://bookface.ycombinator.com/cli/install.sh | bash Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL https://bookface.ycombinator.com/cli/install.sh | bash How it starts
The opening of the file, as written. The whole thing — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.
YC CLI (yc) — demo operator's guide
yc is the Y Combinator CLI; it talks to Bookface over an authenticated
API. In our demo it's the investor-research source behind Step 5: pulling a
fund's track record (check size, YC conversion, recent deals) from the terminal.
This guide covers only the parts the demo touches.
0. Install + PATH (do this first)
Before using yc, check whether it's installed and decide whether to install
it — you (the agent) own this judgment; don't blindly run an install.
-
Check if it's available. Put the usual install locations on PATH first, since the binary often isn't there in a non-interactive shell, then look:
export PATH="$HOME/.yc/bin:$HOME/.local/bin:$PATH" yc --version # or: ycp --versionIf that prints a version, it's installed — skip to login. If it errors with "command not found", continue.
-
Confirm it's genuinely missing, not just off PATH. A bare
yccan fail just because PATH wasn't set. Before installing, verify the binary truly isn't on disk (e.g. check~/.yc/bin/ycand~/.local/bin/yc). Only if it's actually absent do you install. -
Install only when missing:
curl -fsSL https://bookface.ycombinator.com/cli/install.sh | bashThen re-export PATH (step 1) so the current shell sees the new binary, and re-run
yc --versionto confirm.
Notes:
- If an existing
yccommand was detected at install time, the CLI may be installed asycpinstead — tryycpifycis absent. - Non-interactive SSH shells don't source
~/.zshrc, so set theexport PATH=...line at the top of any script before callingyc.
1. The optimal login flow (VALIDATED — use this)
We are NOT logged in yet. This is the flow we rehearsed to convergence — it's
the demo's Step 5 trust beat: the agent forwards its browser to the user, the
user signs in on their own device, the agent never sees the password. yc login
spins a local callback listener on localhost:19876; the agent's forwarded
browser can't reach that localhost, so we keep yc login alive in tmux and
let the CLI catch the callback directly while the user signs in.
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 · 232 lines · 69 tokens per session scan C 5d3622930611
yc-cli is a skill published in the GitHub repository Open-Curiosity/gini-agent (1,869 stars, last pushed 1mo ago), licensed MIT. It adds 69 tokens to every session and 2,679 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
gno
Search local documents, files, notes, and knowledge bases. Index directories, search with BM25/vector/hybrid, get AI answers with citations. Use when user wants to search files, find documents, query notes, look up information in local folders, index a directory, set up document search, build a knowledge base, needs…
vibelution-continuous-optimization-loop
Runs one evidence-driven Vibelution optimization iteration from the ROI backlog: pick one todo item, worktree isolate, implement, machine-verify, merge, update STATE. Use when the user starts /loop for project improvement, continuous optimization, or agent-dev ROI backlog work.
personal-assistant
Use this skill whenever the user acts like Bamboo is their personal assistant. Triggers include stating commitments, deadlines, appointments, or recurring routines ("remind me to...", "I need to... by Friday", "every Monday I..."), asking to be reminded of something, agenda questions ("what's on my plate", "what's due…
review
Review code changes, pull requests, patches, or a scoped code area for actionable correctness, security, compatibility, and test risks with file and line evidence. Use for review or audit requests; do not use for general proofreading, feature implementation, or debugging a reported failure when the user wants a fix.
debug
Diagnose a concrete failure, regression, crash, hang, flaky test, or incorrect runtime behavior by reproducing it, testing hypotheses, and identifying the evidence-backed root cause. Use when symptoms or failing output exist; do not use for feature implementation without a failure, general code review, or a conceptual…
plan
Build an executable implementation, migration, or rollout plan from read-only repository exploration, including constraints, dependencies, ordered changes, verification, risks, and rollback points. Use when the user asks for a plan or decomposition before implementation; do not use when they want a small change…