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 WaniWani-AI/sdk --skill instrument-trackinggit clone --depth 1 https://github.com/WaniWani-AI/sdkWrote 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/waniwani-ai/sdk/instrument-tracking)<a href="https://agentmods.dev/skills/waniwani-ai/sdk/instrument-tracking"><img src="https://agentmods.dev/badge/skills/waniwani-ai/sdk/instrument-tracking/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/waniwani-ai/sdk/instrument-tracking"><img src="https://agentmods.dev/badge/skills/waniwani-ai/sdk/instrument-tracking.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 59 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 59 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- medium Agent Snooping · line 117 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00106 | $0.02340 |
| Opus 5 | $0.00053 | $0.01170 |
| Sonnet 5 | $0.00021 | $0.00468 |
| Haiku 4.5 | $0.00011 | $0.00234 |
Grade A, and why
instrument-tracking 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 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.
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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Instrument tracking on a createFlow app
Read the project's flows, map each node to the Waniwani event taxonomy, insert the tracking calls with metadata sourced from flow state, and verify. The output is a flow where every funnel stage emits exactly the right event, without the user writing a single track call.
Hosted reference: docs.waniwani.ai/sdk/tracking/instrumentation
The taxonomy (closed set)
Events are typed and first-class. Never invent a custom event name; model every funnel step with one of these.
| Event | Helper | When it fires | Required data |
|---|---|---|---|
tool.called |
automatic via withWaniwani(server) |
Every tool invocation | none |
lead_qualified |
waniwani?.track.leadQualified({ externalId?, email?, name? }) |
The conversation produced a concrete handoff to your business | identity only |
price_shown |
waniwani?.track.priceShown({ amount, currency, itemId?, label? }) |
You showed one price | amount, currency |
prices_compared |
waniwani?.track.pricesCompared({ options: [{ id, amount, currency }] }) |
You showed 2+ options side by side | options[] |
option_selected |
waniwani?.track.optionSelected({ id, amount, currency }) |
The user picked one option | id, amount, currency |
converted |
waniwani?.track.converted({ amount, currency, occurredAt? }) |
The user became paying | amount, currency |
| identity | waniwani?.identify(userId, properties?) |
A stable external id becomes known | userId |
page.viewed, chat.*, and widget_render are emitted automatically by the chat widget and the widget hook. Never send them from server code.
Placement rules
Work these out per flow, in order:
lead_qualifiedfires at the handoff, not at flow entry. A lead is qualified when the conversation produces a concrete handoff toward the business: the user is redirected to the pricing page or the business's own website, books a call, is sent an email, or meets an explicit qualification bar (finished the qualifying questions, requested a demo, matched the target profile). Place it where the handoff happens: the node that pushes the lead to a CRM or sends the email, or the widget callback right before the external redirect. Emit it exactly once per flow run. A user merely starting the flow is not a qualified lead;tool.calledalready covers activity. Latest definition: docs.waniwani.ai/sdk/tracking/events.lead_qualifiedmetadata comes from flow state. Fill every property you can:externalId: the strongest field. Use the record id your CRM or lead API returns (place the event after that push so the id exists).emailandname: map from the state fields that hold them, whatever they are called (email,workEmail,contactName, ...).
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 · 136 lines · 106 tokens per session scan A a8856e5daa0a
instrument-tracking is a skill published in the GitHub repository WaniWani-AI/sdk (17 stars, last pushed 3d ago), licensed MIT. It adds 106 tokens to every session and 2,340 once invoked, about $0.0005 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
codex-with-chatgpt
A connection that lets ChatGPT help plan and review coding work while Codex edits files, runs commands, tests code, and handles execution.
codexless-browser-repair
Diagnose and temporarily repair Codexless Browser compatibility after a Codex, Chrome Skill, or Browser runtime update when Codexless Browser stopped working. Use for current-version Codexless Browser compatibility drift, not ordinary website bugs, general Browser operation, Codexless install/update work, or long-term…
add-widget
Add a new widget (React UI + MCP tool) to this template. Use when asked to "add a widget", "add a new tool with UI", "create a new widget", "scaffold a widget", or "build a new MCP App feature".
create-mcp-tool
Add a plain (text-only) or UI-enhanced MCP tool to this template's server. Use when asked to "add a tool", "add an MCP tool", "create a new tool", "add a server-side tool without a widget", "add a tool with a UI", "add a tool with a widget", or "create a tool and a widget".
threebrowser-studio-mcp
Author, inspect, render, validate, animate, and save Three.js WebGPU projects in the native ThreeBrowser Studio through its real threestudio MCP tools. Use whenever Codex is asked to build or edit a ThreeBrowser Studio scene, material, Blender-style shader or texture graph, animation, lighting setup, camera, or…
install-shellby-mcp
Install and verify Shellby MCP on a Mac using terminal access only. Use when a user asks an agent to install, set up, configure, or finish a new Shellby MCP installation from this repository.