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 audit-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/audit-tracking)<a href="https://agentmods.dev/skills/waniwani-ai/sdk/audit-tracking"><img src="https://agentmods.dev/badge/skills/waniwani-ai/sdk/audit-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/audit-tracking"><img src="https://agentmods.dev/badge/skills/waniwani-ai/sdk/audit-tracking.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
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 →
- medium Agent Snooping · line 152 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 | $0.00118 | $0.02772 |
| Opus 5 | $0.00059 | $0.01386 |
| Sonnet 5 | $0.00024 | $0.00554 |
| Haiku 4.5 | $0.00012 | $0.00277 |
Grade A, and why
audit-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 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 — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audit tracking on a Waniwani MCP app
Read the whole project, inventory every tracking call on every surface, verify each event against the defined taxonomy, map the funnel, and report the gaps. The output is a report, not code changes: what is wrong, what is missing, and exactly where each missing event belongs. To apply fixes afterwards, use the instrument-tracking skill.
Source of truth: fetch the live docs first
Event definitions evolve. Before auditing, fetch these pages and treat them as the latest definitions; where they disagree with this file, the docs win:
- docs.waniwani.ai/sdk/tracking/events: the full event catalog and the definition of a qualified lead
- docs.waniwani.ai/sdk/tracking/instrumentation: placement rules per funnel stage
- docs.waniwani.ai/sdk/tracking/identify: identify semantics
- docs.waniwani.ai/sdk/reference/event-schema: typed property shapes
Also read the taxonomy the installed SDK version actually accepts, since that is what typechecks in the project:
bun -e "import { EVENT_TYPES } from '@waniwani/sdk'; console.log(EVENT_TYPES)"
If the installed list differs from the docs (older SDK), audit against the docs and flag the version gap as a finding: the project should upgrade (see the changelog at docs.waniwani.ai/sdk/changelog).
The taxonomy (closed set)
Snapshot for orientation; the docs pages above are authoritative.
| Event | Sent by | When |
|---|---|---|
page.viewed |
chat widget, automatic | Visitor lands on a page with the widget |
session.started |
Waniwani backend, automatic | First time a session id is seen |
tool.called |
withWaniwani(server), automatic |
Every tool invocation |
widget_render |
useWaniwani(), automatic |
A widget initialized |
user.identified |
identify(userId, properties?) |
A stable identity became known |
lead_qualified |
track.leadQualified({ externalId?, email?, name? }) |
The handoff happened (definition below) |
price_shown |
track.priceShown({ amount, currency }) |
One price shown |
prices_compared |
track.pricesCompared({ options }) |
2+ options shown side by side |
option_selected |
track.optionSelected({ id, amount, currency }) |
The user picked one option |
converted |
track.converted({ amount, currency, occurredAt? }) |
The user became paying |
link.clicked |
generic track({ event: "link.clicked" }) |
An outbound link was followed |
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 · 160 lines · 118 tokens per session scan A a5700430818b
audit-tracking is a skill published in the GitHub repository WaniWani-AI/sdk (17 stars, last pushed 2d ago), licensed MIT. It adds 118 tokens to every session and 2,772 once invoked, about $0.0006 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
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…
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.
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.