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 ai-analyst-lab/ai-analyst-plugin --skill drop-off-formatgit clone --depth 1 https://github.com/ai-analyst-lab/ai-analyst-pluginWrote 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/ai-analyst-lab/ai-analyst-plugin/drop-off-format)<a href="https://agentmods.dev/skills/ai-analyst-lab/ai-analyst-plugin/drop-off-format"><img src="https://agentmods.dev/badge/skills/ai-analyst-lab/ai-analyst-plugin/drop-off-format.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 | $0.00077 | $0.00923 |
| Opus 5 | $0.00039 | $0.00462 |
| Sonnet 5 | $0.00015 | $0.00185 |
| Haiku 4.5 | $0.00008 | $0.00092 |
Grade A, and why
drop-off-format 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 6d 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: Drop-Off Format
Purpose
A percentage without a count hides scale. A count without a percentage hides severity. "We lost 12,000 users" sounds bad until you learn that's 3% of the base. "34% drop-off" sounds bad until you learn that's 850 users out of 2,500. This skill enforces one rule: every drop-off shows three numbers.
When to Use
Before presenting ANY step-to-step drop-off — in a funnel table, in narrative text, in a chart annotation, in a Slack message, or on a slide. This runs on every output that contains funnel or conversion-step data.
The Rule
Every drop-off must show: entering count, exiting count, and drop-off percentage.
All three, every time. The format:
checkout_started (43,490) -> payment_attempted (35,543): 18.3% drop-off
In a table, this becomes three columns:
| Step | Users | Drop-off |
|---|---|---|
| checkout_started | 43,490 | -- |
| payment_attempted | 35,543 | 18.3% (7,947 lost) |
Either format is acceptable. What is not acceptable is showing only one or two of the three numbers.
Instructions
Step 1: Find every drop-off in your draft output
Scan the response you are about to send. Every place where two adjacent funnel steps are compared — in a table row, a sentence, a chart label — is in scope.
Step 2: Check for all three numbers
For each drop-off, confirm you have:
- Entering count — unique users at the upstream step
- Exiting count — unique users at the downstream step
- Drop-off percentage —
(entering - exiting) / entering x 100
If any of the three is missing, add it before sending.
Step 3: Verify the arithmetic
The percentage must equal (entering - exiting) / entering x 100, rounded to
one decimal place. Do the division — do not estimate. A wrong percentage is
worse than a missing one.
Step 4: Apply to the "biggest leak" callout too
When the readout names the biggest drop-off, it must follow the same rule. "The biggest leak is checkout_started -> payment_attempted" is incomplete. "The biggest leak is checkout_started -> payment_attempted: 43,490 -> 35,543, an 18.3% drop-off" is complete.
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.
- 6d ago First seen · 90 lines · 77 tokens per session scan A e8ba82a23333
drop-off-format is a skill published in the GitHub repository ai-analyst-lab/ai-analyst-plugin (32 stars, last pushed 10d ago), licensed MIT. It adds 77 tokens to every session and 923 once invoked, about $0.0004 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…