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 gs-bbluhm/gainsight-mcp-plugins --skill staircase-follow-up-draftgit clone --depth 1 https://github.com/gs-bbluhm/gainsight-mcp-pluginsWrote 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/gs-bbluhm/gainsight-mcp-plugins/staircase-follow-up-draft)<a href="https://agentmods.dev/skills/gs-bbluhm/gainsight-mcp-plugins/staircase-follow-up-draft"><img src="https://agentmods.dev/badge/skills/gs-bbluhm/gainsight-mcp-plugins/staircase-follow-up-draft/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/gs-bbluhm/gainsight-mcp-plugins/staircase-follow-up-draft"><img src="https://agentmods.dev/badge/skills/gs-bbluhm/gainsight-mcp-plugins/staircase-follow-up-draft.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 | $0.00095 | $0.01211 |
| Opus 5.5 | $0.00038 | $0.00484 |
| Sonnet 5.5 | $0.00019 | $0.00242 |
| Haiku 4.5 | $0.00010 | $0.00121 |
Grade A, and why
staircase-follow-up-draft 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 25d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Staircase Follow-Up Draft
Turn the last ~90 days of communication into a warm, specific follow-up email the user can edit and send. It references real conversations (not generic pleasantries), addresses the open items, and comes with the source interactions so the user can verify before sending. This skill drafts. It never sends.
Foundation references
Read these before composing the query if you have not in this session:
../staircase-mcp-expert/: query mechanics, non-determinism handling.../../_shared/staircase-output-best-practices.md: the house style and the draft-do-not-send rule.
When to use
Trigger phrases:
- "draft a follow-up to [account]" / "draft a follow-up email for [account]"
- "write a follow-up email for [account]"
- "help me follow up with [account]"
- "draft an email to [account]"
Optimized for: Cowork (draft in a card, copy-ready) and Code (draft to stdout, optional file).
Step 1: Resolve the account
Call staircase_account_lookup(name=<account>) first.
- High-confidence single match: proceed.
- Multiple low-confidence matches: STOP and ask which account. Do not guess.
- No match: say so and ask for an alternate name.
Step 2: Run the follow-up query
Use the validated Draft a Follow-Up prompt verbatim via staircase_analyze_account.
staircase_analyze_account(account_id, query="
Draft a follow-up email to <Account> based on my most recent interactions. First give me a two-line summary of what it needs to address (open items, commitments, any concern to acknowledge), then write the email: warm but concise, in my voice, referencing specifics from our actual conversations, with clear next steps. Show me the source interactions you drew from so I can verify before sending.")
Non-determinism: re-run the same phrasing once or twice if thin. If the account has almost no recent communication, say so rather than inventing specifics. A grounded draft beats a fabricated one.
Optional evidence drill: confirm a referenced detail with staircase_fetch_evidence(<evidence_id>) before it goes in the draft, so the email does not misquote a conversation.
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.
- 25d ago First seen · 100 lines · 95 tokens per session scan A 95eee7c0ec37
staircase-follow-up-draft is a skill published in the GitHub repository gs-bbluhm/gainsight-mcp-plugins (4 stars, last pushed 20d ago), licensed MIT. It adds 95 tokens to every session and 1,211 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-26.
Other skills, from other repositories
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…
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…