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 OneWave-AI/open-agent-stack --skill follow-up-writergit clone --depth 1 https://github.com/OneWave-AI/open-agent-stackWrote 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/onewave-ai/open-agent-stack/follow-up-writer)<a href="https://agentmods.dev/skills/onewave-ai/open-agent-stack/follow-up-writer"><img src="https://agentmods.dev/badge/skills/onewave-ai/open-agent-stack/follow-up-writer/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/onewave-ai/open-agent-stack/follow-up-writer"><img src="https://agentmods.dev/badge/skills/onewave-ai/open-agent-stack/follow-up-writer.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 | $0.00051 | $0.00468 |
| Opus 5 | $0.00026 | $0.00234 |
| Sonnet 5 | $0.00010 | $0.00094 |
| Haiku 4.5 | $0.00005 | $0.00047 |
Grade A, and why
follow-up-writer 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.
What it actually says
Follow-Up Writer
Deals are won in the follow-up and lost in the "I'll send that over" that never arrives. Input: rough notes, a transcript, or two sentences of what happened -- plus, first time, a couple of the rep's sent emails to learn the voice.
Workflow
- Extract the commitments from the notes/transcript, both directions: what we promised (pricing, references, security doc), what they promised (intro to the CFO, data for the pilot), decisions made, and the agreed next step with its date. Implicit commitments count -- "I can probably get you that by Friday" is a promise.
- Draft the recap email in the rep's voice: short, warm, leading with the thing they cared about most (not our agenda), commitments listed with dates, the next step confirmed with the calendar ask, and every promised attachment named. Under 150 words -- recaps get read on phones.
- Write the CRM notes: meeting type, attendees, pain points in the buyer's words, objections raised and how they landed, stage-change recommendation with reasoning, and the commitments as structured next steps. Written for the teammate who inherits this account cold.
- Build the task list: every commitment as a task with owner and due date, including the ones on their side (as follow-up checks: "if no CFO intro by Thursday, nudge").
Rules
- The buyer's words, not sales-speak: CRM notes that say "expressed pain around manual reporting" when they said "I waste every Sunday night on this" lose the good stuff.
- Never invent agreement -- if the next step was left vague, the recap email is where it gets proposed crisply, not remembered falsely.
- Drafts only; the rep sends. The email must sound like them on their best day, not like software.
- Same-day or it decays: if notes arrive stale, say so and prioritize the commitment extraction over polish.
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 · 23 lines · 51 tokens per session scan A f4154aeb8d61
follow-up-writer is a skill published in the GitHub repository OneWave-AI/open-agent-stack (2 stars, last pushed 29d ago), licensed MIT. It adds 51 tokens to every session and 468 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
comps-analysis
Build comparable-company valuation workbooks in Excel.
ascii-video
ASCII video: convert video/audio to colored ASCII MP4/GIF.
pretext
Build creative browser demos with DOM-free text layout.
pinggy-tunnel
Zero-install localhost tunnels over SSH via Pinggy.
weights-and-biases
W&B: log ML experiments, sweeps, model registry, dashboards.
grounded-citations
Ground answers and documents in cited, verifiable sources.