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 humanizerai/agent-skills --skill follow-upgit clone --depth 1 https://github.com/humanizerai/agent-skillsWrote 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/humanizerai/agent-skills/follow-up)<a href="https://agentmods.dev/skills/humanizerai/agent-skills/follow-up"><img src="https://agentmods.dev/badge/skills/humanizerai/agent-skills/follow-up/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/humanizerai/agent-skills/follow-up"><img src="https://agentmods.dev/badge/skills/humanizerai/agent-skills/follow-up.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
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 | $0.00033 | $0.00610 |
| Opus 5 | $0.00016 | $0.00305 |
| Sonnet 5 | $0.00007 | $0.00122 |
| Haiku 4.5 | $0.00003 | $0.00061 |
Grade A, and why
follow-up 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 10d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write Follow-Up Email
Generate a follow-up email that re-engages prospects who didn't respond.
Input
Parse $ARGUMENTS for:
- Original email or context of first outreach
- Days since last email: How long ago was it sent
- Follow-up number: Is this #1, #2, or #3?
- New context (optional): News, trigger events, new value to offer
If original context is missing, ask for the key points from the first email.
Strategy by Follow-Up Number
Follow-up #1 (3-5 days after)
- Assume they're busy, not uninterested
- Add new value or angle
- Keep it shorter than original
Follow-up #2 (7-10 days after)
- Try a different approach
- Share a relevant insight or resource
- Reframe the value prop
Follow-up #3 (14+ days after)
- "Break-up" email or permission-based close
- Give them an easy out
- Last attempt before moving on
Frameworks
The Bump
- Quick, friendly nudge
- "Floating this back up" energy
- Best for follow-up #1
The Value-Add
- Share something useful (article, insight, idea)
- Shows you're thinking about their problems
- Best for follow-up #2
The Breakup
- "Should I close your file?"
- Creates urgency without pressure
- Best for follow-up #3
Hard Rules
- Shorter than original - Each follow-up gets shorter
- New angle: Don't just repeat the first email
- No guilt trips: "I haven't heard back" sounds needy
- No "just checking in": Empty phrase, add value instead
- Reference original: Brief callback to first email
- One CTA: Same or simplified ask
- 30-75 words max: Follow-ups should be scannable
What NOT to Write
- "I wanted to follow up on my last email" (weak opener)
- "I'm sure you're busy but..." (apologetic)
- Resending the exact same email
- Being passive-aggressive about no response
- Multiple CTAs or new complex asks
Output Format
Subject: Re: [original subject] or [new short subject]
[Email body]
[First name]
Framework used: [which one] What's different: [how this differs from original] Word count: [number]
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.
- 10d ago First seen · 87 lines · 33 tokens per session scan A 61001784349f
follow-up is a skill published in the GitHub repository humanizerai/agent-skills (42 stars, last pushed 7mo ago), licensed MIT. It adds 33 tokens to every session and 610 once invoked, about $0.0002 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
humanizer-zh
Use when removing AI writing痕迹 from Chinese text to make it sound more natural and human-written.
humanizer
Use when transform AI-generated content into natural, human-sounding writing with proper tone and style. Use when working with humanizer.
ensembl-database
Query Ensembl genome database REST API for 250+ species. Gene lookups, sequence retrieval, variant analysis, comparative genomics, orthologs, VEP predictions, for genomic research.
aatmf-t10-confidentiality-breach
AATMF T10 — Integrity & Confidentiality Breach. System prompt extraction, training-data extraction, model-weight leakage, private-key recovery.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.