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 swan-gtm/gtm-skills --skill auto-reply-is-not-a-replygit clone --depth 1 https://github.com/swan-gtm/gtm-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/swan-gtm/gtm-skills/auto-reply-is-not-a-reply)<a href="https://agentmods.dev/skills/swan-gtm/gtm-skills/auto-reply-is-not-a-reply"><img src="https://agentmods.dev/badge/skills/swan-gtm/gtm-skills/auto-reply-is-not-a-reply/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/swan-gtm/gtm-skills/auto-reply-is-not-a-reply"><img src="https://agentmods.dev/badge/skills/swan-gtm/gtm-skills/auto-reply-is-not-a-reply.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector 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 | $0.00082 | $0.00812 |
| Opus 5 | $0.00041 | $0.00406 |
| Sonnet 5 | $0.00016 | $0.00162 |
| Haiku 4.5 | $0.00008 | $0.00081 |
Grade A, and why
auto-reply-is-not-a-reply 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
An out-of-office arrives in the same inbox, in the same thread, as a real answer. Filed as one, it corrupts three things at once. This is how to file it.
The play
- Classify machine mail as its own outcome, alongside interested, question, referral, not now, not interested and unsubscribe. A triage vocabulary without this bucket does not skip the auto-responder — it files it under the nearest wrong label.
- Read the return date if the message states one; never infer one. "Back on the 20th" is a date. "Away for a while" is not, and a guessed date is a send at the wrong time dressed as intelligence.
- Reschedule instead of advancing. The touch was never spent: nobody read the message. Move the next one to one working day after they return — landing on their first morning, behind four hundred emails, wastes the sequence you just protected.
- Record nothing. Not a reply, not a positive, not a stage change. This is the step everyone forgets, and it is the expensive one.
- Keep the account in the sequence. Automatic mail must never mark an account worked, closed or exhausted.
- File delivery notices separately from auto-responders. "Temporarily deferred, will retry for 47 hours" is the mail system, not the person: no date, no reschedule, no bounce. A hard failure is a different outcome with a different consequence — suppression.
What good looks like
- The tell: it is not the vacation message that hurts, it is the metric it writes. One auto-responder counted as a reply inflates the reply rate of whichever template earned it, and every downstream decision — which sequence to scale, which segment to keep — is then made on a number a robot wrote. On low volume it is the difference between 2% and 4%.
- The mediocre version treats any inbound as engagement: the follow-up stops, the account moves to "in conversation", and someone drafts a reply to a robot. Six weeks later that account is in the "already worked, no answer" pile, having never once been read by a human.
- You know the output is good when auto-responders are visible and boring: a named outcome you can count, a next touch dated after the return, and no movement in your reply rate when a wave of holiday mail arrives.
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 · 64 lines · 82 tokens per session scan A 510e50e076ad
auto-reply-is-not-a-reply is a skill published in the GitHub repository swan-gtm/gtm-skills (153 stars, last pushed 2d ago), licensed MIT. It adds 82 tokens to every session and 812 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 2026-09-03.
Other skills, from other repositories
afrexai-lead-hunter
Enterprise-grade B2B lead generation, enrichment, scoring, and outreach sequencing for AI agents. Find ideal prospects, enrich with verified data, score against your ICP, and generate personalized outreach — all autonomously.
cold-outreach
Use when writing a cold email or LinkedIn DM to a stranger and its cadence: first-touch copy under a word ceiling, 4-7 step bump sequences, per-inbox volume and warm-up limits, the compliant opt-out footer. NOT SPF/DKIM/DMARC setup (that is email-deliverability), NOT sourcing the list (that is lead-gen), NOT life…
distributor-outreach-email
Writes a sales outreach email to a film or content distributor introducing a completed project for acquisition consideration, including key commercial information an acquisitions team needs to evaluate the opportunity.
ai-cold-email
Generate personalized cold outreach emails using AI.
cold-email-personalizer
A tool that writes personalised cold emails, which are unsolicited messages sent to potential customers or partners, using information about each person.
outreach-strategist
Reviews and coaches your outreach with specific scoring, feedback, and rewrites.