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 HinkoK/agent-skills --skill aftercallgit clone --depth 1 https://github.com/HinkoK/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/hinkok/agent-skills/aftercall)<a href="https://agentmods.dev/skills/hinkok/agent-skills/aftercall"><img src="https://agentmods.dev/badge/skills/hinkok/agent-skills/aftercall.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 | $0.00067 | $0.02736 |
| Opus 5 | $0.00034 | $0.01368 |
| Sonnet 5 | $0.00013 | $0.00547 |
| Haiku 4.5 | $0.00007 | $0.00274 |
Grade A, and why
aftercall 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 8d 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 — 324 lines — stays where its author put it; the contents beside it link to each section on GitHub.
aftercall
Hermes usage rules
- Use after a conversation has happened; do not use for live note-taking.
- If the user provides audio/video, transcribe first, then analyze.
- If the user provides transcript/notes, analyze directly.
- Pick the narrowest mode that fits: work call, client follow-up, study call, therapy/coaching reflection, voice note, or speaker-labeling.
- For therapy/coaching content, do not diagnose; separate observations from interpretations and use careful language.
- End with practical next steps, owners, deadlines, or a ready-to-send follow-up when relevant.
Overview
Use this skill when the user wants to turn a finished conversation into a clear outcome: transcript, structured recap, decisions, owners, next steps, follow-up draft, task list, study notes, or deeper reflection.
This skill is for after a conversation happened. It is not for live note-taking during a call.
Trigger examples
Typical requests:
- "Разбери этот созвон и собери итоги"
- "Вот запись звонка, сделай выжимку и action items"
- "Проанализируй мою сессию с психологом и скажи, над чем поработать"
- "Из этого transcript сделай follow-up письмо"
- "Что мы решили на этом колле и кто за что отвечает?"
- "Сделай учебную выжимку из этого study call"
- "Подготовь заметку в Obsidian по итогам звонка"
- "Сделай транскрипт с Speaker 1 / Speaker 2"
- "Попробуй отличить, кто говорит в записи"
Workflow
1) Identify the input type
Start by determining what the user provided:
- Audio/video recording → transcribe first, then analyze
- Transcript → analyze directly
- Raw notes/messages → normalize into a clean after-call recap
- Several materials → merge them, deduplicate overlaps, then analyze
If the input is missing, ask for exactly one thing: the recording, transcript, or notes.
2) Pick the right mode
Choose the narrowest mode that fits the conversation. If the user does not specify one, infer it from context.
Mode: work-call
Use for team syncs, client calls, planning calls, sales calls, and internal work meetings.
What ships with it
9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- aftercall.skill 15 KB
- README.md 734 B
- references/evaluation-cases.json 3.9 KB
- references/export-templates.md 1.1 KB
- references/modes.md 1.0 KB
- references/output-templates.md 1.8 KB
- references/prompt-formatter.md 2.1 KB
- references/speaker-labeling.md 2.2 KB
- scripts/build_after_call_prompt.py 3.0 KB runs code
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.
- 8d ago First seen · 324 lines · 67 tokens per session scan A b98b74814601
aftercall is a skill published in the GitHub repository HinkoK/agent-skills (5 stars, last pushed 2mo ago), licensed MIT. It adds 67 tokens to every session and 2,736 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
meeting-assistant
AI meeting partner for solopreneurs and professionals. Generates pre-meeting briefs from your notes and context, captures structured meeting notes during the conversation, and produces action item summaries with owners and deadlines. Integrates with project-tracker, inbox-triage, client-relationship-manager, and…
ai-meeting-notes
Messy notes → Clear action items. Instantly. Paste any meeting notes, transcript, or text. Get summaries, action items with owners and deadlines. Auto-saved, searchable, with integrated to-do tracking. No bot. No subscription. No setup.
strategic-questioning
Transforms leaders from directive communicators into strategic questioners who use inquiry to inspire thinking, surface hidden problems, build ownership, and drive better decisions. Covers five essential leadership questions, the art of context-rich inquiry, question-driven meeting design, and techniques for using…
meeting-minutes
Meeting notes processor with action item extraction.
Transcription Automation
Automate audio/video transcription, meeting notes, subtitle generation, and content processing.
meeting-notes
This skill transforms raw meeting notes, transcripts, or audio summaries into clear, structured documentation with action items, decisions, and key takeaways.