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 serejaris/personal-corp-os --skill meeting-copilotgit clone --depth 1 https://github.com/serejaris/personal-corp-osWrote 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/serejaris/personal-corp-os/meeting-copilot)<a href="https://agentmods.dev/skills/serejaris/personal-corp-os/meeting-copilot"><img src="https://agentmods.dev/badge/skills/serejaris/personal-corp-os/meeting-copilot/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/serejaris/personal-corp-os/meeting-copilot"><img src="https://agentmods.dev/badge/skills/serejaris/personal-corp-os/meeting-copilot.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 | $0.00071 | $0.01283 |
| Opus 5.5 | $0.00028 | $0.00513 |
| Sonnet 5.5 | $0.00014 | $0.00257 |
| Haiku 4.5 | $0.00007 | $0.00128 |
Grade A, and why
meeting-copilot 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 1mo 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 — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Meeting Copilot
Create and maintain a local HTML dashboard for a live meeting. The dashboard gives the user a second-screen view of context, questions, topic progress, decisions, risks, and follow-ups while the call is happening.
This skill is designed for private workspaces. Do not publish raw transcripts, client names, personal notes, or generated meeting artifacts unless the user explicitly asks for a sanitized export.
Modes
Use one of three modes:
| Mode | When | Output |
|---|---|---|
| CREATE | Before the meeting | A local dashboard app with prepared context and questions |
| UPDATE | During the meeting | Updated questions, topics, decisions, risks, and follow-ups from transcript chunks |
| CLOSE | After the meeting | Final summary, action items, CRM or notes updates, and optional sanitized export |
CREATE
Inputs:
- meeting title or contact name
- meeting type, for example discovery, sales, mentoring, support, hiring, partnership
- date
- available context files, if any
- output directory
Create this structure:
YYYY-MM-DD-meeting-copilot/
app/
index.html
app.js
components.js
styles.css
tabs/
briefing.js
questions.js
topics.js
decisions.js
followups.js
state/
transcript.txt
diff.py
Dashboard tabs:
briefing.js: meeting goal, known context, participants, constraintsquestions.js: grouped live questionstopics.js: planned and discussed topicsdecisions.js: decisions, risks, blockers, open loopsfollowups.js: action items, owners, due dates, next message draft
If the app uses ES modules, serve it over HTTP:
cd YYYY-MM-DD-meeting-copilot/app
python3 -m http.server 8080
Then open http://127.0.0.1:8080.
UPDATE
Input is usually a full transcript copied from a transcription tool. Treat it as sensitive.
Use suffix diffing so the agent processes only the new part:
#!/usr/bin/env python3
import pathlib
import sys
baseline = pathlib.Path(__file__).parent / "transcript.txt"
old = baseline.read_text() if baseline.exists() else ""
new = sys.stdin.read()
old_s = old.strip()
new_s = new.strip()
if not old_s:
sys.stdout.write(new)
elif new_s.startswith(old_s):
sys.stdout.write(new_s[len(old_s):].lstrip())
else:
sys.stderr.write("[diff] baseline mismatch; using full transcript\n")
sys.stdout.write(new)
What ships with it
1 file 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.
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.
- 1mo ago First seen · 193 lines · 71 tokens per session scan A 24a7f56b1a54
meeting-copilot is a skill published in the GitHub repository serejaris/personal-corp-os (238 stars, last pushed 2d ago), licensed MIT. It adds 71 tokens to every session and 1,283 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
usage-audit
Audit a Claude Code setup for token waste and context bloat. Checks MCP servers, CLAUDE.md, skills, and settings against bloat filters. Triggers on: "audit my context", "usage audit", "token audit", "context bloat". NOT for codebase audits.
janitor-discover
Find new skills on GitHub or check a specific skill before installing. Use when the user wants to search for skills, evaluate a skill URL, check overlap and security risk before installing, or compare a local skill against alternatives. Trigger with '/janitor-discover'.
janitor-value
Show whether each skill is earning its context-window cost — combined tokens-used view sorted by waste. Use when the user asks 'are my skills worth it', 'what's my context budget', 'which skills are dead weight', or wants to audit skill value, token cost, or usage. Trigger with '/janitor-value'.
claude-tracker-suite
Manage Claude Code sessions — search by topic or ID, browse recent sessions with full metadata (tags, summaries, titles, cost), view title/nickname history timelines, resume in Ghostty tabs, spawn interactive or headless sessions, monitor live sessions, and bootstrap new setups. Triggers on resume session, find…
janitor-fix
Automatically fix skill problems (safe preview first). Also use with --prune to find and remove broken symlinks, empty directories, and orphaned skills. Trigger with '/janitor-fix'.
photo-to-slack-emoji
Convert photos into Slack-optimized custom emojis using Nano Banana Pro (Gemini 3 Pro Image) with automatic subject identification, style transformation, and image editing. 64KB/128px compliant. Triggers on: slack emoji, photo to emoji, convert to emoji, edit emoji, emoji maker.