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 ahkedia/lyra-ai --skill chief-of-staffgit clone --depth 1 https://github.com/ahkedia/lyra-aiWrote 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/ahkedia/lyra-ai/chief-of-staff)<a href="https://agentmods.dev/skills/ahkedia/lyra-ai/chief-of-staff"><img src="https://agentmods.dev/badge/skills/ahkedia/lyra-ai/chief-of-staff/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/ahkedia/lyra-ai/chief-of-staff"><img src="https://agentmods.dev/badge/skills/ahkedia/lyra-ai/chief-of-staff.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 | $0.00046 | $0.01121 |
| Opus 5.5 | $0.00018 | $0.00448 |
| Sonnet 5.5 | $0.00009 | $0.00224 |
| Haiku 4.5 | $0.00005 | $0.00112 |
Grade A, and why
chief-of-staff 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Chief of Staff (Lyra)
Orchestration skill for day-to-day operations: triage, scheduling context, task focus, and outreach hygiene. This skill does not replace other skills — it coordinates them.
When to load this skill
- Akash asks for: morning brief, daily prep, "chief of staff", "EA mode", inbox triage, week plan, recruiter pipeline review
- A cron message says:
chief-of-staffor references morning prep / daily operations (keep cron bodies short; full steps live here)
When not to use this skill
- Tier 0 reminder/list CRUD ("list my reminders", "add milk to shopping") → use
crud/cli.pyperskills/model-router/SKILL.mdandconfig/routing-rules.yaml - Abhigna requests → follow
SOUL.mdaccess rules only; do not surface Akash-only databases - Health logging →
skills/health-coach/SKILL.mdonly
Canonical surfaces (no conflicts)
| Surface | Role |
|---|---|
Notion (references/notion.md) |
System of record for reminders, recruiter tracker, projects |
tasks/current.md |
Human-editable today focus — promote 3–5 items; dedupe against Notion before acting |
TOOLS.md |
Quick index of tools and constraints — read if unsure what exists |
Repo copies live under lyra-ai/workspace/; server copies under ~/.openclaw/workspace/. Deploy syncs via scripts/deploy-lyra.sh.
Operating rules (non-negotiable)
Email (himalaya / Gmail MCP)
- Prefer message-level understanding: do not assume one thread = one decision; scan recent messages that match the task
- Draft first; never send without explicit "YES send" (see
SOUL.md)
Calendar (skills/google-calendar/SKILL.md, scripts/gcal-helper.js)
- Before proposing or confirming a time: consider all relevant calendars (personal, shared, work) per SOUL routing
- Surface conflicts explicitly; do not assume "free" on one calendar means free overall
Recruiter / outreach (Notion Recruiter Tracker)
- Update the tracker (status, last touch, next step) before treating a reply or thread as "handled"
- Do not mark outreach "done" in chat without a Notion update (or explicit Akash instruction to skip)
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 · 92 lines · 46 tokens per session scan A c9fbfd9a3ff3
chief-of-staff is a skill published in the GitHub repository ahkedia/lyra-ai (5 stars, last pushed 1mo ago), licensed MIT. It adds 46 tokens to every session and 1,121 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
brief
Brief — the owner's day in review: tasks, calendar, mail, Telegram, every Connection and plugin, goals from CORE, weather. Load in a scheduled Brief turn, on /digest, and when the owner asks for a day plan, a review of the day or their open tasks.
slack-tools
Slack workspace management and automation specialist.
telegram-userbot
A skill for connecting to and working through the owner's personal Telegram account, rather than a Telegram bot. It can read personal chats, search messages, and send messages as the account owner after setup and consent.
email-triage
The shared-inbox triage runbook — how to read a new inbound email, label it, look up {{helpdoc}} for a standard answer, draft a reply in Gmail or file a ticket in {{linearteam}}, and when to leave a thread label-only for a human.
interview-scheduling
Daily interview-scheduling sweep for {{projectName}}. Reads {{greenhousepipeline}} for candidates ready to schedule and each one's interview plan, checks {{interviewercalendars}} for panel availability, and drafts a candidate slot proposal plus a calendar invite per interviewer to {{coordinatorreviewinbox}}. Never…
insight
A scheduled daily practice that looks for a repeated manual task, builds and tests a small tool for it, and suggests the result. It can instead report a development issue when the agent cannot solve its own problem.