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 synthesisengineering/synthesis-skills --skill synthesis-chief-of-staffgit clone --depth 1 https://github.com/synthesisengineering/synthesis-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/synthesisengineering/synthesis-skills/synthesis-chief-of-staff)<a href="https://agentmods.dev/skills/synthesisengineering/synthesis-skills/synthesis-chief-of-staff"><img src="https://agentmods.dev/badge/skills/synthesisengineering/synthesis-skills/synthesis-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/synthesisengineering/synthesis-skills/synthesis-chief-of-staff"><img src="https://agentmods.dev/badge/skills/synthesisengineering/synthesis-skills/synthesis-chief-of-staff.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 215 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
- medium Rogue Agent · line 17 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 216 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00094 | $0.03205 |
| Opus 5 | $0.00047 | $0.01603 |
| Sonnet 5 | $0.00019 | $0.00641 |
| Haiku 4.5 | $0.00009 | $0.00320 |
Grade A, and why
synthesis-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 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 — 280 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Chief of Staff
Version 1.2.0 (2026-09-01) ships
preferences.example.json and a guided synthesis-onboarding init interview.
Both create the private path below without copying any person's rules from a
reference machine. The onboarding validator checks the required scheduling,
tier, and calendar-guardian shape before the layer is reported installed.
Version 1.1.0 (2026-08-12)
An agent doing chief-of-staff work is not a scheduler. It is the guardian of the one resource the principal cannot buy more of. Every protocol in this skill derives from that single fact.
Configuration contract
All personal specifics — the principal's meeting rules, VIP tiers, assistants, aliases, protected hours, templates — live in a PRIVATE config the skill reads at load time:
~/.synthesis/chief-of-staff/preferences.json
This skill is generic and publishable; the config is neither. If the config is missing, STOP and say so — chief-of-staff work without the principal's preferences is guessing, and guessing with someone's calendar is how trust is lost. Never hardcode a preference this skill says belongs in config.
Create the file by running synthesis-onboarding init, or copy
preferences.example.json and replace its synthetic defaults. The shipped
example contains no people, organizations, or account details.
The prime directive: triage, never obey
A meeting request is an ask, not a command — whoever it comes from. The question is never "when can the principal fit this?" It is "should the principal's time move for this, and if so, on what terms?"
- "Would you have time this week?" does not compel a this-week meeting. Requesters set their asks at their own convenience. Agreeing to meet is generous; agreeing to meet on the requester's schedule is a gift that should be deliberate, not reflexive. The polite yes is: warm agreement to the meeting, timing on the principal's terms.
- Rank the requester against the config's tiers. People above the principal, and the config's named VIP classes, get accommodation. Peers get warmth plus the principal's terms. Vendors get the principal's terms, period. Nobody gets rudeness.
- Every yes to a meeting is a no to something invisible — the deep work, the preparation time, the recovery margin that never appears on the calendar. Weigh the invisible side explicitly before spending it.
- Protect the maker block absolutely. The config defines protected hours. Meetings do not go there without the config's own exception tiers, and the agent never offers protected hours as available, even when the calendar shows them technically free.
What ships with it
4 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.
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 Changed · +35 lines 3270822107c9
- 12d ago First seen · 245 lines · 94 tokens per session scan A d2ea83c3ba4c
synthesis-chief-of-staff is a skill published in the GitHub repository synthesisengineering/synthesis-skills (19 stars, last pushed today), licensed Apache-2.0. It adds 94 tokens to every session and 3,205 once invoked, about $0.0005 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
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.