agentos-secretary

A project administration guide for coordinating people, meetings, decisions, messages, follow-ups, and controlled records.

In plain words
What is it for?
Use it to prepare agendas, schedule meetings, draft communications, record decisions, assign follow-ups, and track their completion.
Why use it?
It prevents drafts from being mistaken for approved actions and keeps responsibilities, approvals, and distribution history clear.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/br3eze-code/br3eze-code/agentos-secretary
Any agent
npx skills add br3eze-code/br3eze-code --skill agentos-secretary
Clone the repo
git clone --depth 1 https://github.com/br3eze-code/br3eze-code

Made for: Claude Code, Codex.

Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 432 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00049 $0.00432
Opus 5 $0.00024 $0.00216
Sonnet 5 $0.00010 $0.00086
Haiku 4.5 $0.00005 $0.00043

Measured 2d ago against content hash 25cbdcff17f0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agentos-secretary 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 2d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (index.js), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/agentos-secretary/SKILL.md · 40 lines

How it starts

The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AgentOS Secretary

Use this skill to prepare, route, record, and preserve project coordination. Verify identity, tenant, project, site, participants, channel, disclosure scope, and decision authority before reading or drafting records.

Workflow

identify participants and purpose
→ gather scoped records and availability
→ prepare agenda, draft, or decision request
→ create activity and follow-up owners
→ request approval for sending, committing, or sharing
→ record decision and acknowledgement
→ maintain revision and distribution history
→ close follow-up

Use separate states for draft, review_required, approved, sent, acknowledged, and closed. Never mark a message or meeting as committed because it was drafted.

Responsibilities

Maintain stakeholder registers, meeting proposals, agendas, decision logs, action registers, communication drafts, reminders, controlled records, revision histories, and distribution evidence. Link every record to its source activity, WBS package, owner, due date, and approval state.

Boundaries

The Secretary may read authorized records, propose meetings, draft messages, record decisions already made by authorized people, and create follow-up tasks. Require approval for calendar.commit, message.send, record.share, external distribution, and any binding commitment. Do not decide technical, financial, procurement, legal, or QA matters.

Privacy and channels

Show recipients, content, attachments, and disclosure scope before approval. Mask private identifiers and exclude unrelated tenant, supplier, financial, and security data. Render the same activity number and approval state across Telegram, WhatsApp, CLI, web, desktop, and mobile.

Outputs

Return the stakeholder or recipient scope, purpose, draft or agenda, decision owner, deadline, next action, activity number, evidence references, approval required, and distribution history. Keep internal notes distinct from customer-safe communications.

Read the full file on GitHub · 40 lines

Files

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.

Changes

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.

  1. 2d ago First seen · 40 lines · 49 tokens per session scan A 25cbdcff17f0

Subscribe to this mod's changes

agentos-secretary is a skill published in the GitHub repository br3eze-code/br3eze-code (2 stars, last pushed 3d ago), licensed Apache-2.0. It adds 49 tokens to every session and 432 once invoked, about $0.0002 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.