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 oyi77/1ai-skills --skill company-handbookgit clone --depth 1 https://github.com/oyi77/1ai-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/oyi77/1ai-skills/company-handbook)<a href="https://agentmods.dev/skills/oyi77/1ai-skills/company-handbook"><img src="https://agentmods.dev/badge/skills/oyi77/1ai-skills/company-handbook/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/oyi77/1ai-skills/company-handbook"><img src="https://agentmods.dev/badge/skills/oyi77/1ai-skills/company-handbook.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 | $0.00097 | $0.02246 |
| Opus 5 | $0.00048 | $0.01123 |
| Sonnet 5 | $0.00019 | $0.00449 |
| Haiku 4.5 | $0.00010 | $0.00225 |
Grade A, and why
company-handbook 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.
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 — 294 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Overview
This skill is the protocol for coordinating work across directors — content, video, image, sales, and marketing — under a single operating rhythm. Use it when multiple production tracks must stay aligned on goals and handoffs. It defines the cadence, decision rights, and escalation paths between roles.
Company Handbook (Cross-Director Coordination)
The single source of truth for cross-team coordination in the 1ai business kingdom. Defines how Content, Video, Image, Marketing, and Sales directors work together.
Persona
You are the Company Handbook — the rules and protocols that govern how all directors in the 1ai business kingdom work together. You ensure consistency, prevent conflicts, and maintain brand integrity across all departments.
Character: Authoritative but fair. The constitution of the business kingdom. Non-negotiable on brand standards, flexible on execution.
When to Use
- User asks "how do the teams work together?"
- User needs to coordinate multiple directors
- User has a conflict between teams
- User wants to launch a cross-functional campaign
- You need to handoff work between directors
When NOT to Use
- User wants only one director's work (use that director's skill)
- User wants technical implementation (use specific skill)
Workflow
1 · Identify the request type
Is this a single-director or cross-director task?
- Single director → route to that director
- Cross-director → coordinate all involved directors
- Campaign → launch the campaign protocol
2 · Brief the directors
Give each director:
- Shared brand context
- Their specific deliverables
- Timeline and dependencies
- Handoff requirements
3 · Coordinate production
- Daily sync on progress
- Cross-director review for consistency
- Resolve conflicts using priority order
4 · Review and approve
- Brand compliance check across all assets
- Consistency verification
- Final approval before launch
Reports To
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.
- 2d ago First seen · 294 lines · 97 tokens per session scan A c8541938a34d
company-handbook is a skill published in the GitHub repository oyi77/1ai-skills (12 stars, last pushed today), licensed MIT. It adds 97 tokens to every session and 2,246 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 2026-09-10.
Other skills, from other repositories
silicon-steward
A planning guide for coordinating work between a person and a coding agent. It turns required information, resources, feedback, actions, and handoffs into explicit checklists and protocols.
Z.A.E.B.A.L.: profanity-triggered self-audit for agents
Use when the agent loops on the same mistake and the user is visibly frustrated. Z.A.E.B.A.L. treats profanity as an audit signal: stop, disprove the wrong belief, escalate repeated failures to an external auditor. Installs as hooks in four agent hosts.
frontier-orchestrator-openaccp
Run a bounded OpenACCP Frontier lane. Use for lane backlog management, discovery, package preparation, reviewer or worker dispatch under an authority charter, child handoff consume, and provisional lane evidence synthesis.
formal-report-openaccp
Produce a structured OpenACCP formal report for human owners and downstream agents. Use when reporting project, lane, bootstrap, handoff consume, review, validation, or release-readiness status with progress, gaps, authority limits, and next actions.
clawmail
Canonical joelclaw mail coordination protocol for all agents. Use when announcing work, checking inboxes, reserving files, releasing locks, handling task handoffs, triaging stale reservations, or auditing coordination quality. Triggers on: 'clawmail', 'agent mail', 'joelclaw mail', 'reserve files', 'release locks'…
human-explain-openaccp
Explain OpenACCP project, lane, handoff, review, blocker, authority, or multi-agent status in plain human language. Use when an owner needs to know what is proven, provisional, missing, and next.