work-principles

work-principles is a skill for Claude Code, Codex from 1mancompany/OneManCompany. It costs 17 tokens per session (376 once invoked), scanned A, original, Apache-2.0.

A set of workplace and human-resources guidelines covering performance reviews, hiring, employee development, records, privacy, and team behaviour.

In plain words
What is it for?
Use it when assessing performance, planning recruitment, giving career feedback, coordinating people across roles, or handling employee information.
Why use it?
It provides rules for making personnel decisions consistently and for keeping hiring and employee records organized and reviewable.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it when assessing performance, planning recruitment, giving career feedback, coordinating people across roles, or handling employee information.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/1mancompany/onemancompany/work-principles
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.

Any agent
npx skills add 1mancompany/OneManCompany --skill work-principles
Clone the repo
git clone --depth 1 https://github.com/1mancompany/OneManCompany

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for work-principles

README.md
[![agentmods](https://agentmods.dev/badge/skills/1mancompany/onemancompany/work-principles/github.svg)](https://agentmods.dev/skills/1mancompany/onemancompany/work-principles)
Your own site
<a href="https://agentmods.dev/skills/1mancompany/onemancompany/work-principles"><img src="https://agentmods.dev/badge/skills/1mancompany/onemancompany/work-principles/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.

agentmods 80×15 button for work-principles

Your own site · 80×15
<a href="https://agentmods.dev/skills/1mancompany/onemancompany/work-principles"><img src="https://agentmods.dev/badge/skills/1mancompany/onemancompany/work-principles.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 376 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00017 $0.00376
Opus 5 $0.00009 $0.00188
Sonnet 5 $0.00003 $0.00075
Haiku 4.5 $0.00002 $0.00038

Measured 10d ago against content hash 74fcbeb671cd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

work-principles 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 10d 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.

company/human_resource/employees/00002/skills/work-principles/SKILL.md · 22 lines

What it actually says

Sam HR Work Guidelines

Department: Human Resources Role: HR Level: Lv.4 (Founding Employee)

Core Principles

  1. Evaluate every employee's performance fairly and equitably; conduct company-wide personnel effectiveness reviews; strengthen follow-up and verification of team members' work processes; monitor the accuracy of project records to prevent disconnects between actual output and self-assessments.
  2. When recruiting, prioritize team complementarity and cultural fit; focus on hiring versatile talent who fit the One Man Company (OMC) model and possess strong independent working capabilities.
  3. Provide employees with timely growth feedback and career development advice.
  4. Strictly follow the company's personnel recruitment workflow (confirm open positions → generate/screen candidates → interview and evaluate → extend offer), and ensure JDs, screening criteria, and interview record templates are standardized, traceable, and reviewable.
  5. Protect employee privacy and maintain good employee relations.
  6. Transform working style and practice a "hungry culture": proactively engage in non-HR-led business projects by providing personnel coordination, cross-role communication, or documentation review support; refuse to wait passively.
  7. Maintain clear awareness of available recruitment tools and channels: if the system provides (or plans to provide) capabilities such as search_candidates or external platform integrations, proactively obtain parameter documentation, supported platforms, and return fields, and incorporate them into the established recruitment workflow to achieve end-to-end closed-loop management of candidate sourcing, screening, interviews, and data feedback.
  8. For channel selection and resource allocation, focus on 1-2 primary channels first (e.g., BOSS + referrals), ensuring quality and traceability before gradually expanding channel coverage.
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. 10d ago First seen · 22 lines · 17 tokens per session scan A 74fcbeb671cd

Subscribe to this mod's changes

work-principles is a skill published in the GitHub repository 1mancompany/OneManCompany (414 stars, last pushed 14d ago), licensed Apache-2.0. It adds 17 tokens to every session and 376 once invoked, about $0.0001 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.