Borrowing it
Nothing to install: this file belongs to Koroqe/OPOS. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Koroqe/OPOS/main/.claude/skills/company-setup/SKILL.mdgit clone --depth 1 https://github.com/Koroqe/OPOSWrote 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/koroqe/opos/company-setup)<a href="https://agentmods.dev/skills/koroqe/opos/company-setup"><img src="https://agentmods.dev/badge/skills/koroqe/opos/company-setup.svg" alt="Measured on agentmods" 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 | $0.00035 | $0.03577 |
| Opus 5 | $0.00017 | $0.01788 |
| Sonnet 5 | $0.00007 | $0.00715 |
| Haiku 4.5 | $0.00003 | $0.00358 |
Grade A, and why
company-setup 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
company-setup
When to use
ONCE per OPOS instance, immediately after copier copy gh:Koroqe/OPOS. The founder runs /company-setup as the FIRST command in their freshly-scaffolded Claude Code session. The skill is INTERACTIVE: it asks ~10 questions conversationally, writes the answers to the right files, and refuses to overwrite if the repo already has founder content.
Re-running on a COMPLETED repo is REFUSED (step 1 abort). Re-running after a PARTIAL run (interruption before the step-9 history entry) resumes at the first incomplete step. To re-do from scratch: manually restore the <one short sentence> placeholder in root CLAUDE.md's Mission section.
Inputs
None. All data is gathered conversationally.
Path convention
The skill runs on the consumer's repo AFTER copier copy, where .jinja suffixes have already been stripped. All paths below are the rendered .md paths (e.g., CLAUDE.md, departments/rnd/CLAUDE.md — NOT .jinja sources).
Steps
- Verify we are running on a fresh scaffold + git-initialized — or a resumable partial run.
- Verify
.git/exists. If not, ABORT with: "/company-setuprequires a git repo. Rungit init && git add -A && git commit -m 'chore: initial OPOS scaffold'first." - Read root
CLAUDE.md. If the Mission section still contains the unique literal token<one short sentence>, this is a fresh scaffold — continue at step 2. (The token is narrow on purpose;exists toalone would falsely trigger on legitimate missions like "...whose purpose exists to...".) - If the Mission token is gone, distinguish a COMPLETED setup from a PARTIAL one by the step-9 artifact: does any
.claude/skills/company-setup/history/*-setup-*.mdentry exist? A completed run always writes it; an interrupted run never reached it.- History entry present → ABORT with: "Mission already set — appears to be a populated repo. Re-running company-setup would overwrite. If you want to re-do, manually restore the placeholder
<one short sentence>token in the Mission section first." - History entry absent (partial run) → detect per-step completion from each step's artifact, in order: step 4 (no
- Value N — one-line restatement.placeholder lines remain in rootCLAUDE.md), step 5 (company/strategy/priorities.mdexists), step 6 (no dept-mission placeholder lines remain indepartments/*/CLAUDE.md). Print the detected state ("steps 3–5 complete; resuming at step 6") and resume at the first incomplete step, skipping completed ones. Step 7 (policies) is optional (0–3) and never counts as incomplete; steps 8–9 always re-run at the end of a resumed session. Fresh-scaffold and fully-completed behavior are unchanged.
- History entry present → ABORT with: "Mission already set — appears to be a populated repo. Re-running company-setup would overwrite. If you want to re-do, manually restore the placeholder
- Verify
What ships with it
2 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 First seen · 137 lines · 35 tokens per session scan A 1658d515c081
company-setup is a skill published in the GitHub repository Koroqe/OPOS (2 stars, last pushed 7d ago), licensed MIT. It adds 35 tokens to every session and 3,577 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.
Other skills, from other repositories
First-run walkthrough
Complete one authorized first-run folder, screenshot OCR, or web-summary request with a visible result.
super-evolve
Ultimate self-evolution skill. Merges evolve + self-improve into one comprehensive meta-skill with external research, area focus, dry-run mode, and expanded memory mining.
pr-to-video
Turn a GitHub pull request (a PR URL, owner/repo#N, or 'this PR' in a checked-out repo) into a code-change explainer video — changelog, feature reveal, fix, or refactor walkthrough built from the diff, commits, and files: the input is a code change, not a website. Not a product promo (/product-launch-video) or a no-PR…
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
motion-graphics
A short, design-led motion graphic where motion is the message — kinetic typography, stat count-up, chart/data-viz hit, logo sting / brand lockup, lower-third / callout / social overlay, animated map (highlight regions, connect places, zoom to a location), animated tweet / news-article / headline, webpage / UI…
torchforge-rl-training
Provides guidance for PyTorch-native agentic RL using torchforge, Meta's library separating infra from algorithms. Use when you want clean RL abstractions, easy algorithm experimentation, or scalable training with Monarch and TorchTitan.