Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/serejaris/personal-corp-osnpx agentmods add skills/serejaris/personal-corp-os/corp-newWrote 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/serejaris/personal-corp-os/corp-new)<a href="https://agentmods.dev/skills/serejaris/personal-corp-os/corp-new"><img src="https://agentmods.dev/badge/skills/serejaris/personal-corp-os/corp-new/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/serejaris/personal-corp-os/corp-new"><img src="https://agentmods.dev/badge/skills/serejaris/personal-corp-os/corp-new.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 | $0.00096 | $0.03558 |
| Opus 5.5 | $0.00038 | $0.01423 |
| Sonnet 5.5 | $0.00019 | $0.00712 |
| Haiku 4.5 | $0.00010 | $0.00356 |
Grade A, and why
corp-new scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
corp-new: новый отдел штаба
Штаб это главная папка работы с агентом: файл правил, me.md, карта отделов. Отдел это соседняя папка штаба со своим файлом правил, словарём, скиллами и задачами, например corp-sales или corp-learn. Отдел знает свой штаб, штаб знает свои отделы: связь записана в правилах с обеих сторон.
Скилл идёт по шагам и отвечает таблицей ✓/✗. Правила отдела за человека он не пишет: ставит каркас с пустыми местами, их человек заполняет сам или вместе с агентом через /mp-grill-me. Исключение — готовые отделы из templates/ (шаг 3): их правила уже заполнены. Чужие файлы не трогает, незакоммиченную работу не выбрасывает. GitHub не нужен: отдел живёт в локальной папке.
Команды даны для macOS и Linux (zsh, bash). На Windows агент делает то же средствами PowerShell.
1. Найти штаб
Штаб узнаётся так же, как в скилле hq (шаг 1): папка с me.md или stack/harness.md. Где искать, по порядку:
for d in . ./hq .. ../hq ~/Documents/GitHub/hq ~/hq; do
{ [ -e "$d/me.md" ] || [ -e "$d/stack/harness.md" ]; } && (cd "$d" && pwd -P)
done | sort -u
- Нашёлся один — это штаб; дальше его путь
HQ, папка репозиториевROOT— его родитель. - Нашлось несколько — спросить одной строкой, какой.
- Открыт отдел, и в его файле правил есть ссылка на штаб (
../<папка>) — штаб берётся по ней. - Не нашлось — шаг 2.
2. Штаба нет: поставить из agent-starter
Папка штаба по умолчанию — ~/Documents/GitHub/hq, если есть ~/Documents/GitHub; иначе спросить одной строкой, где держать репозитории. Путь только латиницей.
ROOT=~/Documents/GitHub; HQ="$ROOT/hq"
git clone https://github.com/serejaris/agent-starter.git "$HQ"
git -C "$HQ" remote rename origin upstream # обновления стартера — git pull upstream main
mkdir -p "$HQ/stack"
Дальше в папке штаба пройти скилл hq этого штаба ($HQ/.agents/skills/hq): он определит харнес, поставит главный файл правил и me.md. Пустые правила штаба заполняются по образцу из шага 5 скилла hq, словами человека.
What ships with it
10 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.
- assets/illustration-en.svg 5.9 KB
- assets/illustration.svg 6.6 KB
- README.md 2.2 KB
- README.ru.md 3.1 KB
- templates/common/CONTEXT.md 602 B
- templates/common/gitignore 472 B
- templates/corp-research/AGENTS.md 3.3 KB
- templates/corp-research/INDEX.md 124 B
- templates/corp-research/skills/corp-research/SKILL.md.tmpl 1.4 KB
- templates/corp-research/tags.md 0 B
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.
- today Changed · +59 lines 3c6aaab5f12b
- 16d ago First seen · 137 lines · 96 tokens per session scan A 95bdfe7951b7
corp-new is a skill published in the GitHub repository serejaris/personal-corp-os (230 stars, last pushed today), licensed MIT. It adds 96 tokens to every session and 3,558 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-30.
Other skills, from other repositories
milestone-runner
Use when asked to "run milestones", "execute EXECUTIONPROMPTS.md", "continue the milestone sequence", "run independent milestones in parallel", "merge the stack", or "reconcile M5" after prior work changes the current design. Not for generating plan files; use plan-prompts. Not for repairing one stack; use stacked-prs.
task-decomposer
Produces phased task boards from feature requests: dependency-mapped work items, parallelization flags, risk flags, edge cases, test matrices. Triggers on: "decompose this feature", "task breakdown with dependencies", "phased implementation plan", "work breakdown structure". NOT for discovering which decisions are…
project-context-setup
Scaffolds per-repository agent context so coding agents share the same issue tracker rules, triage label vocabulary, domain glossary, ADR layout, and handoff conventions. Triggers on: "set up project context", "configure agent docs", "create CONTEXT.md", "setup agent workflow", "agent issue tracker setup", "triage…
github
GitHub CLI operations via gh for issues, PRs, Actions, releases, and REST/GraphQL API with --json/--jq parsing. Triggers on: "create an issue", "submit a PR", "check CI status", "why did CI fail", "merge a PR", or pasted GitHub URLs.
slack
Slack workspace integration: 9 on-demand scripts (post, read, delete, search, stream, react, upload, channels, users) + dual-token support + RTS API search + chat streaming + AI Block Kit + Session Bridge + Claudicle unified launcher (Claude Agent SDK, soul engine, three-tier memory).
crm-cleanup
A CRM data-cleanup workflow for finding inactive deals, duplicate contacts, and missing fields. A CRM is software used to manage customers, contacts, sales opportunities, and their activity history.