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/TserenTserenov/FMT-exocortex-templatenpx agentmods add skills/tserentserenov/fmt-exocortex-template/repo-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/tserentserenov/fmt-exocortex-template/repo-new)<a href="https://agentmods.dev/skills/tserentserenov/fmt-exocortex-template/repo-new"><img src="https://agentmods.dev/badge/skills/tserentserenov/fmt-exocortex-template/repo-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/tserentserenov/fmt-exocortex-template/repo-new"><img src="https://agentmods.dev/badge/skills/tserentserenov/fmt-exocortex-template/repo-new.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium analysis-evasion · line 1 Suspicious Unicode normalization or mixed-script contentFix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.
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 | $0.00199 | $0.05209 |
| Opus 5.5 | $0.00080 | $0.02084 |
| Sonnet 5.5 | $0.00040 | $0.01042 |
| Haiku 4.5 | $0.00020 | $0.00521 |
Grade A, and why
repo-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 yesterday.
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 — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/repo-new
Область действия: создать НОВЫЙ репозиторий IWE (экосистемный DS или личное пространство данных) через обязательный гейт имя/данные/владение, с результатом — созданный репозиторий, запись в реестре, развёрнутый скелет. Не входит: расширение существующего репозитория (→ Repo-Touch/Residency Gate); Pack-репозитории (делегировать
/pack-newна Шаге 1 и остановиться); одномоментное развёртывание всей структуры 5 семей (этоsetup.sh/ WP-559 — этот скилл обрабатывает один репозиторий за вызов). Роль: R6 Кодировщик выполняет гейт и записи фазы Execute; носитель авторизации Decision Gate по умолчанию — пилот (WP-527 Ф0 п.3, решено round-loop сессией 01.09.2026, зафиксировано STAGING.md S-60) — новая Pack-роль не вводится, self-approval со стороны R6 запрещён.
When to use
- Пилот хочет создать новый репозиторий (экосистемный
DS-*/instrument/surface, или личное пространство данныхPD-*/MC-*/PACK-*). - Пилот спрашивает, где и как разместить новый вид данных, а подходящего репозитория ещё нет.
- Автоматизации/CI нужно создать репозиторий по уже одобренной ограниченной политике (пилота в моменте нет).
Preconditions
- WP Gate precondition. Задача должна быть привязана к согласованному РП в плане недели (этот скилл — продукт WP-527).
- Карта доменов данных должна быть актуальна.
docs/adr/ADR-004-data-domain-map.md+docs/DATA-DOMAINS-REGISTRY.yaml(FMT-exocortex-template) должны существовать и быть читаемы — у скилла нет запасной карты доменов, и он не должен изобретать её. - Намерение Pack — немедленный выход. Если запрошенный репозиторий — это Pack, делегировать
/pack-newна Шаге 1 и остановиться; не выполнять остаток гейта этого скилла (авторитет там — Pack Creation Gate, не этот).
Известные исключения (не гейтуются этим скиллом)
Инвентаризация 01.09 (WP-527, в авторской рабочей копии): голые вызовы
gh repo create/create_repositoryвне этого гейта. Скилл вызывает LLM-агент, читающий SKILL.md — сырой bash-скрипт его вызвать не может; поэтому найденные каналы — документированные исключения, не кандидаты на переподключение.
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.
- yesterday Changed · +3 lines 00226a3ae802
- 14d ago Changed 88fe14a6c25a
- 22d ago Changed 3c8834f2a31c
- 1mo ago Changed · +1 lines 1879b7403538
- 1mo ago Changed · +7 lines d9d4ad924350
- 1mo ago First seen · 159 lines · 199 tokens per session scan A cf2f9c82e095
repo-new is a skill published in the GitHub repository TserenTserenov/FMT-exocortex-template (63 stars, last pushed today), licensed MIT. It adds 199 tokens to every session and 5,209 once invoked, about $0.0008 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 2026-09-01.
Other skills, from other repositories
loki-mode
Multi-agent autonomous startup system for Claude Code. Triggers on "Loki Mode". Orchestrates 100+ specialized agents across engineering, QA, DevOps, security, data/ML, business operations, marketing, HR, and customer success. Takes PRD to fully deployed, revenue-generating product with zero human intervention.…
capacity-planner
Use when an ops leader (Director of CX, Head of Support, VP Ops, Head of BizOps, Head of IT ops, Head of Finance ops) is sizing ops capacity, building a headcount plan, modeling utilization risk, planning Q3 capacity or annual support capacity, or designing CS coverage — and needs Erlang-C queueing math, P90 demand…
process-mapper
Use when a BizOps lead, COO, or process-improvement owner needs to document an end-to-end business process (procurement, employee onboarding, incident handoff, customer-onboarding, claims adjudication) in BPMN-style notation, measure cycle times by stage, surface where work spends most of its time waiting vs. being…
change-management
Framework for rolling out organizational changes without chaos. Covers the ADKAR model adapted for startups, communication templates, resistance patterns, and change fatigue management. Handles process changes, org restructures, strategy pivots, and culture changes. Use when announcing a reorg, switching tools…
yearly-planner
Produce the Part 8 yearly planner: quarterly themes and monthly initiatives. "plan the whole year month by month".
64-team-brief-global
Use when a leader assigns work to a marketing team member or runs a cross-functional meeting — a task brief with concrete deliverables, a deadline with time and timezone, a definition of done, constraints, and check-in points, plus an async-first meeting agenda and action-item template. Trigger on 'assign a task'…