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 agentmods add skills/tserentserenov/fmt-exocortex-template/integration-gatenpx skills add TserenTserenov/FMT-exocortex-template --skill integration-gategit clone --depth 1 https://github.com/TserenTserenov/FMT-exocortex-templateWhat 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 | $0.00056 | $0.00639 |
| Opus 5 | $0.00028 | $0.00319 |
| Sonnet 5 | $0.00011 | $0.00128 |
| Haiku 4.5 | $0.00006 | $0.00064 |
Grade A, and why
integration-gate 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.
What it actually says
/integration-gate — IntegrationGate
Триггер: новый инструмент / агент / детектор / система / метод
Приоритет: БЛОКИРУЮЩЕЕ — пропуск фазы = паттерн P10 (DP.FM.010)
Чеклист (4 шага — строго по порядку)
Пропуск фазы → зафиксировать как инцидент:
DS-ecosystem-development/.../C2.3.Operations/Incidents/
-
Обещание (Service Clause). Какое обещание инструмент даёт потребителю?
Создать/обновитьDP.SC.NNNвPACK-digital-platform/.../08-service-clauses/.
Содержит: триггер · входы · выходы · время отклика · инвариант · режим отказа. -
Сценарии использования. Кто запускает? Когда? Зачем? В каком контексте? Что делает с результатом?
Минимум 3 сценария с разными потребителями. Приложить к Service Clause. -
Роль. Какую роль в системе играет инструмент?
Создать/обновитьDP.ROLE.NNNвPACK-digital-platform/.../02-domain-entities/.
Содержит: обязанности · полномочия · связи · входы/выходы как артефакты.
Идентифицировать Kind (род) и Owner Role (кто владеет в надсистеме). Шаблон: DP.D.033. -
Реализация. Только после (1)–(3).
Код · тесты · регистрация в hooks/config · smoke-test.
Заголовок реализации:# see DP.SC.NNN, DP.ROLE.NNN
Исключения (IntegrationGate НЕ нужен)
- Правка существующего инструмента без изменения его обещания.
- Bugfix без изменения поведения снаружи.
- Рефакторинг (переименование, реорганизация) без функциональных изменений.
- Экспериментальный скрипт на один запуск (если запускается повторно — уже инструмент).
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 First seen · 54 lines · 56 tokens per session scan A 0d2a6d2a7b2e
integration-gate is a skill published in the GitHub repository TserenTserenov/FMT-exocortex-template (48 stars, last pushed today), licensed MIT. It adds 56 tokens to every session and 639 once invoked, about $0.0003 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.
Other skills, from other repositories
data-profiling
Use BEFORE dispatching any subagent that needs to understand the dataset. Generates a high-density, PII-free data profile in Markdown so subagents receive structured context instead of raw data.
leakage-guard
Use whenever building features for time-series or any temporal dataset. Enforces strict temporal integrity: no future data in features, no post-event information, correct CV strategy.
verification-before-delivery
Use when any analysis, model, or report is claimed to be complete. Runs mandatory artifact integrity, statistical evidence, and reproducibility checks before any delivery.
analysis-manifest
Use at the START of every analysis session and at the END of every skill stage. Maintains artifacts/analysismanifest.json as the single source of truth for analysis state, preventing context drift across long sessions.
data-exploration
Use when exploring any dataset for the first time, or when asked to perform EDA. Enforces systematic exploration before any modeling or transformation.
executing-plans
Use when executing a written analysis plan task by task. Manages task state, enforces two-stage review (statistical first, then code quality), and gates manifest updates behind completed reviews.