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/verify-hypothesesWrote 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/verify-hypotheses)<a href="https://agentmods.dev/skills/tserentserenov/fmt-exocortex-template/verify-hypotheses"><img src="https://agentmods.dev/badge/skills/tserentserenov/fmt-exocortex-template/verify-hypotheses/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/verify-hypotheses"><img src="https://agentmods.dev/badge/skills/tserentserenov/fmt-exocortex-template/verify-hypotheses.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, 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.
- medium Agent Snooping · line 21 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00099 | $0.01766 |
| Opus 5 | $0.00049 | $0.00883 |
| Sonnet 5 | $0.00020 | $0.00353 |
| Haiku 4.5 | $0.00010 | $0.00177 |
Grade A, and why
verify-hypotheses 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 5d 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/verify-hypotheses
Scope: прочитать
hypotheses-log.md, найти записи с наступившей датой сверки, сверить с фактурой, предложить вердикт, записать подтверждённый пилотом вердикт новой записью. Not in scope: не создаёт новые гипотезы (это Note-Review), не выполняет сверку на week-close автоматически (это шаг 6a.claude/skills/week-close/SKILL.md— этот скилл дублирует тот же алгоритм для вызова вне недельного ритма), не редактирует исходные записи. Role: нет выделенной роли-носителя — используется тем, кто сейчас ведёт week-close (Стратег, R1). См. открытый АрхГейт-вопрос РП-496 Ф4.
When to use
- Пилот говорит «сверь гипотезы недели» или «сверь гипотезы» вне обычного ритма Week Close.
- Есть подозрение, что конкретная гипотеза уже разрешилась (пилот увидел факт раньше даты сверки) и хочет проверить досрочно.
- Диагностика: сколько гипотез сейчас «на сверке» и когда у них дата.
Preconditions
- WP Gate precondition. Задача привязана к РП-496 (Журнал гипотез, LPF-регламент обратной связи), фаза 3.
- Журнал существует.
{{GOVERNANCE_REPO}}/current/hypotheses-log.md— если файла нет, сообщить пилоту и завершить (журнал ещё не создан или создан в другом месте).
Algorithm
Step 1 — Прочитать журнал и отфильтровать
Input: {{GOVERNANCE_REPO}}/current/hypotheses-log.md
Action: прочитать все записи. Отобрать те, у которых Статус: на сверке И Дата сверки ≤ сегодня. Записи со статусом черновик (не подтверждённые пилотом на Note-Review) пропустить — они вне цикла сверки. Записи, уже имеющие вердикт (подтверждена/опровергнута/частично подтверждена/неприменимо), пропустить.
Output: список ID (H-NNN) с наступившей датой сверки, готовых к проверке. Если список пуст — сообщить «Нет гипотез с наступившей датой сверки» и завершить (не ошибка, штатный результат).
Step 2 — Сверить каждую запись с фактурой
Input: список ID из Step 1
Action: для каждой записи прочитать критерий фальсификации и сверить с доступными источниками — коммиты (git log по затронутым репо), domain_event (если критерий про измеримую метрику платформы), инфраструктурные логи, факты из ближайшего WeekReport/DayPlan. Если критерий требует данных, которых нет в доступных источниках — явно пометить «данных недостаточно для вердикта», не гадать.
Output: для каждой записи — черновик вердикта (подтверждена / опровергнута / частично подтверждена / неприменимо) с обоснованием (какие факты сверены, откуда).
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.
- 5d ago Changed · +1 lines 5c7b1a9216c7
- 10d ago First seen · 89 lines · 99 tokens per session scan A 781eea21f39f
verify-hypotheses is a skill published in the GitHub repository TserenTserenov/FMT-exocortex-template (51 stars, last pushed today), licensed MIT. It adds 99 tokens to every session and 1,766 once invoked, about $0.0005 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
team-management-debugging
Systematic debugging — a four-phase root-cause methodology, boundary instrumentation for multi-component systems, the 3-fix escalation rule, and a verification gate to run before claiming anything is fixed. Use on any test failure, production bug, build failure, performance regression, or integration glitch, and…
team-management-receiving-feedback
How to receive code review as technical evaluation rather than social performance — verify claims against the codebase before implementing, push back with evidence, and drop the performative agreement. Use when responding to a human reviewer, a PR comment, or another AI reviewer, and when deciding whether a suggestion…
team-management-tdd-discipline
Test-driven development discipline — when TDD applies, when forcing it is wrong, and the RED-GREEN-REFACTOR loop with an explicit "watch it fail" step. Use when writing or reviewing tests, fixing a bug, changing behaviour, or deciding whether a change needs a test at all. Triggers on bug fixes, new validation or…
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.