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 skills add TserenTserenov/FMT-exocortex-template --skill bottleneck-pickgit clone --depth 1 https://github.com/TserenTserenov/FMT-exocortex-templateWrote 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/bottleneck-pick)<a href="https://agentmods.dev/skills/tserentserenov/fmt-exocortex-template/bottleneck-pick"><img src="https://agentmods.dev/badge/skills/tserentserenov/fmt-exocortex-template/bottleneck-pick/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/bottleneck-pick"><img src="https://agentmods.dev/badge/skills/tserentserenov/fmt-exocortex-template/bottleneck-pick.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 | $0.00104 | $0.07000 |
| Opus 5.5 | $0.00042 | $0.02800 |
| Sonnet 5.5 | $0.00021 | $0.01400 |
| Haiku 4.5 | $0.00010 | $0.00700 |
Grade A, and why
bottleneck-pick 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 1mo 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 — 477 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: /bottleneck-pick
see DP.SC.045, DP.ROLE.054, DP.WP.016
Носитель методики TOC для пилота: Goldratt Five Focusing Steps + Tendon TameFlow Replenishment Cycle + Dettmer Thinking Processes. Реализует роль Аналитика ограничений (DP.ROLE.054) через пятифазный ВДВ-каскад. Источник: WP-313 (Ф1 research: Tendon «Tame Your Work Flow», Dettmer, Schragenheim, Goldratt S&T; Ф11 IntegrationGate).
Триггеры
- Пользователь открывает зонтичный РП, эпик, проект и спрашивает «что делать сначала»
- Запрос «выбери bottleneck», «что важнее», «с чего начать»
- Стратегическая сессия с отбором НЭП («какое направление сейчас bottleneck»)
- Диагност (R28) запрашивает анализ для учебного конвейера пилота
- Явный вызов
/bottleneck-pick --target WP-NNN
Принцип SC-first (главное правило)
Документо-центричный подход — анти-паттерн. Начинать со списка pending-РП = риск принять канал доставки за продукт.
Правильно: Ф2 сканирует функциональные обещания (DP.SC) ДО Ф3 (signal-scan по структуре работ). Тест: если в Constraint Brief нет ссылок на конкретные DP.SC, которые «не работают» — это провал Ф2.
API
/bottleneck-pick --target <ref> [--layer intra|platform] [--horizon <горизонт>] [--depth <1|2|3>] [--scope <direct|direct+related|full>]
Параметры
| Параметр | Default | Описание |
|---|---|---|
--target |
обязательный | WP-NNN (зонтичный РП), weekplan (текущая неделя), pilot:<account_id> (учебный конвейер пилота), b2:aisystant (вся экосистема — требует --layer=platform), c2:platform (только техника — требует --layer=platform), project-name, repo-path |
--layer |
intra | intra = внутри одной системы (constraint = фаза / РП / блок). platform = между подсистемами C2 (constraint = подсистема / handover / роль B3). Требуется пользовательская карта систем. |
--systems-map |
memory/project_iwe_systems_map.md в установленном рабочем пространстве |
Путь к пользовательской карте для --layer=platform; можно указать абсолютный путь к закрытому каталогу. Карта не доставляется публичным шаблоном. |
--horizon |
all | day, week, month, wave-1, wave-2, quarter, next-stage |
--depth |
2 | 1 = Five Steps only; 2 = + EC для конфликтующих кандидатов; 3 = + Coupling-analysis SOTA.011 для top-3 handovers (только при --layer=platform) |
--scope |
direct+related | direct = только target; direct+related = + связанные РП из frontmatter; full = + reachable через граф связей ≤2 hops |
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.
- 1mo ago Changed 7ee63c414039
- 1mo ago Changed · +3 lines aed0b019ce95
- 2mo ago Changed · +1 lines bce893b0f6f8
- 2mo ago First seen · 473 lines · 104 tokens per session scan A 6011b7bf5a1b
bottleneck-pick is a skill published in the GitHub repository TserenTserenov/FMT-exocortex-template (63 stars, last pushed today), licensed MIT. It adds 104 tokens to every session and 7,000 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 2026-08-30.
bottleneck-pick compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| bottleneck-pickTserenTserenov/FMT-exocortex-template | Skill | 63 | today | MIT | A | 104 | Claude Code |
| team-management-debuggingTeamManagementPlugin/claude-plugin | Skill | 6 | 25d ago | MIT | A | 95 | Claude Code, Codex |
| team-management-receiving-feedbackTeamManagementPlugin/claude-plugin | Skill | 6 | 25d ago | MIT | A | 97 | Claude Code, Codex |
| team-management-tdd-disciplineTeamManagementPlugin/claude-plugin | Skill | 6 | 25d ago | MIT | A | 96 | Claude Code, Codex |
| data-profilingzpower426/datapowers | Skill | 1 | 7mo ago | MIT | A | 42 | Claude Code |
| leakage-guardzpower426/datapowers | Skill | 1 | 7mo ago | MIT | A | 39 | Claude Code |
| verification-before-deliveryzpower426/datapowers | Skill | 1 | 7mo ago | MIT | A | 36 | Claude Code |