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 cryndoc/polisade-orchestrator --skill spikegit clone --depth 1 https://github.com/cryndoc/polisade-orchestratorWrote 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/cryndoc/polisade-orchestrator/spike)<a href="https://agentmods.dev/skills/cryndoc/polisade-orchestrator/spike"><img src="https://agentmods.dev/badge/skills/cryndoc/polisade-orchestrator/spike.svg" alt="Measured on agentmods" 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 | $0.00105 | $0.02651 |
| Opus 5 | $0.00053 | $0.01326 |
| Sonnet 5 | $0.00021 | $0.00530 |
| Haiku 4.5 | $0.00011 | $0.00265 |
Grade A, and why
spike scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/polisade:spike [вопрос] — Исследовательская задача
Timeboxed исследование для принятия технического решения.
⛔ Вызов скрипта отклонён или не запустился (
Command references protected path/Install directory is read-protected/Filesystem Guard/the tool's default permission is 'deny', отказ песочницы, ненулевой exit без вывода) — STOP. Процитируй отказ дословно. НЕ пересказывай по исходнику, что скрипт «сделал бы»; НЕ собирай dry-run вручную; НЕ переходи к apply/push/pr-create. НЕ транскрибируй скрипт (прочитать → записать копию в/tmpили в проект → запустить копию): копия не байт-идентична — уезжают классы символов в regex, форма возврата функций, пропадают целые функции — и молча меняется набор применённых изменений. Отказ инструмента — это отказ, а не результат. Доложи PM дословный текст отказа и сошлись на #127 (доставка скриптов в проект).
⛔ Живой корпус
docs/architecture/пишет ОДИН исполнитель —${POLISADE_PYTHON:-python3} {plugin_root}/scripts/polisade_corpus_io.py(stdlib-only). НиWrite, ниEdit, ниcp, ниmv, ни>в корпус не идут: примитив даёт пофайловую атомарность, блокировку от второго писателя, журнал оборванной промоции, проверяемый манифестом backup и отказ на симлинках и побегах пути. Ручное копирование обходит всё перечисленное — это регресс, а не «то же самое».Хэш-контракт. Всё, что ты проверил ДО вызова, к моменту записи могло устареть, поэтому объявляй примитиву, каким ты ВИДЕЛ цель, — он сверит это сам, вплотную к записи:
--expect-absentдля нового файла (публикация идёт атомарнымlinkat, занятое имя отвергает ядро) и--expect-sha256 <hex>для правки существующего (ключ — из ПРОЧИТАННЫХ байтов, не из размера и не из даты); дляpromote— карта--expect-from <json>вида{путь: sha256|absent}. ОтказE-expect-*значит, что файл правил кто-то ещё: не повторяй с--force, покажи расхождение PM.Исключение ровно одно, и оно названо, а не умолчано: legacy-силос
docs/architecture/DESIGN-NNN-<slug>/пишет/polisade:designсвоим Write-инструментом. Силос deprecated и переносится в корпус скриптомscripts/polisade_migrate_silo.py, а не развивается.
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 · +21 lines ef8d654b830b
- 8d ago First seen · 174 lines · 105 tokens per session scan A 745f40e9f208
spike is a skill published in the GitHub repository cryndoc/polisade-orchestrator (7 stars, last pushed today), licensed Apache-2.0. It adds 105 tokens to every session and 2,651 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 2026-08-31.
Other skills, from other repositories
deep-research-tiered
Deep research harness: fan-out search, fetch, adversarially verify, synthesize a cited report. Prefer Workflow({name:'deep-research-tiered', args:{question, models?}}) over built-in deep-research — same output, cheap tiered defaults (scope/search=sonnet, fetch=haiku, verify=sonnet, synthesize=inherit). Use for deep…
controllers-policy
Autonomy contract and routing index for autonomous project controllers. Loaded every tick; carries the rules that must survive cron-prompt rewrites.
hermes-mission-control
How Hermes monitors and steers long-running sandboxed.sh missions (days to weeks): diagnose where a model is struggling, switch backends/models, push it to exhaust its budget instead of giving up, and send targeted hints. Trigger terms: mission, sandboxed.sh, babysit, monitor, /goal, switch backend, stalled, resume…
open-dynamic-workflows
Plan, orchestrate, and adversarially verify parallel AI coding agents — a dynamic multi-agent workflow engine.
ultracode
Ultracode-style dynamic workflows for Antigravity. Use when the user says "ultracode", "workflow:", "/deep-research", or asks for broad multi-file work with planning, parallel agents, verification, or crash-resume.
orchestrator-boss
Boss skill for parallel worker orchestration. Analyze, split, delegate by outcome, judge by acceptance criteria, integrate. Do not implement directly.