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/cryndoc/polisade-orchestrator/implementnpx skills add cryndoc/polisade-orchestrator --skill implementgit 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/implement)<a href="https://agentmods.dev/skills/cryndoc/polisade-orchestrator/implement"><img src="https://agentmods.dev/badge/skills/cryndoc/polisade-orchestrator/implement.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 | $0.00004 | $0.32306 |
| Opus 5 | $0.00002 | $0.16153 |
| Sonnet 5 | $0.00001 | $0.06461 |
| Haiku 4.5 | $0.00000 | $0.03231 |
Grade A, and why
implement scanned grade A with 1 finding 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 3d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- автоматический merge PR через любой VCS CLI/API (`polisade_vcs.py pr-merge`, `gh`, curl к Bitbucket) How it starts
The opening of the file, as written. The whole thing — 2,478 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/polisade:implement [TASK-XXX] — Реализация через субагент
Автономная реализация задачи через изолированный субагент с чистым контекстом.
ВАЖНО: /polisade:implement принимает ТОЛЬКО TASK-XXX. Для BUG/DEBT/CHORE автоматически создаётся TASK.
⛔ ARCHRUN-NNN (corpus-run, #187) НЕ реализуется — даже если он попал в
readyToWork после /polisade:unblock. Это не work-item: ARCHRUN.ready
означает «resume required». Если PM передал ARCHRUN-XXX или он оказался
ready-кандидатом — пропусти его и сообщи: «ARCHRUN-XXX — corpus-run;
продолжи через /polisade:design-corpus --resume=<runId>, не через implement».
⛔ КРИТИЧЕСКИ ВАЖНО: Merge выполняет ТОЛЬКО PM!
┌─────────────────────────────────────────────────────────────┐
│ ⛔ /polisade:implement НИКОГДА не мержит PR автоматически! │
│ │
│ После написания кода статус: in_progress │
│ После создания PR статус: review │
│ После успешного review → статус остаётся: review │
│ Merge и статус done → ответственность PM │
└─────────────────────────────────────────────────────────────┘
Полный цикл /polisade:implement:
LOCALIZE → КОД → ТЕСТЫ → PR → REVIEW → STOP
↑ ↑ ↑
│ └── статус in_progress └── PR готов, ждём PM для merge
└── детерминированный grep-протокол (термины → символы → ссылки),
артефакт целей до правок
⛔ ЗАПРЕЩЁННЫЕ git-команды в /polisade:implement
/polisade:implement РАБОТАЕТ ТОЛЬКО в рамках feature-ветки. Следующие
действия ЗАПРЕЩЕНЫ в любой момент жизненного цикла команды —
до и после успешного self-review, при первом и при повторном вызове,
в основном агенте и в субагенте:
git checkout main/git checkout master/git switch maingit push origin main/git push origin master/git push --forceв maingit merge <feature>/git rebase <feature>onto maingit branch -D <feature>/git branch --delete <feature>git push origin --delete <feature>/git push origin :<feature>- автоматический merge PR через любой VCS CLI/API (
polisade_vcs.py pr-merge,gh, curl к Bitbucket) git commit/git add/git pushсcurrent_branch ≠ compute_expected_branch(TASK)(main/master/develop — частный случай: если видишьOn branch mainи собираешься коммитить, это ЯВНЫЙ БАГ OPS-001 — не продолжай, останавливайся, верни blocked)- ⛔ NEVER
git add -f <path>/git add --force <path>на gitignored путях (.gigacode/,.qwen/,.codex/,.worktrees/и любые другие). Разрешено только при явной просьбе PM «добавить принудительно». Фраза «закоммить всё кроме X» — это ИСКЛЮЧЕНИЕ пути X, а НЕ команда его форсить. Исключение по.claude/— только файл.claude/settings.json(коммитится), директория.claude/целиком — НЕТ.
What ships with it
1 file 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.
- 3d ago First seen · 2,478 lines · 4 tokens per session scan A 1ee4b5fb173d
implement is a skill published in the GitHub repository cryndoc/polisade-orchestrator (7 stars, last pushed 8d ago), licensed Apache-2.0. It adds 4 tokens to every session and 32,306 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
hive.chart-creation-foundations
Required reading whenever any chart tool is available. Teaches the one-tool embedding contract (call chartrender → live chart appears in chat AND a downloadable PNG lands in the queen session dir), the ECharts (data viz) vs Mermaid (structural diagrams) decision, the BI/financial-grade aesthetic baseline (no…
browser-edge-cases
SOP for debugging browser automation failures on complex websites. Use when browser tools fail on specific sites like LinkedIn, Twitter/X, SPAs, or sites with Shadow DOM.
openai-whisper-api
Transcribe audio via OpenAI Audio Transcriptions API (Whisper).
chat-complex-documents
Chat with and search your complex documents — ask questions, extract tables and fields, and get answers grounded in the source. Connects the hosted Unstructured Transform MCP server to parse, structure, and enrich PDFs, Word/Excel/PowerPoint, images, scanned files, emails, and 60+ other formats into clean, AI-ready…
agentic-loop-skill
Autonomous decision loop with reflection and iteration.
perf-code-paths
Use when mapping code paths, entrypoints, and likely hot files before profiling.