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 design-corpusgit 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/design-corpus)<a href="https://agentmods.dev/skills/cryndoc/polisade-orchestrator/design-corpus"><img src="https://agentmods.dev/badge/skills/cryndoc/polisade-orchestrator/design-corpus/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/cryndoc/polisade-orchestrator/design-corpus"><img src="https://agentmods.dev/badge/skills/cryndoc/polisade-orchestrator/design-corpus.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 findings, up to high
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 →
- high Prompt Injection · line 52 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- high Prompt Injection · line 52 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- 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 240 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 | $0.00166 | $0.12017 |
| Opus 5 | $0.00083 | $0.06008 |
| Sonnet 5 | $0.00033 | $0.02403 |
| Haiku 4.5 | $0.00017 | $0.01202 |
Grade A, and why
design-corpus 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 2d 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 — 594 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/polisade:design-corpus [SPEC-XXX] — живой архитектурный корпус (experimental, Claude-only)
Применяет инкремент одной SPEC к единому живому корпусу docs/architecture/
вместо изолированного пакета DESIGN-NNN-<slug>/ на каждую SPEC. Организующий
принцип — docs как event-sourcing: SPEC = immutable commit (дельта
требований), корпус = working tree (одно живое состояние). C4-уровни L1/L2,
glossary и доменная модель описывают систему целиком и фиксируются один раз;
каждая SPEC добавляет тонкий changeset.yaml + ADR + trace-рёбра, не дублируя
системный слой.
EXPERIMENTAL / Claude-only. Скилл помечен
claude_only: trueи исключён из qwen/gigacode/opencode-сборок (он рассчитан на сильную модель)./polisade:design(per-SPEC силос) не затронут — это отдельный production-путь для слабых моделей.
Экспериментальный гейт — ВЫПОЛНИ ПЕРВЫМ, до любого IO
-
Прочитай
.state/PROJECT_STATE.json. -
Возьми
settings.experimental.designCorpus(канонически здесь;.claude/settings.json— это permissions, его НЕ читаем и НЕ трогаем). -
Если ключа нет или он
false— объясни PM, что это экспериментальный opt-in режим, и покажи как включить (в.state/PROJECT_STATE.json):settings.experimental.designCorpus: true.Выйди без единой записи. Production-путь per-SPEC силоса —
/polisade:design. -
Только если
true— продолжай.⛔ Скажи ГРОМКО, до применения (класс F1 — отсутствие гарантии запрещено подавать как положительный факт), дословно:
⚠️ BEST-EFFORT CORPUS — мерж БЕЗ защиты корпуса. корпус строится best-effort, без гарантий полноты и без гейтов — провенанс
INFERRED/GAP,CONFIRMED— никогда; и атомарности применения нет: упорядоченная запись staging → формат-линт → промоция, не транзакция. Атомарен КАЖДЫЙ ФАЙЛ (полузаписанных файлов не бывает), но не набор: обрыв между файлами оставляет корпус смешанным — он будет обнаружен и откатывается одной командой, но это не транзакция.
What ships with it
8 files 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.
- 2d ago Changed · +60 lines c8e7a8470b5f
- 10d ago First seen · 534 lines · 166 tokens per session scan A a08678028c67
design-corpus is a skill published in the GitHub repository cryndoc/polisade-orchestrator (7 stars, last pushed today), licensed Apache-2.0. It adds 166 tokens to every session and 12,017 once invoked, about $0.0008 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…
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…
controllers-policy
Autonomy contract and routing index for autonomous project controllers. Loaded every tick; carries the rules that must survive cron-prompt rewrites.
shiploop
Self-improving multi-agent harness: wraps N git sub-repos as one workspace, dispatches named tickets to cheap-floor headless agents that escalate once on failure, promoting lessons into CLAUDE.md. Use when working in or scaffolding a meta-repo workspace (sub-folders each own .git; root has scripts/ + queue/tickets.md…
orchestrator-boss
Boss skill for parallel worker orchestration. Analyze, split, delegate by outcome, judge by acceptance criteria, integrate. Do not implement directly.
open-dynamic-workflows
Plan, orchestrate, and adversarially verify parallel AI coding agents — a dynamic multi-agent workflow engine.