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 reconcile-docsgit 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/reconcile-docs)<a href="https://agentmods.dev/skills/cryndoc/polisade-orchestrator/reconcile-docs"><img src="https://agentmods.dev/badge/skills/cryndoc/polisade-orchestrator/reconcile-docs/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/reconcile-docs"><img src="https://agentmods.dev/badge/skills/cryndoc/polisade-orchestrator/reconcile-docs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 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 80 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 80 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.
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 | $0.00073 | $0.07736 |
| Opus 5.5 | $0.00029 | $0.03094 |
| Sonnet 5.5 | $0.00015 | $0.01547 |
| Haiku 4.5 | $0.00007 | $0.00774 |
Grade A, and why
reconcile-docs 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 17d 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 — 445 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/polisade:reconcile-docs [SPEC-XXX | DESIGN-XXX | <путь>] — сверка архитектура ↔ код (best-effort)
Показывает расхождения между тем, что утверждает архитектурный корпус
docs/architecture/, и тем, что видно в коде. Механическая часть —
разрешимость ссылок корпуса (scripts/polisade_reconcile.py anchors,
stdlib-only); сама сверка смысла — работа модели клиента на его токенах.
⚠️ ЧЕСТНАЯ РАМКА — прочитай и повтори пользователю в КАЖДОМ выводе
┌──────────────────────────────────────────────────────────┐
│ Это МНЕНИЕ модели о расхождениях, а НЕ вердикт. │
│ │
│ Корпус best-effort (провенанс INFERRED/GAP), код читает │
│ та же модель, и сверяет смысл она же. Ни гейтов, ни │
│ штампов, ни провенанса CONFIRMED здесь нет — и не │
│ появится оттого, что список выглядит строго. │
│ │
│ Детерминированной сверки «дизайн ↔ код» с провенансом │
│ и блокирующими гейтами эта команда не выполняет. │
└──────────────────────────────────────────────────────────┘
Что это значит на практике:
- пустой список расхождений = «модель ничего не заметила», а не «архитектура соответствует коду»;
- найденное расхождение = «стоит посмотреть», а не «доказано»: корпус мог устареть, код мог быть переименован, модель могла ошибиться в обе стороны;
- механическая часть (
anchors) проверяет разрешимость ССЫЛКИ — есть ли файл, существуют ли строки, встречается ли символ. Разрешившаяся ссылка ничего не говорит о верности утверждения; - сверки с гарантией здесь нет вовсе: оракул-валидированного провенанса, детерминированных гейтов целостности корпуса и блокирующей проверки эта команда не делает и делать не будет. Её выход — мнение модели со ссылками, которое читает человек.
⛔ Запрещено (класс F1 — «отказ способности подан как положительный факт»): подавать вывод как «дрейфа нет», «архитектура подтверждена», «сверка пройдена», рисовать штампы/галочки соответствия и вешать на вывод exit-код как вердикт. Пиши как есть: «модель заметила N расхождений (best-effort, не проверено)».
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.
- 17d ago Changed ae950325c445
- 18d ago Changed · -2 lines 370c12c882e6
- 1mo ago Changed · +3 lines 8c4eee80e8ef
- 1mo ago Changed · +102 lines 4ed854be2af6
- 1mo ago First seen · 342 lines · 73 tokens per session scan A a8078c8f4615
reconcile-docs is a skill published in the GitHub repository cryndoc/polisade-orchestrator (7 stars, last pushed 9d ago), licensed Apache-2.0. It adds 73 tokens to every session and 7,736 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
arrow-maintenance
Navigation and audit overlay for linked-intent development. Use when working with docs/arrows/ — orienting via index.yaml, auditing spec-to-code coherence, detecting reverse orphans and drift, splitting/merging/renaming/re-parenting segments. Dual-mode: ambient guidance when the overlay is present…
review-depth
Experimental declared review depth for linked-intent development. Use when a LID project's instruction file declares a review depth in prose (e.g. "Review depth - I review through LLD; below that, consolidate to one review") or the user asks to batch phase reviews, consolidate stops, or let go below a phase depth.…
bidirectional-differential
Audit coherence across an arrow of intent by running two parallel fresh Claude sessions — one reconstructs code from a single EARS, the other reconstructs the EARS from stripped code — then classifies the drift between them. Use when the user invokes /differential-audit, asks to audit EARS-to-code drift for a feature…
vanellus
Skill "vanellus" from markmhendrickson/ateles, covering vanellus — pr steward, identity, principals, core job and automated pr review (swarm-panel invocation).
check-work
Check your work with a verification subagent that reviews diffs, runs builds and tests, and evaluates correctness. Read this file for instructions. Use when asked to "check work", "verify changes", "self-verify", "/check-work", "/check", "/verify", or "/self-verify".
defect-hunting
Use when reviewing code, auditing an app, writing a guard rule or test, or certifying any threshold/constant/formula. Finds the defects a diff review structurally cannot see — the second write path, the mis-calibrated constant, the rule that cannot fail. Triggers from code-reviewer, /app-audit, qa-engineer…