An interactive procedure for answering project-manager questions that are holding up tasks. It reads the project's waiting list and handles responses such as supplying a pull-request URL, postponing the task, or cancelling it.

Use it when tasks are waiting for a product or project manager's answer, especially when a manually created pull request must be linked.

It shows which decisions are blocking work and records the chosen answer in the appropriate task state. This lets the workflow continue once the missing information is provided.

unblock — Skill for Claude Code and Codex by cryndoc

Install

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.

Any agent

npx skills add cryndoc/polisade-orchestrator --skill unblock

Clone the repo

git clone --depth 1 https://github.com/cryndoc/polisade-orchestrator

Made for: Claude Code, Codex.

Or install polisade, the plugin that ships this one along with the rest of its 25 skills, 2 commands.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/cryndoc/polisade-orchestrator/unblock/github.svg)](https://agentmods.dev/skills/cryndoc/polisade-orchestrator/unblock)

Your own site

<a href="https://agentmods.dev/skills/cryndoc/polisade-orchestrator/unblock"><img src="https://agentmods.dev/badge/skills/cryndoc/polisade-orchestrator/unblock/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/cryndoc/polisade-orchestrator/unblock"><img src="https://agentmods.dev/badge/skills/cryndoc/polisade-orchestrator/unblock.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 9 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,238 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00009	$0.01238
Opus 5	$0.00005	$0.00619
Sonnet 5	$0.00002	$0.00248
Haiku 4.5	$0.00001	$0.00124

Measured 9d ago against content hash ba237b9df0ae, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

unblock 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 9d 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.

skills/unblock/SKILL.md · 125 lines

How it starts

The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/polisade:unblock — Разблокировка задач

Интерактивная сессия для ответов на вопросы, которые ждут PM.

Алгоритм

Прочитай .state/PROJECT_STATE.json
Получи список waitingForPM
Если список пуст → "Нет вопросов, ждущих ответа. Всё разблокировано!"
Для каждого вопроса последовательно: a. Покажи контекст (какой артефакт, когда создан вопрос)

EARLY EXIT для pr_url_request (OPS-008): a'. Если текст вопроса содержит "pr_url_request" или "Создайте PR вручную" или "Create PR manually" (вопрос создан continue Phase C fallback): - Показать PM: "TASK-XXX ждёт URL вручную созданного PR. Ветка: <expected_branch>." - Варианты ответа: 1. Указать PR URL 2. Отложить (оставить waiting_pm) 3. Отменить задачу - Если PM предоставляет URL: - Валидация: URL содержит /pull/ или /merge-requests/ или аналог (если не проходит — спросить снова, не fallback на status=ready) - Записать в TASK frontmatter: pr_url: <url> (только frontmatter — НЕ в PROJECT_STATE.artifacts) - Удалить из waitingForPM - Добавить в inReview (НЕ readyToWork!) - Статус TASK остаётся review (НЕ ready!) - Вывод: "PR URL записан. /polisade:continue для resume quality review." - Перейти к следующему вопросу (skip шаги b–g) - Если PM говорит "отложить" → оставить waiting_pm (стандартный path) - Если PM говорит "отменить" → status=done cancelled (стандартный path)

EARLY EXIT для ARCHRUN (corpus-run resume, #187): a''. Если ID артефакта начинается с ARCHRUN- (corpus-run, ждёт ответа на вопрос /polisade:design-corpus: synonym-collision, FR-retirement, flow-ceiling, hash-конфликт preflight и т.п.): - Покажи PM процитированный вопрос из docs/architecture/runs/ARCHRUN-NNN.md + контекст из architecture.corpus.pendingRun. - Получи ответ; запиши его в ARCHRUN-NNN.md (раздел ответа). - Установи ARCHRUN-NNN.status = ready, удали из waitingForPM. - НЕ добавляй в readyToWork как обычный work-item и НЕ предлагай /polisade:implement. ARCHRUN.ready означает «resume required». Выведи: "ARCHRUN-NNN разблокирован. Запусти /polisade:design-corpus --resume=<runId> чтобы продолжить применение к корпусу со staging (повторный preflight hash-check)." runId — из architecture.corpus.pendingRun.runId. - Перейти к следующему вопросу (skip шаги b–g).

Read the full file on GitHub · 125 lines

Changes

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.

9d ago First seen · 125 lines · 9 tokens per session scan A ba237b9df0ae

Subscribe to this mod's changes

unblock is a skill published in the GitHub repository cryndoc/polisade-orchestrator (7 stars, last pushed today), licensed Apache-2.0. It adds 9 tokens to every session and 1,238 once invoked, about $0.0000 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.

Autonomous Agents Claude Code LLM Project management ai-agents claude-code-plugin developer-tools

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…

anshss/shiploop · 0 tokens

ungate-queue

Use when the user wants to work THROUGH the blocked items on a queue with you present — "unblock these", "walk me through what is gated", "let us clear the questions" — or immediately after an unattended run reports items it could not do. Turns each gate reason into the single question that would release the item…

haiggoh/run-to-completion · 132 tokens

autopilot

Use when the user asks to run a whole queue of open work unattended — "autopilot", "run everything you can", "clear what you can while I am away", "full auto on my open items". Orchestrates the complete run as an explicit checklist: triage the queue into tiers, execute the autonomous pile without stopping, then close…

haiggoh/run-to-completion · 97 tokens

unblock