A skill for continuing ready development tasks through a required workflow: implementation, regression testing, pull request creation, review, and merge. Regression testing means rerunning the project's tests to catch unintended breakage.

Use it to find tasks ready for work and carry them through coding, testing, review, and merging.

It keeps unfinished tasks moving and prevents them from being marked complete before the required development steps are done.

continue — Skill for Claude Code by cryndoc/polisade-orchestrator

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 continue

Clone the repo

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

Made for: Claude Code.

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/continue/github.svg)](https://agentmods.dev/skills/cryndoc/polisade-orchestrator/continue)

Your own site

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

Per session 11 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 13,375 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

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 Tool Misuse · line 314
Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
high Tool Misuse · line 314
Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
medium analysis-evasion · line 1
Suspicious Unicode normalization or mixed-script content

Fix: Review the flagged content for security risks. Ensure no credentials, secrets, or sensitive data are exposed.

How audits are shown

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	$0.00011	$0.13375
Opus 5.5	$0.00004	$0.05350
Sonnet 5.5	$0.00002	$0.02675
Haiku 4.5	$0.00001	$0.01337

Measured 3d ago against content hash 110c92c806f8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

continue 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.

> Bare `git push` запрещён (push обязан проверяться сравнением remote SHA — OPS-028); самодельные REST/curl-вызовы к Bitbucket/GitHub запрещены; helper не транскрибируется в `/tmp`.

skills/continue/SKILL.md · 850 lines

How it starts

The opening of the file, as written. The whole thing — 850 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/polisade:continue — Автономная работа

Найти готовые к работе артефакты и выполнять их автономно.

⛔ КРИТИЧЕСКИ ВАЖНО: Полный цикл обязателен!

┌─────────────────────────────────────────────────────────────┐
│  ⛔ ЗАПРЕЩЕНО ставить status: done если:                    │
│                                                             │
│     ✗ Regression tests НЕ прогнаны                          │
│     ✗ PR НЕ создан                                          │
│     ✗ Review НЕ пройден                                     │
│     ✗ Merge НЕ выполнен                                     │
│                                                             │
│  После написания кода статус: in_progress                   │
│  После создания PR статус: review                           │
│  После merge PR статус: done                                │
└─────────────────────────────────────────────────────────────┘

Каждая TASK, выбранная для реализации, проходит ПОЛНЫЙ ЦИКЛ:

1. IMPLEMENT    → код + unit tests + commit      → статус: in_progress
2. REGRESSION   → запуск ВСЕХ тестов проекта     → исправить если упали
3. CREATE PR    → push + pr-create (polisade_vcs.py)  → статус: review
4. REVIEW LOOP  → ждать/исправлять               → повторять до approve
5. MERGE        → pr-merge --task + delete-branch → статус: done пишет pr-merge (exit 0; иначе waiting_pm)

НЕ ПЕРЕХОДИ к следующей TASK пока текущая не завершена полностью или PM явно не отменил её с причиной. cancelled закрывает отменённую работу без PR, а not_actual закрывает отклонённый BUG без исправления. Оба исхода требуют status_reason и не считаются done; TASK с depends_on: на такой исход ждёт явного решения PM.

Использование

/polisade:continue    # Начать автономную работу

Алгоритм

⛔ Если вызов скрипта на этом шаге ты СДЕЛАЛ, и он 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. Вызова не было — отказа нет: сначала выполни команду; этот блок описывает её вывод и сам ответом не служит. 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 /tmp или 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 назови следствие: без рабочего вызова скрипта этот шаг выполнить нечем. Причину не придумывай — её называет только сам текст отказа.

Read the full file on GitHub · 850 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.

3d ago Changed 110c92c806f8
8d ago Changed · +59 lines 792b84dc914c
9d ago Changed · +23 lines 96fb02b0a759
11d ago Changed · +42 lines 4a47d54ca859
12d ago Changed · +25 lines e0c04c483b88
1mo ago Changed · +40 lines 3bf8ee981e85
1mo ago First seen · 661 lines · 11 tokens per session scan A f016cfbd78eb

Subscribe to this mod's changes

continue is a skill published in the GitHub repository cryndoc/polisade-orchestrator (7 stars, last pushed 4d ago), licensed Apache-2.0. It adds 11 tokens to every session and 13,375 once invoked, about $0.0000 per session on Opus 5.5. 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.

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

lanius

Skill "lanius" from markmhendrickson/ateles, covering lanius — github workflow coordinator, identity, principals, core job and workflow phases (feature issues).

markmhendrickson/ateles · 0 tokens

orchestrate-issues

Drive a whole graph of GitHub issues to completion using background subagents. Queries the unblocked frontier through native GitHub issue dependencies, dispatches one implementer per ready issue into an isolated worktree, runs a spec-review agent against the result, lands the PR, then re-queries as each merge opens…

aj604/toolshed · 209 tokens

continue