defect

defect is a skill for Claude Code, Codex from cryndoc/polisade-orchestrator. It costs 109 tokens per session (1,453 once invoked), scanned A, original, Apache-2.0.

A command for registering a software defect, meaning behavior that does not work as intended, and creating a task to fix it. The defect and its fix task receive tracked IDs and are stored in the project's backlog and task folders.

In plain words
What is it for?
Use it to report issues such as broken mobile buttons or server errors when loading large files. It creates both the bug record and the linked implementation task.
Why use it?
It puts a bug into the normal implementation and review process instead of leaving it as an informal note. Checks for duplicate IDs and conflicting files help prevent records from being overwritten.

Skill for Claude CodeCodex

Part of the polisade plugin — 27 skills, 2 commands shipped together

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.

agentmods
npx agentmods add skills/cryndoc/polisade-orchestrator/defect
Any agent
npx skills add cryndoc/polisade-orchestrator --skill defect
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 27 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.

agentmods badge for defect

README.md
[![agentmods](https://agentmods.dev/badge/skills/cryndoc/polisade-orchestrator/defect.svg)](https://agentmods.dev/skills/cryndoc/polisade-orchestrator/defect)
Your own site
<a href="https://agentmods.dev/skills/cryndoc/polisade-orchestrator/defect"><img src="https://agentmods.dev/badge/skills/cryndoc/polisade-orchestrator/defect.svg" alt="Measured on agentmods" height="20"></a>
Per session 109 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,453 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00109 $0.01453
Opus 5 $0.00055 $0.00727
Sonnet 5 $0.00022 $0.00291
Haiku 4.5 $0.00011 $0.00145

Measured 5d ago against content hash 5ed44a293354, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

defect 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 5d 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/defect/SKILL.md · 181 lines

How it starts

The opening of the file, as written. The whole thing — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/polisade:defect [описание] — Добавить баг

Быстрое добавление бага с автоматическим созданием TASK для исправления.

Использование

/polisade:defect Кнопка не работает на мобильных
/polisade:defect Ошибка 500 при загрузке большого файла

Алгоритм

  1. Вычисли next-id для BUG и TASK по протоколу из skills/tasks/references/compute-next-id.md (единый max по .state/counters.json, PROJECT_STATE.artifactIndex и file-scan). При Counter drift — АБОРТ с рекомендацией python3 {plugin_root}/scripts/polisade_sync.py . --apply --yes.

  2. Write-guard. Перед Write проверь, что backlog/bugs/BUG-{N}-slug.md и tasks/TASK-{N}-slug.md не существуют и что ключей BUG-{N} / TASK-{N} нет в state.artifactIndex. При коллизии — АБОРТ.

  3. Создай файл backlog/bugs/BUG-XXX-slug.md

  4. Автоматически создай tasks/TASK-XXX-slug.md со ссылкой на BUG (парный write-guard: проверка применяется к обоим файлам перед IO).

    КРИТИЧНО: TASK-файл ДОЛЖЕН быть ровно tasks/TASK-XXX-*.md в корневой папке tasks/. НЕ в docs/tasks/, НЕ в docs/TASK-*.md, НЕ в backlog/tasks/. /polisade:implement ищет таски ТОЛЬКО в корневой tasks/. Если папки нет — mkdir -p tasks.

  5. Спроси краткие уточнения (если нужно):

    • "Как воспроизвести?"
    • "Критичность: блокер / серьёзный / мелкий?"
  6. Инкрементируй счётчики BUG и TASK (counters.json[BUG] = N_bug, counters.json[TASK] = N_task).

  7. Обнови .state/PROJECT_STATE.json:

    • Добавь BUG со статусом ready
    • Добавь TASK со статусом ready в readyToWork
  8. Выведи подтверждение

Автоматическое создание TASK

ВАЖНО: Баг автоматически создаёт связанную TASK:

/polisade:defect Кнопка не работает на мобильных

Создаёт:
1. backlog/bugs/BUG-001-mobile-button.md (status: ready)
2. tasks/TASK-001-fix-mobile-button.md (status: ready, parent: BUG-001)

Это гарантирует единый workflow: /polisade:implement работает только с TASK.

Шаблон файла BUG

---
id: BUG-XXX
title: "[Описание]"
status: ready
created: YYYY-MM-DD
priority: P1
severity: medium  # blocker | critical | major | minor
task: TASK-XXX  # Связанная задача
---

# Bug: [Описание]

## Описание проблемы

[Описание из команды]

## Как воспроизвести

1. [Шаг 1]
2. [Шаг 2]
3. [Результат]

## Ожидаемое поведение

[Как должно работать]

## Фактическое поведение

[Что происходит]

## Окружение

- Браузер/платформа:
- Версия:

## Возможная причина

[Если очевидно]

## Критерии исправления

- [ ] Баг не воспроизводится
- [ ] Тест добавлен

Read the full file on GitHub · 181 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.

  1. 5d ago First seen · 181 lines · 109 tokens per session scan A 5ed44a293354

Subscribe to this mod's changes

defect is a skill published in the GitHub repository cryndoc/polisade-orchestrator (7 stars, last pushed 9d ago), licensed Apache-2.0. It adds 109 tokens to every session and 1,453 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

deep-execution

Executes agent-enhanced council queries as one Workflow of parallel Claude analyst agents that each query a provider, evaluate response quality, ask follow-up questions, and return a schema-enforced analysis with confidence ratings and blind spot analysis. Invoked when the --agents flag is used or when complex…

hex/claude-council · 66 tokens

update-lid

Configure or reconcile a project for linked-intent development (LID). Dispatches on project state — fresh bootstrap, append directives to an existing agent-instructions file (AGENTS.md or CLAUDE.md), add missing mode marker, reconcile convention drift, or run mode transitions. Invoked as /update-lid. For fresh…

jszmajda/lid · 105 tokens

matryca-github

Apply Matryca maintainer standards for GitHub issues, pull requests, branches, reviews, merges, milestones, tags, releases, and remote comments. Use before any GitHub-facing action or artifact.

MarcoPorcellato/matryca-plumber · 47 tokens

matryca-logseq-io

Choose safe direct-file versus Local HTTP API access for Logseq. Use when changing graph reads, writes, background indexing, live Logseq integration, authentication, or JSON-RPC communication.

MarcoPorcellato/matryca-plumber · 45 tokens

sflo

Starts and manages SFLO factory runs through the configured runner. Use when the user explicitly asks to start, run, resume, list, kill, clean, or inspect an SFLO factory, including requests to build something with SFLO. Do not use when SFLO appears only in quoted text, documentation, examples, code, logs, or…

simonasrazm/simon-factory-lights-out · 74 tokens

map-codebase

Bootstrap LID in an existing (brownfield) codebase. Deep-reads every file in the declared scope, offers lens-based clustering options, generates skeleton LLDs/HLD/EARS bottom-up, then creates arrow docs and prompts the user to flesh out the skeletons. Token-intensive by design. Use when asked to map a codebase…

jszmajda/lid · 92 tokens