What is iwe-bug-report?

A reporting skill for bugs in the IWE platform, the software system it supports. It creates a GitHub issue, a tracked report for a software problem, in the FMT-exocortex-template repository.

Reporting bugs, documentation errors, requested improvements, or unclear platform behavior with the relevant category.

It gives platform problems a structured place to be recorded instead of leaving them in conversation notes.

iwe-bug-report — Skill for Claude Code by TserenTserenov

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 TserenTserenov/FMT-exocortex-template --skill iwe-bug-report

Clone the repo

git clone --depth 1 https://github.com/TserenTserenov/FMT-exocortex-template

Made for: Claude Code.

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/tserentserenov/fmt-exocortex-template/iwe-bug-report/github.svg)](https://agentmods.dev/skills/tserentserenov/fmt-exocortex-template/iwe-bug-report)

Your own site

<a href="https://agentmods.dev/skills/tserentserenov/fmt-exocortex-template/iwe-bug-report"><img src="https://agentmods.dev/badge/skills/tserentserenov/fmt-exocortex-template/iwe-bug-report/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/tserentserenov/fmt-exocortex-template/iwe-bug-report"><img src="https://agentmods.dev/badge/skills/tserentserenov/fmt-exocortex-template/iwe-bug-report.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,227 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. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

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	$0.00033	$0.01227
Opus 5.5	$0.00013	$0.00491
Sonnet 5.5	$0.00007	$0.00245
Haiku 4.5	$0.00003	$0.00123

Measured 27d ago against content hash a8aa70a95a89, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

iwe-bug-report 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 27d 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.

.claude/skills/iwe-bug-report/SKILL.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Отчёт об ошибке платформы IWE

Проблема: $ARGUMENTS

When to use

Сообщить об ошибке или проблеме платформы IWE. Создаёт GitHub issue в FMT-exocortex-template.

Algorithm

Шаг 0. Проверка на запрос справки (issue #274)

Если $ARGUMENTS пуст, отсутствует, или равен --help/-h/help — НЕ создавать issue. Вместо этого вывести:

«/iwe-bug-report [описание проблемы] — сообщает об ошибке платформы IWE, создаёт GitHub issue в FMT-exocortex-template. Опиши, что произошло и что ожидалось, например: /iwe-bug-report day-close не архивирует DayPlan.»

Прекратить выполнение.

Шаг 1. Категоризация

Определи категорию по содержанию $ARGUMENTS:

Метка	Когда
`bug`	Скилл / протокол / скрипт работает не так, как задумано
`documentation`	Неточность или пробел в документации / memory / SKILL.md
`enhancement`	Улучшение существующего поведения (не новый функционал)
`question`	Поведение непонятно, нужно уточнение

Шаг 2. Сбор деталей

Извлеки из $ARGUMENTS и контекста сессии:

Что произошло: конкретное наблюдаемое поведение
Что ожидалось: правильное поведение по протоколу
Шаги воспроизведения: команда / скилл / триггер (если применимо)
Где: путь к скиллу / протоколу / скрипту или имя файла

Если какой-либо элемент не указан — пропусти соответствующий блок в issue (не оставляй пустые заголовки).

Шаг 3. Получить версию IWE

Запусти:

git -C "${IWE_WORKSPACE:-$HOME/IWE}/FMT-exocortex-template" log -1 --format="%h %ad" --date=short 2>/dev/null || echo "неизвестно"

Шаг 4. Проверить gh CLI

Запусти:

gh auth status 2>&1 | head -3

Если gh не авторизован или не установлен — выведи сообщение:

«gh CLI не найден или не авторизован. Установи (macOS: brew install gh; Linux: apt install gh или https://cli.github.com/), затем gh auth login. Issue не создан.» Прекрати выполнение.

Шаг 5. Создать issue

Собери переменные:

TITLE: до 80 символов, формат [ТИП] Краткое описание
CATEGORY: метка из шага 1
DATE: сегодняшняя дата (YYYY-MM-DD)
IWE_VERSION: из шага 3

Read the full file on GitHub · 136 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.

27d ago Changed a8aa70a95a89
2mo ago Changed · +1 lines 9ac44b9799e5
2mo ago First seen · 135 lines · 33 tokens per session scan A 627aa06118e3

Subscribe to this mod's changes

iwe-bug-report is a skill published in the GitHub repository TserenTserenov/FMT-exocortex-template (63 stars, last pushed today), licensed MIT. It adds 33 tokens to every session and 1,227 once invoked, about $0.0001 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 2026-08-30.

Claude Code Debugging agentic-workflows ai-agents ai-second-brain anthropic-claude claude-plugin

iwe-bug-report next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
iwe-bug-reportTserenTserenov/FMT-exocortex-template	Skill	63	today	MIT	A	33	Claude Code
team-management-debuggingTeamManagementPlugin/claude-plugin	Skill	6	25d ago	MIT	A	95	Claude Code, Codex
debugging-pipelineszpower426/datapowers	Skill	1	7mo ago	MIT	A	34	Claude Code
agenticx-agent-obsDemonDamon/AgenticX	Skill	1.0k	today	Apache-2.0	A	89	Claude Code, Codex
openlore-debugclay-good/OpenLore	Skill	358	today	MIT	A	39	Claude Code, Codex
five-whyswesammustafa/Claude-Code-Everything-You-Need-to-Know	Skill	3.6k	3d ago	none	A	53	Claude Code
ci-debugyonatangross/orchestkit	Skill	300	today	MIT	A	55	Claude Code