Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add CaesiumY/dding-dong/plugin install dding-dongWrote 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/caesiumy/dding-dong/dd-feedback)<a href="https://agentmods.dev/skills/caesiumy/dding-dong/dd-feedback"><img src="https://agentmods.dev/badge/skills/caesiumy/dding-dong/dd-feedback.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00088 | $0.01779 |
| Opus 5 | $0.00044 | $0.00890 |
| Sonnet 5 | $0.00018 | $0.00356 |
| Haiku 4.5 | $0.00009 | $0.00178 |
Grade A, and why
dd-feedback 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 7d 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 — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.
dding-dong 피드백 제출
사용자의 피드백을 자연어로 받아 자동 분류하고 GitHub 이슈를 생성합니다.
1단계: 입력 수집
$ARGUMENTS가 비어있지 않으면 해당 텍스트를 피드백으로 사용합니다.
$ARGUMENTS가 비어있으면 사용자에게 질문합니다:
"dding-dong에 대한 피드백을 자유롭게 입력해주세요. (버그, 기능 요청, 질문 등 무엇이든 괜찮습니다)"
사용자의 응답을 피드백 텍스트로 사용합니다.
2단계: GitHub CLI 사전 검증
gh auth status 2>&1 && echo "GH_READY" || echo "GH_NOT_READY"
GH_NOT_READY인 경우 아래 메시지를 안내하고 종료합니다:
GitHub CLI(gh)가 설치되지 않았거나 인증되지 않았습니다.
피드백을 제출하려면:
1. gh CLI 설치: https://cli.github.com/
2. 인증: gh auth login
또는 직접 이슈를 작성해주세요:
https://github.com/CaesiumY/dding-dong/issues/new
3단계: 컨텍스트 수집
저장소 정보와 환경 정보를 한 번에 수집합니다:
node "${CLAUDE_PLUGIN_ROOT}/skills/dd-feedback/scripts/collect-context.mjs" --cwd "$(pwd)"
JSON 결과를 파싱하여 이후 단계에서 사용합니다:
repository: 대상 저장소 (예:CaesiumY/dding-dong).null이면 기본값CaesiumY/dding-dong사용.environment: 환경 정보 객체.error필드가 있으면 환경 정보를 "감지 불가"로 표시하고 계속 진행.
4단계: 자동 분류 및 구조화
1단계에서 수집한 피드백 텍스트를 분석하여 아래 항목을 결정합니다.
카테고리 판별
- 오류, 안 됨, 안 나옴, 깨짐, 실패, crash, error, fail, broken, not working →
bug - 추가, 지원, 있으면 좋겠, 제안, 개선, want, suggest, add, feature, improve →
enhancement - 어떻게, 왜, 방법, 질문, 궁금, how, why, question, what does →
question - 불확실하면 →
enhancement(기본값)
우선순위 추정
- 긴급, 심각, 전혀 안됨, 완전히, critical, urgent, blocker, completely broken →
high - 사소한, 미미한, 작은, cosmetic, minor, tiny, small →
low - 그 외 일반적 피드백 →
medium(기본값)
제목 생성
사용자 입력에서 핵심 문제 또는 요청을 한 줄로 요약합니다.
- 50자 이내
- 한국어/영어 모두 허용
- 이슈 제목으로 적합한 간결한 형태
이슈 본문 구성
버그 리포트 (bug) 본문:
## 설명
[사용자 입력을 구조화하여 정리]
## 재현 단계
[텍스트에서 재현 단계가 추출되면 기술, 없으면 "제공되지 않음"]
## 환경 정보
| 항목 | 값 |
|------|-----|
| 플랫폼 | {platform} |
| 오디오 플레이어 | {audioPlayer} |
| 알림 도구 | {notifier} |
| 사운드 팩 | {soundPack} |
| 볼륨 | {volume} |
| 언어 | {language} |
| Node.js | {nodeVersion} |
---
*이 이슈는 `/dding-dong:dd-feedback`을 통해 자동 생성되었습니다.*
기능 요청 (enhancement) / 질문 (question) 본문:
## 설명
[사용자 입력을 구조화하여 정리]
## 환경 정보
| 항목 | 값 |
|------|-----|
| 플랫폼 | {platform} |
| Node.js | {nodeVersion} |
---
*이 이슈는 `/dding-dong:dd-feedback`을 통해 자동 생성되었습니다.*
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 7d ago First seen · 212 lines · 88 tokens per session scan A 15a8e1428ec3
dd-feedback is a skill published in the GitHub repository CaesiumY/dding-dong (2 stars, last pushed 6mo ago), licensed MIT. It adds 88 tokens to every session and 1,779 once invoked, about $0.0004 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.
Other skills, from other repositories
schedule-edit
Edit a workhub schedule note (projects/ /schedules/.md) from a natural-language instruction — move or resize the bars, arrows, milestones and notes in ## Items, and adjust ## Non-working days. Use when asked to shift a phase, rebalance a plan, add or remove non-working days, or when the workhub app launches a schedule…
shared-space
Record and use a team knowledge base that lives outside the vault - a network drive, Google Drive, OneDrive or SharePoint folder. Survey mode reads the place and writes down how it is organised into projects/ /shared/; place mode says where a vault note belongs in it. Use when the user wants to register a team share…
vault-setup
Set up a machine to work with a workhub vault - check/install required software (git, Node.js, Claude Code, OpenCode), initialize the vault if needed, wire up Claude plugins, and run the OpenCode sync scripts. Use when onboarding a new machine, after a fresh vault-init, or when the harness feels half-configured.
create-work-log
A tool that turns Git activity from configured repositories into a daily or weekly work log in Markdown. Git is a system that records changes to code, including who made them and when.
manage-backlog
Add, refine, split, or reorder PBIs in the file-based product backlog in the team-shared folder. Use when the user wants to create backlog items, write user stories or acceptance criteria, estimate points, split oversized items, or tidy the product backlog.
plan-sprint
Plan a sprint - set the goal, commit backlog items into scope, and write the burndown baseline (scope.json). Use at a sprint boundary when the user wants to plan the next sprint or commit items to a sprint.