collab-feedback-loop

collab-feedback-loop is a skill for Claude Code from modu-ai/moai-cowork. It costs 127 tokens per session (1,891 once invoked), scanned A, original, Apache-2.0.

A guide for giving and receiving workplace feedback about specific actions and their effects.

In plain words
What is it for?
Use it to prepare constructive feedback, respond to negative feedback, ask for a progress review, or structure a conversation with the situation-behavior-impact method.
Why use it?
It helps keep feedback from sounding like a personal attack and helps the recipient separate useful facts from hurt feelings or unfair criticism.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the moai-coworker plugin — 32 skills shipped together

Good fit Use it to prepare constructive feedback, respond to negative feedback, ask for a progress review, or structure a conversation with the situation-behavior-impact method.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/modu-ai/moai-cowork/collab-feedback-loop
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 modu-ai/moai-cowork --skill collab-feedback-loop
Clone the repo
git clone --depth 1 https://github.com/modu-ai/moai-cowork

Made for: Claude Code.

Or install moai-coworker, the plugin that ships this one along with the rest of its 32 skills.

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 collab-feedback-loop

README.md
[![agentmods](https://agentmods.dev/badge/skills/modu-ai/moai-cowork/collab-feedback-loop/github.svg)](https://agentmods.dev/skills/modu-ai/moai-cowork/collab-feedback-loop)
Your own site
<a href="https://agentmods.dev/skills/modu-ai/moai-cowork/collab-feedback-loop"><img src="https://agentmods.dev/badge/skills/modu-ai/moai-cowork/collab-feedback-loop/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.

agentmods 80×15 button for collab-feedback-loop

Your own site · 80×15
<a href="https://agentmods.dev/skills/modu-ai/moai-cowork/collab-feedback-loop"><img src="https://agentmods.dev/badge/skills/modu-ai/moai-cowork/collab-feedback-loop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 127 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,891 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00127 $0.01891
Opus 5 $0.00063 $0.00945
Sonnet 5 $0.00025 $0.00378
Haiku 4.5 $0.00013 $0.00189

Measured 9d ago against content hash 2c851ec01a91, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

collab-feedback-loop 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.

plugins/moai-coworker/skills/collab-feedback-loop/SKILL.md · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

피드백 주고받기 (Feedback Loop)

개요

피드백은 어렵다. 주는 사람은 관계가 상할까 봐 돌려 말하다 메시지가 흐려지고, 받는 사람은 인격 공격으로 받아들여 방어부터 한다. 이 스킬은 피드백을 사람이 아니라 행동·사안에 고정하는 구조(SBI)를 제공하고, 받은 피드백에서 감정과 사실을 분리해 배울 것만 건지는 법을 돕는다. 회피하지 않고, 깨지지도 않게.

트리거 키워드

피드백, 피드백 주는 법, 피드백 받기, 부정적 피드백, 건설적 피드백, 쓴소리, 피드백 회피, 중간 보고, 중간 피드백, SBI, 피드백 소화

워크플로우

1단계: 피드백의 목적 정하기

비난과 피드백은 다르다. 피드백은 상대가 더 잘하도록 돕는 것이지 화풀이가 아니다.

  • 주기 전 자문: "이 말로 상대가 무엇을 바꾸길 바라는가?" 답이 없으면 그건 감정 배설이다.
  • 받을 때 전제: "이 안에 내가 쓸 수 있는 게 한 조각이라도 있나?"
  • 칭찬 피드백도 똑같이 구체적으로 — "잘했어" 대신 "어디가 왜 좋았는지"

2단계: SBI 구조로 전달하기 (주는 쪽)

행동을 사람에서 떼어내는 3단 구조다.

단계 내용 예시
S (상황) 언제·어디서 "어제 고객 미팅에서"
B (행동) 관찰한 사실(해석 빼고) "발표 중 자료를 미리 안 띄워서 5분 지연됐어요"
I (영향) 그 행동이 미친 결과 "고객이 준비가 덜 됐다고 느낀 것 같아요"

→ "당신은 항상 준비가 부족해" 같은 인격·일반화는 금지. 사실 → 영향만 말하고, 개선은 함께 찾는다.

3단계: 받은 피드백 소화하기 (받는 쪽)

부정적 피드백이 오면 본능은 방어다. 그 사이에 한 박자를 둔다.

  1. 즉답 대신 멈춤: "피드백 고마워요, 정리해서 다시 말씀드릴게요"로 시간 확보
  2. 감정 ↔ 사실 분리: 기분 나쁜 것과 내용이 맞는지는 별개로 본다
  3. 하나만 건지기: 전부 맞을 필요 없다. 쓸 수 있는 한 조각만 골라 행동으로 바꾼다
  4. 출처 가중치: 신뢰하는 사람·반복되는 피드백은 무겁게, 일회성·악의는 가볍게

→ 피드백은 나에 대한 최종 판결이 아니라 한 시점의 한 관점이다.

4단계: 먼저 피드백 요청하기

피드백을 기다리지 말고 먼저 구하면 작게·자주 받을 수 있다(중간 보고).

  • 구체적으로 묻기: "어땠어요?"(막연) 대신 "이 보고서에서 논리가 약한 부분이 있을까요?"
  • 타이밍 잡기: 완성 전 초안 단계에서 — 다 만든 뒤보다 고치기 쉽다
  • "나 일하고 있어요" 신호: 진행 중 중간 공유는 신뢰를 쌓고 막판 사고를 막는다

5단계: 피드백을 행동으로 닫기

받았으면 닫아야 다음 피드백이 온다.

  • 받은 피드백 중 바꿀 1~2가지를 정해 실제로 적용
  • 피드백 준 사람에게 반영 결과를 짧게 공유 — "지난번 말씀 반영해서 이렇게 바꿨어요"
  • 이 닫는 루프가 "이 사람은 피드백을 받는 사람"이라는 신뢰를 만든다

사용 예시

예시 1: "후배가 자꾸 마감을 놓치는데 어떻게 말해야 기분 안 상하게 전달할까?" → SBI 구조(상황·행동·영향) → 인격 표현 제거 → 개선책을 함께 찾는 질문형 마무리

예시 2: "상사한테 일 못한다는 피드백 받고 너무 속상해" → 감정·사실 분리 → 반복·신뢰 출처인지 가중치 판단 → 쓸 수 있는 1조각 + 행동 전환안

예시 3: "프로젝트 중간에 피드백을 미리 받고 싶은데 어떻게 요청하지?" → 구체적 질문 설계 → 초안 단계 타이밍 → 중간 보고 메시지 템플릿

산출물

  • SBI 기반 피드백 스크립트(상황·행동·영향)
  • 받은 피드백 소화 체크리스트(감정/사실 분리·가중치)
  • 피드백 요청 질문 + 중간 보고 메시지 템플릿
  • 반영 결과 공유 멘트

주의사항

  • 부정적 피드백은 1:1로, 즉시·짧게. 공개 자리에서의 지적은 메시지보다 모욕으로 남는다.
  • 받은 피드백을 전부 수용할 필요는 없다. 단, 반복되는 피드백은 신호일 가능성이 높다.
  • 피드백을 "돌려 말하기"로 부드럽게 하려다 핵심이 사라지면 안 준 것과 같다.

Read the full file on GitHub · 116 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. 9d ago First seen · 116 lines · 127 tokens per session scan A 2c851ec01a91

Subscribe to this mod's changes

collab-feedback-loop is a skill published in the GitHub repository modu-ai/moai-cowork (298 stars, last pushed 5d ago), licensed Apache-2.0. It adds 127 tokens to every session and 1,891 once invoked, about $0.0006 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 2026-08-30.

Related

Other skills, from other repositories

agentic-os-obsidian

Set up an agentic OS inside an Obsidian vault — a configurable command-center dashboard with 5 auto-installed, bundled plugins (Dataview, CustomJS, Shell-commands, Terminal, Homepage), Home + per-profile + Vault Overview pages, KPI cards, sparklines, heatmap, task rollup, and a button bar wired to user-defined Claude…

naveedharri/benai-skills · 154 tokens

operator

Build and schedule a personalized Operator prompt that runs a Baalda vault as a second brain on a recurring cadence. Run it from inside the vault: it reads Context/ and CLAUDE.md first to infer org, team, brand voice and paths, then asks only the gaps (cadence, connectors, DM recipient, budgets, signature), writes the…

naveedharri/benai-skills · 156 tokens

marketing-os-setup

Set up a Marketing OS: a markdown second brain that becomes the single source of truth every marketing skill reads, plus the routines that keep it current and a control-center dashboard on top. Interview-driven and idempotent, safe to re-run. Builds seven knowledge folders (Context, Channels, Campaigns, Offers…

naveedharri/benai-skills · 200 tokens

os-operator

Build and schedule a personalized Operator prompt that runs the user's second brain on a recurring cadence. The skill is invoked from inside the vault folder locally — it reads Context/ and CLAUDE.md first to infer org, team, brand voice, and paths, then asks ONLY the gaps it can't determine (cadence, connectors, DM…

naveedharri/benai-skills · 192 tokens

cloud-os-builder

Set up a Cloud OS — your second brain hosted either in a synced cloud folder (Google Drive, OneDrive, iCloud, Dropbox) or as a Notion workspace. Asks where to host it, then takes the matching route: for a folder it builds the Local OS structure (root CLAUDE.md + Context + Projects/Intelligence/Daily/Resources/Skills…

naveedharri/benai-skills · 0 tokens

local-os-builder

Set up a Local OS — bootstrap a local Obsidian vault as your second brain and run personalized onboarding. Creates all directories, system files, Obsidian config, memory system, hooks, and output styles, then interviews the user to personalize everything. Two modes — Solopreneurs/Professionals (default)…

naveedharri/benai-skills · 124 tokens