feedback-draft

feedback-draft is a skill for Claude Code from kenshikobayashi/everything-claude-code-for-business. It costs 14 tokens per session (418 once invoked), scanned A, original, MIT.

A feedback-writing guide based on SBI: Situation, Behavior, and Impact. It turns observations about a person into specific, respectful feedback.

In plain words
What is it for?
Use it to draft positive, constructive, or 360-degree feedback with a forward-looking suggestion.
Why use it?
It prevents vague or personal criticism by linking feedback to what happened and its effect.

Skill for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

Part of the everything-claude-code-for-business plugin — 24 skills, 13 agents, 4 hooks shipped together

Good fit Use it to draft positive, constructive, or 360-degree feedback with a forward-looking suggestion.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/kenshikobayashi/everything-claude-code-for-business/feedback-draft
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 kenshikobayashi/everything-claude-code-for-business --skill feedback-draft
Clone the repo
git clone --depth 1 https://github.com/kenshikobayashi/everything-claude-code-for-business

Made for: Claude Code.

Or install everything-claude-code-for-business, the plugin that ships this one along with the rest of its 24 skills, 13 agents, 4 hooks.

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 feedback-draft

README.md
[![agentmods](https://agentmods.dev/badge/skills/kenshikobayashi/everything-claude-code-for-business/feedback-draft/github.svg)](https://agentmods.dev/skills/kenshikobayashi/everything-claude-code-for-business/feedback-draft)
Your own site
<a href="https://agentmods.dev/skills/kenshikobayashi/everything-claude-code-for-business/feedback-draft"><img src="https://agentmods.dev/badge/skills/kenshikobayashi/everything-claude-code-for-business/feedback-draft/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 feedback-draft

Your own site · 80×15
<a href="https://agentmods.dev/skills/kenshikobayashi/everything-claude-code-for-business/feedback-draft"><img src="https://agentmods.dev/badge/skills/kenshikobayashi/everything-claude-code-for-business/feedback-draft.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 14 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 418 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.
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 $0.00014 $0.00418
Opus 5 $0.00007 $0.00209
Sonnet 5 $0.00003 $0.00084
Haiku 4.5 $0.00001 $0.00042

Measured 9d ago against content hash fd33e8054e12, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

feedback-draft 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.

skills/feedback-draft/SKILL.md · 53 lines

What it actually says

You are executing the /feedback-draft command. Draft feedback for a person.

Input

$ARGUMENTS — Person and situation description, optionally with:

  • --type [positive|constructive|360]: Feedback type (default: constructive)

Steps

  1. Understand the situation and what feedback is needed
  2. Structure using SBI framework:
    • Situation: When/where did this happen?
    • Behavior: What specifically did they do? (observable, not interpreted)
    • Impact: What was the effect? (on you, the team, the project)
  3. Add a forward-looking element:
    • For positive: "I'd love to see more of this because..."
    • For constructive: "Going forward, I'd suggest..." or "What would help is..."
  4. Review for tone — firm but respectful, specific but not personal

Output Format

## Feedback Draft: [Person]
**Type**: [Positive / Constructive / 360]

### Feedback (SBI Format)

**Situation**: [When and where]

**Behavior**: [What they specifically did — observable facts, not interpretations]

**Impact**: [The effect on you, the team, or the outcome]

**Going Forward**: [What you'd like to see / suggestion for improvement]

---

### Delivery Tips
- **Setting**: [1-on-1 / written / real-time]
- **Timing**: [ASAP / next 1-on-1 / end of sprint]
- **Tone**: [Direct but supportive / celebratory / coaching]

Constraints

  • Focus on behavior, not character ("You were late to 3 meetings" not "You're unreliable")
  • Be specific — vague feedback is useless
  • For constructive feedback, always include a forward-looking suggestion
  • Draft only — the user delivers the feedback, not Claude
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 · 53 lines · 14 tokens per session scan A fd33e8054e12

Subscribe to this mod's changes

feedback-draft is a skill published in the GitHub repository kenshikobayashi/everything-claude-code-for-business (2 stars, last pushed 3mo ago), licensed MIT. It adds 14 tokens to every session and 418 once invoked, about $0.0001 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens