give-feedback

give-feedback is a skill for Claude Code from samkawsarani/sams-product-plugins. It costs 100 tokens per session (1,438 once invoked), scanned A, original, MIT.

A workflow for turning a vague reaction into specific, useful feedback using the SBIR framework, which organizes feedback around the situation, behavior, impact, and recommendation.

In plain words
What is it for?
Writing constructive or positive feedback and practicing how to receive feedback.
Why use it?
It helps explain what happened and what should change, instead of giving comments that are too general to act on.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter.

Part of the give-feedback plugin — 1 skill shipped together

Good fit Writing constructive or positive feedback and practicing how to receive feedback.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/samkawsarani/sams-product-plugins/give-feedback
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 samkawsarani/sams-product-plugins --skill give-feedback
Clone the repo
git clone --depth 1 https://github.com/samkawsarani/sams-product-plugins

Made for: Claude Code.

Or install give-feedback, the plugin that ships this one along with the rest of its 1 skill.

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 give-feedback

README.md
[![agentmods](https://agentmods.dev/badge/skills/samkawsarani/sams-product-plugins/give-feedback/github.svg)](https://agentmods.dev/skills/samkawsarani/sams-product-plugins/give-feedback)
Your own site
<a href="https://agentmods.dev/skills/samkawsarani/sams-product-plugins/give-feedback"><img src="https://agentmods.dev/badge/skills/samkawsarani/sams-product-plugins/give-feedback/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 give-feedback

Your own site · 80×15
<a href="https://agentmods.dev/skills/samkawsarani/sams-product-plugins/give-feedback"><img src="https://agentmods.dev/badge/skills/samkawsarani/sams-product-plugins/give-feedback.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 100 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,438 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 $0.00100 $0.01438
Opus 5 $0.00050 $0.00719
Sonnet 5 $0.00020 $0.00288
Haiku 4.5 $0.00010 $0.00144

Measured 10d ago against content hash 9aebe0cb93a5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

give-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 10d 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/give-feedback/skills/give-feedback/SKILL.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

What this skill does

Takes a raw reaction ("their Slack posts are too long", "great job today") and rebuilds it into feedback the recipient can act on based on SBIR framework, the Anatomy of High-Impact Feedback, and Radical Candor.

The core standard: If the person receiving the feedback doesn't know exactly what to do differently next time, the feedback wasn't instructional enough.


Step 1: Get the raw material

If the user hasn't already given it, ask for both in one message:

  1. What happened — the specific situation and behavior (not "they're disorganized" — what did they do).
  2. Who it's for + the relationship — direct report, peer, or someone more senior. This sets the Radical Candor framing.

If they only have a vague label ("not a team player", "bad at meetings"), pull the concrete moment out of them — the feedback can't be built without one observable behavior anchored in time. Don't proceed on a generalization.

Skip the interrogation if they've already supplied a situation + behavior. Bias for drafting.


Step 2: Classify — constructive or positive

Both use SBIR. Don't sandwich them together: keep praise and criticism in separate conversations, each gets its own space.

  • Positive feedback is not "great job." Generic praise is noise. It must be instructional — tell them the exact behavior to repeat and why it mattered.
  • Constructive feedback communicates a change you want to see.

Step 3: Build it in SBIR

Draft the feedback across four parts:

Part What goes here Test
S — Situation Anchor it. "In yesterday's client demo at 2pm…" No generalities. A specific time/place.
B — Behavior Observable actions only. "You interrupted the client twice." NOT interpretation ("you were rude"). Could a camera have recorded it?
I — Impact The effect that behavior had. "The client went quiet and we lost the pitch's momentum." Ties the behavior to a real consequence.
R — Request What you'd like next time, OR a question inviting their view. "Can you help me understand what was happening?" / "Next time, can we lead with the status?" Gives a path forward or opens collaboration.

Read the full file on GitHub · 103 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. 10d ago First seen · 103 lines · 100 tokens per session scan A 9aebe0cb93a5

Subscribe to this mod's changes

give-feedback is a skill published in the GitHub repository samkawsarani/sams-product-plugins (2 stars, last pushed 1mo ago), licensed MIT. It adds 100 tokens to every session and 1,438 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

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