feedback-collector

feedback-collector is a skill for Claude Code from taizen-ai/taizen-claude-plugins. It costs 24 tokens per session (785 once invoked), scanned A, original, MIT.

A background system for recording corrections, suggestions, and problems with coding-agent skills. It can use connected company information sources and send logged feedback to configured databases or alerts.

In plain words
What is it for?
Logging user corrections and improvement suggestions, looking up related internal documentation, storing feedback, and alerting owners about serious problems.
Why use it?
It helps skill owners collect recurring issues without interrupting the person using the agent. High-severity issues can be routed to a configured team channel.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

Part of the taizen-gtm-skills plugin — 30 skills, 21 MCP servers shipped together

Good fit Logging user corrections and improvement suggestions, looking up related internal documentation, storing feedback, and alerting owners about serious problems.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/taizen-ai/taizen-claude-plugins/feedback-collector
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 taizen-ai/taizen-claude-plugins --skill feedback-collector
Clone the repo
git clone --depth 1 https://github.com/taizen-ai/taizen-claude-plugins

Made for: Claude Code.

Or install taizen-gtm-skills, the plugin that ships this one along with the rest of its 30 skills, 21 MCP servers.

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-collector

README.md
[![agentmods](https://agentmods.dev/badge/skills/taizen-ai/taizen-claude-plugins/feedback-collector/github.svg)](https://agentmods.dev/skills/taizen-ai/taizen-claude-plugins/feedback-collector)
Your own site
<a href="https://agentmods.dev/skills/taizen-ai/taizen-claude-plugins/feedback-collector"><img src="https://agentmods.dev/badge/skills/taizen-ai/taizen-claude-plugins/feedback-collector/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-collector

Your own site · 80×15
<a href="https://agentmods.dev/skills/taizen-ai/taizen-claude-plugins/feedback-collector"><img src="https://agentmods.dev/badge/skills/taizen-ai/taizen-claude-plugins/feedback-collector.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 785 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 $0.00024 $0.00785
Opus 5 $0.00012 $0.00392
Sonnet 5 $0.00005 $0.00157
Haiku 4.5 $0.00002 $0.00078

Measured 10d ago against content hash 098b2eef3fd9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

feedback-collector 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/taizen-gtm-skills/skills/feedback-collector/SKILL.md · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Feedback Collector Skill

Silent feedback capture for skill improvement.

Purpose

This is a silent feedback collection skill that logs user corrections, suggestions, and issues for review by skill owners.


Required Integrations

Setup: Connect these data sources to enable feedback logging and aggregation.

Data Sources

# FEEDBACK COLLECTOR DATA SOURCES
# Configure where feedback should be logged

# Enterprise Search (for context lookup)
- source: enterprise_search
  connector: "{{GLEAN | MOVEWORKS | ELASTIC}}"
  data:
    - internal_docs
    - wiki_content

Output Destinations

# Where to deliver feedback outputs
outputs:
  # Log feedback silently (no user-visible output)
  - type: database
    connector: "{{AIRTABLE | GOOGLE_SHEETS | NOTION_DATABASE}}"
    destination: "Skill Feedback Log"

  # Alert skill owners on high-severity issues
  - type: slack
    connector: "{{SLACK}}"
    channel: "#skill-feedback"
    severity_filter: high

When This Skill Activates

This skill should be invoked when:

  • User explicitly flags a correction ("That's not right", "Actually...", "The correct answer is...")
  • User provides feedback on skill output ("This could be better if...", "Missing...", "Inaccurate...")
  • User identifies outdated information
  • User suggests improvements

Feedback Capture Format

When feedback is detected, log the following:

{
  "timestamp": "[ISO timestamp]",
  "skill_invoked": "[Which skill was being used]",
  "user_context": "[User role/context if known]",
  "feedback_type": "[correction|suggestion|bug|outdated]",
  "original_output": "[Summary of what the skill produced]",
  "user_feedback": "[Exact user feedback]",
  "suggested_correction": "[If applicable, the correct information]",
  "severity": "[high|medium|low]"
}

Feedback Categories

Corrections

  • Factual errors in skill output
  • Outdated information
  • Incorrect frameworks or methodologies
  • Wrong competitive information

Read the full file on GitHub · 132 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 · 132 lines · 24 tokens per session scan A 098b2eef3fd9

Subscribe to this mod's changes

feedback-collector is a skill published in the GitHub repository taizen-ai/taizen-claude-plugins (8 stars, last pushed 3mo ago), licensed MIT. It adds 24 tokens to every session and 785 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