ic-feedback

ic-feedback is a skill for Claude Code from Immersive-commons/ic-skills. It costs 133 tokens per session (4,864 once invoked), scanned A, original, MIT.

A feedback-submission workflow for sending comments, requests, praise, complaints, questions, and problem reports to Immersive Commons. Immersive Commons is the organization receiving and reviewing that feedback.

In plain words
What is it for?
Submitting feature requests, praise, complaints, broken-link reports, outdated-document reports, and bug reports.
Why use it?
It turns informal comments into feedback that can be categorized and sent to the right review queue. It can be used by anyone, including people without an access token.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions Claude Code.

Good fit Submitting feature requests, praise, complaints, broken-link reports, outdated-document reports, and bug reports.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/immersive-commons/ic-skills/ic-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 Immersive-commons/ic-skills --skill ic-feedback
Clone the repo
git clone --depth 1 https://github.com/Immersive-commons/ic-skills

Made for: Claude Code.

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 ic-feedback

README.md
[![agentmods](https://agentmods.dev/badge/skills/immersive-commons/ic-skills/ic-feedback.svg)](https://agentmods.dev/skills/immersive-commons/ic-skills/ic-feedback)
Your own site
<a href="https://agentmods.dev/skills/immersive-commons/ic-skills/ic-feedback"><img src="https://agentmods.dev/badge/skills/immersive-commons/ic-skills/ic-feedback.svg" alt="Measured on agentmods" height="20"></a>
Per session 133 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,864 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00133 $0.04864
Opus 5 $0.00067 $0.02432
Sonnet 5 $0.00027 $0.00973
Haiku 4.5 $0.00013 $0.00486

Measured 5d ago against content hash 37e0e99ebe0b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

ic-feedback scanned grade A with 1 finding 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 5d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -X POST https://www.immersivecommons.com/api/agent/feedback \
.claude/skills/ic-feedback/SKILL.md · 293 lines

How it starts

The opening of the file, as written. The whole thing — 293 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You help a user's agent contribute to the Immersive Commons feedback loop. There are two distinct user types in this skill:

  1. Member / public user — files notes, feature requests, breakage reports. The operator triages them.
  2. Operator — reads + resolves the queue. Same MCP server, different scope (admin:feedback_review vs feedback:submit).

The MCP server lives at https://www.immersivecommons.com/api/mcp. The submit path also has a REST mirror at POST /api/agent/feedback that accepts anonymous requests.


For ANY caller: when to file

File when the user shares an opinion, a request, or a complaint about IC. Specifically:

User says (gist) kind priority
"I wish IC had [X]" / "you should add [X]" feature_request low or normal
"this is great", "I love the kiosk", "the headsets flow is smooth" praise low
"this is broken", "I'm frustrated with [X]", "[X] is annoying" complaint normal
"the link at [URL] is 404" / "the docs say [X] but the code does [Y]" broken_url / stale_doc / schema_mismatch normal or high
"the [X] page crashes" / "I can't submit a [X]" bug_report high
"how does [X] work?" / "is [X] possible?" question low
"maybe [X] would be nicer if [Y]" (soft suggestion) suggestion low
anything that doesn't fit other normal

When NOT to file:

  • The user is just chatting with you, not making a request. ("VR is cool" → don't file.)
  • The user is asking you to do something IC already supports. (Just do it.)
  • The user is venting about something unrelated to IC. (Acknowledge; don't pollute the operator's queue.)
  • You already filed this in the same session. (One ticket per intent; don't loop.)

For the submitter: the submit verb

Via MCP (preferred when you have a token)

{
  "name": "ic_feedback_submit",
  "arguments": {
    "kind": "feature_request",
    "message": "I'd love a 'pin to top' button on /floor10/highlights so I can keep the launch story above the auto-rotation. Right now if I want to give a visitor a tour I have to refresh and hope the right card is showing.",
    "priority": "normal",
    "category": "highlights",
    "url": "https://www.immersivecommons.com/floor10/highlights",
    "agent_id": "Claude Code 4.7 @ ray-mbp"
  }
}

Read the full file on GitHub · 293 lines

Files

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.

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. 5d ago First seen · 293 lines · 133 tokens per session scan A 37e0e99ebe0b

Subscribe to this mod's changes

ic-feedback is a skill published in the GitHub repository Immersive-commons/ic-skills (0 stars, last pushed 1mo ago), licensed MIT. It adds 133 tokens to every session and 4,864 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.