plugin-feedback

plugin-feedback is a skill for Claude Code from rossumai/claude-marketplace. It costs 88 tokens per session (1,460 once invoked), scanned A, original, MIT.

A reporting workflow for problems found in the Rossum integration plugin. Rossum is a service that processes documents and extracts their data.

In plain words
What is it for?
Reporting a plugin bug, a missing tool capability, or incorrect Rossum information as a GitHub issue or an anonymous maintainer-reviewed report.
Why use it?
It turns a confusing tool problem or missing fact into a privacy-safe report, while requiring confirmation before anything is sent.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the rossum-sa plugin — 33 skills, 4 hooks shipped together

Good fit Reporting a plugin bug, a missing tool capability, or incorrect Rossum information as a GitHub issue or an anonymous maintainer-reviewed report.

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

Made for: Claude Code.

Or install rossum-sa, the plugin that ships this one along with the rest of its 33 skills, 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 plugin-feedback

README.md
[![agentmods](https://agentmods.dev/badge/skills/rossumai/claude-marketplace/plugin-feedback.svg)](https://agentmods.dev/skills/rossumai/claude-marketplace/plugin-feedback)
Your own site
<a href="https://agentmods.dev/skills/rossumai/claude-marketplace/plugin-feedback"><img src="https://agentmods.dev/badge/skills/rossumai/claude-marketplace/plugin-feedback.svg" alt="Measured on agentmods" height="20"></a>
Per session 88 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,460 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 $0.00088 $0.01460
Opus 5 $0.00044 $0.00730
Sonnet 5 $0.00018 $0.00292
Haiku 4.5 $0.00009 $0.00146

Measured 8d ago against content hash 6a8d91298bd1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

plugin-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 8d 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 -sG --data-urlencode "q=repo:<target_repo> state:open <signature>" https://api.github.com/search/issues`.
plugins/rossum-sa/skills/plugin-feedback/SKILL.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Report plugin feedback (sanitized, ONE confirmation stop)

You help a Rossum SA turn friction with THIS plugin into a sanitized, deduplicated report — fast. The whole flow costs the SA ONE reply: they see the draft and pick the channel in the same message. You NEVER send anything before that reply, and you NEVER include customer data.

0. Read the friction state (if any)

The detector hook may have written a state file for this session: ~/.cache/rossum-sa/friction/<session_id>.json (honor $XDG_CACHE_HOME). Read it if present for deterministic signal metadata. If absent, proceed from the SA's description and the current conversation. If you were started from the detector's offer, the SA's "yes" only starts this flow — it is NOT approval to send.

1. Classify into exactly ONE route — do not ask

  • tool-request — a Rossum capability the generalist tools could not do cleanly (a write/action gap, or an awkward read). NOT clean rossum_get usage.
  • agent-bug — a tool returned/did the wrong thing.
  • knowledge-gap — a Rossum fact/behavior the plugin got wrong or didn't know. Pick the best fit yourself; the SA corrects it at the single stop below.

2. Build the sanitized draft — metadata ONLY

Use ONLY the fields in reference/payload-contract.md. Never include raw payloads, field values, document content, annotation/org IDs, emails, or file contents. Scrub the SA's free text for anything resembling customer data and redact it.

3. Dedup — silently, before the stop

Search open issues in target_repo (from feedback-config.json) by signature (METHOD /endpoint for tool-request; tool + error class for agent-bug; pack + section for knowledge-gap). With gh, use gh search issues; without it, curl -sG --data-urlencode "q=repo:<target_repo> state:open <signature>" https://api.github.com/search/issues. If the search fails, skip dedup and continue — never block on it. On a confident match, plan to propose commenting + 👍 instead of a new issue.

4. ONE stop: draft + channel in a single message, then send

Read feedback-config.json. If form_url is empty (e.g. a fork, or the form not yet provisioned), do not offer (b)/(c) — say why, and offer (a) + the clipboard fallback only. Compose ONE message containing:

  1. the route you picked (one line, correctable),
  2. the FULL rendered draft — the SA seeing it is the privacy gate,
  3. the dedup note, if any ("matches #N — I'd comment + 👍 instead"),
  4. the channel question:

Read the full file on GitHub · 99 lines

Files

What ships with it

2 files 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. 8d ago First seen · 99 lines · 88 tokens per session scan A 6a8d91298bd1

Subscribe to this mod's changes

plugin-feedback is a skill published in the GitHub repository rossumai/claude-marketplace (5 stars, last pushed 4d ago), licensed MIT. It adds 88 tokens to every session and 1,460 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

debug-optimize-lcp

Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…

ChromeDevTools/chrome-devtools-mcp · 99 tokens

systematic-debugging

Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.

open-metadata/OpenMetadata · 37 tokens

diagnose

Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.

emdash-cms/emdash · 43 tokens

repro-admin

Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.

emdash-cms/emdash · 48 tokens

log-error-digest

Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…

zebbern/claude-code-guide · 71 tokens

byted-util-volcengine-detect-retry

An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.

bytedance/agentkit-samples · 101 tokens