feedback

feedback is a command for Claude Code from TOMOSIA-VIETNAM/open-pr. It costs 32 tokens per session (1,581 once invoked), scanned A, original, MIT.

A command for reporting problems with the open-pr plugin itself to that plugin's public issue tracker.

In plain words
What is it for?
It gathers and anonymises a problem, prepares an issue for the fixed tracker, and leaves the user's repository unchanged.
Why use it?
It keeps plugin feedback separate from the user's code and prevents reports from being posted before the exact text is approved.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the open-pr plugin — 5 commands shipped together

Good fit It gathers and anonymises a problem, prepares an issue for the fixed tracker, and leaves the user's repository unchanged.

Compare 6 commands from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add TOMOSIA-VIETNAM/open-pr
Claude Code
/plugin install open-pr

Made for: Claude Code.

Or install open-pr, the plugin that ships this one along with the rest of its 5 commands.

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

README.md
[![agentmods](https://agentmods.dev/badge/commands/tomosia-vietnam/open-pr/feedback.svg)](https://agentmods.dev/commands/tomosia-vietnam/open-pr/feedback)
Your own site
<a href="https://agentmods.dev/commands/tomosia-vietnam/open-pr/feedback"><img src="https://agentmods.dev/badge/commands/tomosia-vietnam/open-pr/feedback.svg" alt="Measured on agentmods" height="20"></a>
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,581 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 $0.00032 $0.01581
Opus 5 $0.00016 $0.00790
Sonnet 5 $0.00006 $0.00316
Haiku 4.5 $0.00003 $0.00158

Measured 8d ago against content hash 836e4b50708b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

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.

python3 -c 'import json,os,urllib.parse as u;d=json.load(open(os.environ.get("TMPDIR","/tmp")+"/open-pr-feedback.json"));print("https://github.com/TOMOSIA-VIETNAM/open-pr/issues/new?"+u.urlencode(d))'
src/commands/feedback.md · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CRITICAL: Read "${CLAUDE_PLUGIN_ROOT}"/core/guardrails.md FIRST — shared rules, not repeated here. On top of those:

  • Destination is FIXED: TOMOSIA-VIETNAM/open-pr, the plugin's own tracker. FORBIDDEN: any other repo, and any write to the user's repo, config, memory or worktrees.
  • The issue is PUBLIC and cannot be unposted. FORBIDDEN: creating or commenting before the user approves the exact text at Step 4.
  • Carries the PROBLEM, never the user's work — Step 2.

This CRITICAL block is the SOLE enforcement layer — no allowed-tools backs it (deliberate).

Step 1 — What is being reported

Sources, in order: ARGUMENTS, then what THIS chat session shows — which /open-pr: command the user ran, what it did, what they wanted instead. FORBIDDEN: reading the reviewed repo, its diff, its notebooks/review/, its settings or memory.

Both empty ⇒ ONE free-text question — what should change, and what prompted it — then WAIT.

Step 2 — Strip what identifies the user

Anonymise: a reader MUST NOT be able to tell which repo, company or person it came from.

in the report goes in as
repo / org / product / host name, remote or PR URL, PR number drop — "a PR"
path, filename, branch, sha, ticket id its generic kind — "a config file", "a large diff"
code, diff, log or error text quoting the user's content the behaviour, in your own words
person name, email, handle drop
token, key, password, internal hostname, IP drop — never echoed, not even masked
vendor (GitHub/GitLab/Bitbucket), stack, language, command name, plugin's own message text KEEP

Unsure whether a detail identifies ⇒ drop it.

Step 3 — Draft it, in English

English whatever the chat language. Title ≤ 70 chars, states the problem. The tracker answers 2 forms — pick by what is reported, fill that form's fields, nothing else:

the plugin form label field = its heading ← content
misbehaved, crashed, reviewed wrongly bug_report.yml bug description = Bug description ← what it did + what was expected · steps = Steps to reproduce ← the sequence that reached it · version = Plugin version in use ← below · env = Environment ← OS, vendor, stack
lacks something, could be better feature_request.yml enhancement problem = Problem you're facing ← the situation hit · solution = Proposed solution ← the wish · alternatives = Alternatives considered (if any) ← what was tried instead, omitted when nothing was

Read the full file on GitHub · 120 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. 8d ago First seen · 120 lines · 32 tokens per session scan A 836e4b50708b

Subscribe to this mod's changes

feedback is a command published in the GitHub repository TOMOSIA-VIETNAM/open-pr (42 stars, last pushed 2d ago), licensed MIT. It adds 32 tokens to every session and 1,581 once invoked, about $0.0002 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 2026-08-30.