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.
/plugin marketplace add TOMOSIA-VIETNAM/open-pr/plugin install open-prWrote 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.
[](https://agentmods.dev/commands/tomosia-vietnam/open-pr/feedback)<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>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.
| Model | Per session | Once 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 | $0.00158 |
Grade A, and why
feedback scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
python3 -c 'import json,os,urllib.parse as u;d=json.load(open(os.environ.get("TMPDIR","/tmp")+"/open-pr-feedback.json"));print("https://github.com/TOMOSIA-VIETNAM/open-pr/issues/new?"+u.urlencode(d))' How it starts
The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CRITICAL:
Read"${CLAUDE_PLUGIN_ROOT}"/core/guardrails.mdFIRST — 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-toolsbacks 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 |
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.
- 8d ago First seen · 120 lines · 32 tokens per session scan A 836e4b50708b
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.
Other commands, from other repositories
cpp-review
Comprehensive C++ code review for memory safety, modern C++ idioms, concurrency, and security. Invokes the cpp-reviewer agent.
epic-claim
Claim an epic issue, stamp coordination state, and sync local ownership.
epic-review
Mark epic review requested, approved, or changes requested.
epic-unblock
Sweep blocked epic issues and reopen anything whose dependencies are closed.
gh-triage
GitHub OSS maintainer lifecycle triage, review, and approval management.
backlog
The project layer: milestones, epics, and user stories with refusing controllers — spec-seeded, sprint-ready.