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.
npx skills add metaschema-framework/claude-plugins --skill pr-feedbackgit clone --depth 1 https://github.com/metaschema-framework/claude-pluginsWrote 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/skills/metaschema-framework/claude-plugins/pr-feedback)<a href="https://agentmods.dev/skills/metaschema-framework/claude-plugins/pr-feedback"><img src="https://agentmods.dev/badge/skills/metaschema-framework/claude-plugins/pr-feedback/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.
<a href="https://agentmods.dev/skills/metaschema-framework/claude-plugins/pr-feedback"><img src="https://agentmods.dev/badge/skills/metaschema-framework/claude-plugins/pr-feedback.svg" alt="Reviewed on agentmods" width="80" 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 | $0.02779 |
| Opus 5.5 | $0.00013 | $0.01112 |
| Sonnet 5.5 | $0.00006 | $0.00556 |
| Haiku 4.5 | $0.00003 | $0.00278 |
Grade A, and why
pr-feedback 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 2mo 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.
How it starts
The opening of the file, as written. The whole thing — 379 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Feedback Skill
Use this skill when addressing PR review feedback to ensure comments are properly responded to and resolved.
DOs and DONTs
DO
- DO fetch all PR comments before starting to understand the full scope
- DO verify technical claims in feedback before implementing (see Step 2)
- DO address all feedback, including nits and style suggestions
- DO commit fixes with a clear message referencing what was addressed
- DO present proposed responses to the user for review BEFORE posting
- DO get user approval before resolving any review threads
- DO use the GraphQL API to resolve review threads
- DO verify all threads are resolved before considering feedback complete
- DO repeat the cycle until all checks pass AND no comments remain
- DO batch related fixes into a single commit when possible
DON'T
- DON'T blindly implement feedback without verifying correctness
- DON'T post responses or resolve threads without user approval
- DON'T ignore nits - they improve code quality and show attention to detail
- DON'T leave review threads unresolved after addressing them
- DON'T use the REST API
/repliesendpoint - it returns 404 for review comments - DON'T assume a general PR comment closes review threads - it doesn't
Step 1: Fetch PR Feedback
Get all review comments and feedback:
# Get PR comments and reviews
gh pr view <PR_NUMBER> --comments --json comments,reviews,body
# Get file-level review comments
gh api repos/<OWNER>/<REPO>/pulls/<PR_NUMBER>/comments
Step 2: Verify Feedback Correctness
Automated reviewers (like CodeRabbit) can be wrong. Before implementing feedback:
Verify Technical Claims
- API/schema claims - Use introspection or official docs to verify
# Example: Verify GraphQL field exists gh api graphql -f query='{ __type(name: "TypeName") { fields { name } } }' - Language/framework claims - Check official documentation
- Best practice claims - Consider project context; not all "best practices" apply universally
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.
- 2mo ago First seen · 379 lines · 32 tokens per session scan A 4624a6775421
pr-feedback is a skill published in the GitHub repository metaschema-framework/claude-plugins (10 stars, last pushed 8mo ago), licensed CC0-1.0. It adds 32 tokens to every session and 2,779 once invoked, about $0.0001 per session on Opus 5.5. 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.
pr-feedback compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| pr-feedbackmetaschema-framework/claude-plugins | Skill | 10 | 8mo ago | CC0-1.0 | A | 32 | Claude Code |
| prYeachan-Heo/oh-my-claudecode | Skill | 41k | today | MIT | A | 47 | Claude Code |
| merge-batchdiegosouzapw/OmniRoute | Skill | 85k | 2d ago | MIT | A | 46 | Claude Code |
| otto-pr-review-loopomnigent-ai/omnigent | Skill | 11k | today | Apache-2.0 | A | 17 | Claude Code, Codex |
| engram-branch-prGentleman-Programming/engram | Skill | 7.9k | yesterday | MIT | A | 37 | Claude Code, Codex |
| github-contributordaymade/claude-code-skills | Skill | 1.5k | today | MIT | A | 105 | Claude Code, Codex |
| revdiffumputun/revdiff | Skill | 949 | yesterday | MIT | A | 250 | Claude Code |