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 karashiiro/agent-skills --skill organizing-pr-feedbackgit clone --depth 1 https://github.com/karashiiro/agent-skillsWrote 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/karashiiro/agent-skills/organizing-pr-feedback)<a href="https://agentmods.dev/skills/karashiiro/agent-skills/organizing-pr-feedback"><img src="https://agentmods.dev/badge/skills/karashiiro/agent-skills/organizing-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/karashiiro/agent-skills/organizing-pr-feedback"><img src="https://agentmods.dev/badge/skills/karashiiro/agent-skills/organizing-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 | $0.00040 | $0.00943 |
| Opus 5 | $0.00020 | $0.00472 |
| Sonnet 5 | $0.00008 | $0.00189 |
| Haiku 4.5 | $0.00004 | $0.00094 |
Grade A, and why
organizing-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 10d 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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Organizing PR Feedback
Overview
Collect all feedback threads from a GitHub PR, cross-reference author replies to identify resolved vs. open items, and produce a consolidated revision table grouped by topic.
When to Use
- Reviewing or organizing PR comments
- Identifying what still needs addressing after reviews
- Preparing a revision pass
Fetching PR Feedback via Gateway
Issue-level comments (general discussion)
local comments = github.issue_read({
owner = "OWNER",
repo = "REPO",
issue_number = PR_NUMBER,
method = "get_comments",
perPage = 100
}):await()
local out = {}
for _, c in ipairs(comments.comments or {}) do
table.insert(out, {
id = c.id,
author = c.user and c.user.login or "unknown",
created = c.created_at,
body = c.body
})
end
result(out)
Inline review threads (code-level comments)
local res = github.pull_request_read({
method = "get_review_comments",
owner = "OWNER",
repo = "REPO",
pullNumber = PR_NUMBER,
perPage = 100
}):await()
local threads = {}
if res.review_comments and res.review_comments.reviewThreads then
for _, thread in ipairs(res.review_comments.reviewThreads) do
local t = {
isResolved = thread.IsResolved,
isOutdated = thread.IsOutdated,
path = nil,
comments = {}
}
if thread.Comments and thread.Comments.Nodes then
for _, c in ipairs(thread.Comments.Nodes) do
table.insert(t.comments, {
author = c.Author and c.Author.Login or "unknown",
body = c.Body,
path = c.Path,
line = c.Line
})
t.path = t.path or c.Path
end
end
table.insert(threads, t)
end
end
result(threads)
Note: Review thread fields use PascalCase (GraphQL style): IsResolved, Comments.Nodes, Author.Login, Body, Path, Line.
Top-level reviews (approve/request-changes verdicts)
local res = github.pull_request_read({
method = "get_reviews",
owner = "OWNER",
repo = "REPO",
pullNumber = PR_NUMBER,
perPage = 100
}):await()
local reviews = {}
for _, r in ipairs(res.reviews or {}) do
table.insert(reviews, {
author = r.user and r.user.login or "unknown",
state = r.state,
body = r.body
})
end
result(reviews)
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.
- 10d ago First seen · 133 lines · 40 tokens per session scan A 68c78b3c645f
organizing-pr-feedback is a skill published in the GitHub repository karashiiro/agent-skills (2 stars, last pushed 4mo ago), licensed Unlicense. It adds 40 tokens to every session and 943 once invoked, about $0.0002 per session on Opus 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.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…