slidespeak-onbrand: Skill for Claude Code

.agents/skills/review-feedback/SKILL.md

review-feedback is a skill for Claude Code from SlideSpeak/slidespeak-onbrand. It costs 46 tokens per session (1,181 once invoked), scanned A, original, MIT.

A workflow for collecting pull-request review comments and examining them against the codebase. A pull request is a proposed set of code changes submitted for review before being merged.

In plain words
What is it for?
It helps find the relevant pull request, fetch all review feedback, research each issue in the code, and ask the developer what action to take.
Why use it?
It brings together inline comments and feedback written in the pull-request description, including findings that may otherwise be overlooked.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: installed under .agents/ (shared by several agents).

This is SlideSpeak/slidespeak-onbrand's own configuration. It tells Claude Code how to work on slidespeak-onbrand itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything slidespeak-onbrand configures →

Reuse

Borrowing it

Nothing to install: this file belongs to SlideSpeak/slidespeak-onbrand. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/SlideSpeak/slidespeak-onbrand/develop/.agents/skills/review-feedback/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/SlideSpeak/slidespeak-onbrand

Made for: Claude Code.

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 review-feedback

README.md
[![agentmods](https://agentmods.dev/badge/skills/slidespeak/slidespeak-onbrand/review-feedback/github.svg)](https://agentmods.dev/skills/slidespeak/slidespeak-onbrand/review-feedback)
Your own site
<a href="https://agentmods.dev/skills/slidespeak/slidespeak-onbrand/review-feedback"><img src="https://agentmods.dev/badge/skills/slidespeak/slidespeak-onbrand/review-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.

agentmods 80×15 button for review-feedback

Your own site · 80×15
<a href="https://agentmods.dev/skills/slidespeak/slidespeak-onbrand/review-feedback"><img src="https://agentmods.dev/badge/skills/slidespeak/slidespeak-onbrand/review-feedback.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,181 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00046 $0.01181
Opus 5 $0.00023 $0.00590
Sonnet 5 $0.00009 $0.00236
Haiku 4.5 $0.00005 $0.00118

Measured 11d ago against content hash 8919533d032c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

review-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 11d 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.

.agents/skills/review-feedback/SKILL.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review PR Feedback

Go through all review comments on a pull request, research each one, and grill the user on what action to take.

1. Resolve the PR

  • If $ARGUMENTS is provided, use it as the PR URL or number.
  • Otherwise, detect the PR for the current branch: gh pr view --json number,url,headRefName
  • If no PR is found, ask the user for a PR URL or number.

2. Fetch all feedback sources

Fetch both inline review comments and PR-body feedback. Some review agents (for example Greptile) edit the PR description with findings that are not represented as inline review comments, often under headings like Outside diff, Outside the diff, Additional findings, Potential issues, or similar.

# Get PR metadata and body/description. gh pr view supports the `body` JSON field.
gh pr view {number-or-url} --json number,url,title,author,body,comments,reviews

# Get unresolved inline review conversations on changed lines.
# Use reviewThreads instead of /pulls/{number}/comments so resolved conversations can be ignored.
gh api graphql --paginate -f owner='{owner}' -f name='{repo}' -F number={number} -f query='
  query($owner: String!, $name: String!, $number: Int!, $endCursor: String) {
    repository(owner: $owner, name: $name) {
      pullRequest(number: $number) {
        reviewThreads(first: 100, after: $endCursor) {
          pageInfo { hasNextPage endCursor }
          nodes {
            isResolved
            isOutdated
            path
            line
            startLine
            diffSide
            comments(first: 100) {
              nodes {
                id
                url
                body
                author { login }
                createdAt
                outdated
              }
            }
          }
        }
      }
    }
  }'

# Optional: get regular PR conversation comments too, in case agents post feedback there.
gh api repos/{owner}/{repo}/issues/{number}/comments --paginate

Ignore review threads where isResolved is true. For unresolved review threads, use the latest substantive comment in the thread as the primary feedback item and keep earlier thread comments as context. If isOutdated is true, keep the item but mark it as outdated, deprioritize it behind fresh unresolved threads, and re-check the current file before presenting it because the diff context may have shifted. Do not separately include raw /pulls/{number}/comments results unless reviewThreads is unavailable; that REST endpoint includes comments from resolved conversations and can cause already-resolved feedback to be reprocessed.

Read the full file on GitHub · 123 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. 11d ago First seen · 123 lines · 46 tokens per session scan A 8919533d032c

Subscribe to this mod's changes

review-feedback is a skill published in the GitHub repository SlideSpeak/slidespeak-onbrand (7 stars, last pushed today), licensed MIT. It adds 46 tokens to every session and 1,181 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.