Borrowing it
Nothing to install: this file belongs to utensils/claudette. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/utensils/claudette/main/.claude/commands/incorporate-feedback.mdgit clone --depth 1 https://github.com/utensils/claudetteWrote 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/utensils/claudette/incorporate-feedback)<a href="https://agentmods.dev/commands/utensils/claudette/incorporate-feedback"><img src="https://agentmods.dev/badge/commands/utensils/claudette/incorporate-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/commands/utensils/claudette/incorporate-feedback"><img src="https://agentmods.dev/badge/commands/utensils/claudette/incorporate-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 | $0.00000 | $0.00618 |
| Opus 5 | $0.00000 | $0.00309 |
| Sonnet 5 | $0.00000 | $0.00124 |
| Haiku 4.5 | $0.00000 | $0.00062 |
Grade A, and why
incorporate-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.
What it actually says
Review and incorporate valid feedback from the current pull request.
Steps
-
Identify the PR — Determine which PR to review:
- Run
gh pr view --json number,url,titleto get the current branch's PR - If no PR exists, inform the user and stop
- Run
-
Fetch all review comments — Gather feedback:
- Run
gh pr view --json reviews,commentsto get top-level PR comments and reviews - Use
gh api repos/{owner}/{repo}/pulls/{number}/commentsto get inline review comments - Focus on unresolved comments and actionable feedback
- Run
-
Categorize each comment — Sort feedback into two buckets:
- Clear and actionable — The feedback points to an obvious improvement (e.g., a typo, missing error handling, a correctness bug, a straightforward refactor). Plan to incorporate these without asking.
- Ambiguous or debatable — The feedback involves a style preference, an architectural suggestion, an unclear request, or has multiple valid responses. These need user input.
-
Ask the user about ambiguous feedback — For each ambiguous comment (or batch of related comments), present the user with a question that includes:
- A brief quote or summary of the reviewer's comment for context
- Concrete suggested options for how to address it (e.g., "Refactor to use X as suggested", "Add a code comment explaining the current approach")
- An "Ignore this feedback" option — always included so the user can decline any suggestion
- The user will also have the option to type a free-form response if none of the suggested options fit
- Batch related comments into a single question where possible to reduce back-and-forth
-
Make changes — For feedback you're incorporating:
- Implement the requested changes
- Run the project's format, lint, typecheck (if applicable), and test commands after changes
- Fix any issues introduced by the changes
-
Respond to comments — For every comment:
- Incorporated: Reply confirming the change was made (e.g., "Done — updated to use
Xinstead") - Ignored by user's choice: Reply with a clear, respectful explanation based on the user's reasoning (e.g., "We discussed this and decided to keep the current approach because..." or "Intentional — [user's reason]")
- Incorporated with the user's custom approach: Reply describing what was done and why that approach was chosen
- Use
gh apito post replies to review comments
- Incorporated: Reply confirming the change was made (e.g., "Done — updated to use
-
Commit and push — If changes were made:
- Stage and commit using conventional commit format:
fix(scope): incorporate PR feedback - Include specifics in the commit body about what was addressed
- Push to the branch:
git push
- Stage and commit using conventional commit format:
-
Summary — Report back what was changed and what was declined, with reasoning.
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 · 42 lines · 0 tokens per session scan A 32f47c2f304b
incorporate-feedback is a command published in the GitHub repository utensils/claudette (76 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 618 tokens. 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 2026-08-30.
Other commands, from other repositories
afrv
Revise the current feature worktree after code review — decide accept/revert/modify (shortcut for feature-code-revise).
Code.Review
Your task is to perform a deep, non-superficial code review on the target branch.
Hexagonal.Gatekeeper
Your role is to perform a deep, architecture-focused code review on a specific branch. You must validate that all changes strictly follow Hexagonal Architecture (Ports & Adapters) principles and align with the existing codebase patterns.
mach12:pr-review
Run a comprehensive PR review with independent reviewers and post the results as a structured comment.
mach12:gh-pr-read
Read a GitHub pull request's title, body, and all top-level PR conversation comments; optionally locate an HTML-marker comment.
mach12:integrate-branch
Integrate a same-repository branch locally, review the combined result, and push when authorized.