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 tomzx/agents --skill handle-pr-author-feedbackgit clone --depth 1 https://github.com/tomzx/agentsWrote 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/tomzx/agents/handle-pr-author-feedback)<a href="https://agentmods.dev/skills/tomzx/agents/handle-pr-author-feedback"><img src="https://agentmods.dev/badge/skills/tomzx/agents/handle-pr-author-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/tomzx/agents/handle-pr-author-feedback"><img src="https://agentmods.dev/badge/skills/tomzx/agents/handle-pr-author-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 | $0.00053 | $0.01846 |
| Opus 5 | $0.00026 | $0.00923 |
| Sonnet 5 | $0.00011 | $0.00369 |
| Haiku 4.5 | $0.00005 | $0.00185 |
Grade A, and why
handle-pr-author-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 5d 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 — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Handle PR Author Feedback
As the reviewer of a GitHub pull request, verifies that the author's fixes actually address the review feedback left earlier. For each unresolved review thread, inspects the current code and diff to decide whether the comment is addressed, partially addressed, not addressed, or reasonably rejected, then resolves the fixed threads and replies on the rest. Whether replies are posted and threads resolved on GitHub is decided by should-post-to-github (based on ~/.sdlc/config.yaml), otherwise replies are drafted without posting.
This skill never modifies the PR's code. To implement fixes on your own PR, use handle-pr-reviewer-feedback instead.
Prerequisites
ghCLI authenticated with write access to the target repository- PR number identifying an open pull request where you left review comments
- If
$1is provided, use it directly - If
$1is not provided, resolve the PR number with:gh pr list --head $(git branch --show-current) --json number --jq '.[0].number'
- If
Skill attribution (GitHub)
Before posting any PR comment with gh, read github-post-attribution/SKILL.md and append the Posted with footer for SKILL_DIR = handle-pr-author-feedback.
Workflow
Fetch PR threads + metadata ($1)
|
v
Filter to unresolved threads
authored by current user
|
v
For each thread
|
v
Inspect current code + diff
since the comment
|
v
Verdict: addressed / partial /
not addressed / rebuttal
|
v
Present verdicts to user for approval
/ \
Approved Rejected
| |
v v
Resolve + Skip
reply per thread
(ghx + GraphQL),
only if
should-post-to-github
allows
|
v
All threads resolved? --Yes--> Suggest /quick-pr-review
to re-approve
Steps
- Fetch PR metadata and threads:
Extract the latest commit SHA, the PR author, and the current user (ghx pr view $1 --json --refresh ghx pr threads $1 --ids --state allgh api user --jq .login).
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.
- 5d ago First seen · 159 lines · 53 tokens per session scan A 22584774b3f9
handle-pr-author-feedback is a skill published in the GitHub repository tomzx/agents (6 stars, last pushed 5d ago), licensed MIT. It adds 53 tokens to every session and 1,846 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
review-implement-phase
Implements triaged review actions, commits focused fixes, and posts Done plus resolves threads. Use when the user wants only the implementation phase of the review-framework workflow.
engram-branch-pr
PR creation workflow for Engram following the issue-first enforcement system. Trigger: When creating a pull request, opening a PR, or preparing changes for review.
verify-behavior
Verify or reproduce visible product behavior by driving the real UI with pi-computer-use's checked tools, requiring verified expect postconditions and durable state evidence for meaningful UI flows. Use when triage needs visual reproduction, implementation needs behavioral proof, review needs interactive confirmation…
github-contributor
End-to-end playbook for shipping high-quality pull requests to open-source projects you don't maintain — discovery, CONTRIBUTING compliance, PR-size check, minimal-diff implementation, PR description with AI-assisted disclosure, conflict resolution, and post-submission maintainer interaction. Use whenever creating…
revdiff
Review diffs, files, and documents with inline annotations in a TUI overlay, or answer questions about revdiff usage, configuration, themes, and keybindings. Opens revdiff in agterm/tmux/zellij/herdr/kitty/wezterm/cmux/ghostty/iterm2/emacs-vterm, captures annotations, and addresses them. Works in git, hg, and jj repos…
write-pr
Reference standards for writing pull request titles and descriptions in the tldraw repository, plus the pre-flight comment sweep over the diff. Use as supporting guidance when another skill or workflow needs PR content standards, not as the user-facing create/update PR workflow.