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 stilero/claude-plugins --skill fix-pr-comments-loopgit clone --depth 1 https://github.com/stilero/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/stilero/claude-plugins/fix-pr-comments-loop)<a href="https://agentmods.dev/skills/stilero/claude-plugins/fix-pr-comments-loop"><img src="https://agentmods.dev/badge/skills/stilero/claude-plugins/fix-pr-comments-loop/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/stilero/claude-plugins/fix-pr-comments-loop"><img src="https://agentmods.dev/badge/skills/stilero/claude-plugins/fix-pr-comments-loop.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 | $0.00195 | $0.05312 |
| Opus 5.5 | $0.00078 | $0.02125 |
| Sonnet 5.5 | $0.00039 | $0.01062 |
| Haiku 4.5 | $0.00019 | $0.00531 |
Grade A, and why
fix-pr-comments-loop 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 1mo 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 — 305 lines — stays where its author put it; the contents beside it link to each section on GitHub.
fix-pr-comments-loop
Orchestrator that drives a PR to a clean review state by dispatching one fresh subagent per round. Each round runs in its own Agent-tool subagent so accumulated noise (hardcore-reviewer reports, fix-step diffs, verification logs, polling output) stays isolated and does not bloat the orchestrator's context across rounds.
This skill does not run the round itself. The per-round work — steps 0–8 (count unresolved threads, fix, harden, verify, push, resolve threads, re-request copilot, poll, decide) — lives in the companion skill fix-pr-comments-loop-round, which the orchestrator invokes once per round in a fresh subagent.
If the per-comment fix behavior changes, edit pr-comment-fixer:fix-issues. If the hardcore review heuristics change, edit hardcore-code-reviewer:hardcore-code-reviewer. If the per-round procedure changes, edit fix-pr-comments-loop-round. This skill only encodes the outer-loop / dispatch contract.
When to use
Trigger phrases the user might say:
- "fix-pr-comments loop"
- "address all PR comments and re-request review until clean"
- "autonomous PR fix loop"
- "drive PR to clean review"
- "keep fixing the PR until copilot is happy"
If the user just wants a single round of fixes (no loop, no re-request), use pr-comment-fixer:fix-issues directly instead — this skill is the bigger hammer.
Prerequisites
ghCLI version>= 2.88(needed forgh pr edit --add-reviewer "$COPILOT_REVIEWER"— the bare bot login, not@copilot; see "Reviewer login (configurable)" below).- An open PR for the current branch on GitHub.
- The three child skills installed and triggerable:
pr-comment-fixer:fix-issues,hardcore-code-reviewer:hardcore-code-reviewer, andfix-pr-comments-loop-round. - A clean working tree at the start of the run.
Shell execution environment: every shell pipeline below (especially gh ... | jq ... invocations) should run with set -o pipefail so an upstream gh failure surfaces instead of being silently swallowed by a downstream jq that succeeds against empty stdin. The agent harness's bash session does NOT enable pipefail by default — set it explicitly at the start of any subshell or function that runs these pipelines.
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.
- 1mo ago First seen · 305 lines · 195 tokens per session scan A 3638e3562839
fix-pr-comments-loop is a skill published in the GitHub repository stilero/claude-plugins (2 stars, last pushed 3mo ago), licensed MIT. It adds 195 tokens to every session and 5,312 once invoked, about $0.0008 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.
Other skills, from other repositories
pr
Draft a PR body from OMC's paper trail — the smallest visual that proves the change, evidence consumed from the verify protocol (never re-collected), reversibility from the ADR test on the diff, glossary language throughout.
merge-batch
Prepare and merge an owner-selected PR batch with contributor credit and exact-candidate admission. Use for a pasted PR list; combined focused validation is diagnostic, and every actual landing still requires its applicable checks and authorization.
otto-pr-review-loop
Run Polly and OCR on a PR until all findings settle.
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.
github-contributor
A step-by-step guide for contributing code, tests, documentation, or build changes to open-source projects you do not maintain. It explains how to prepare a pull request that follows the project’s rules and is easier for maintainers to review.
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…