Borrowing it
Nothing to install: this file belongs to P2ERGmbH/agentic-coding. 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/P2ERGmbH/agentic-coding/main/.agents/skills/resolve-review/SKILL.mdgit clone --depth 1 https://github.com/P2ERGmbH/agentic-codingWrote 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/p2ergmbh/agentic-coding/resolve-review)<a href="https://agentmods.dev/skills/p2ergmbh/agentic-coding/resolve-review"><img src="https://agentmods.dev/badge/skills/p2ergmbh/agentic-coding/resolve-review/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/p2ergmbh/agentic-coding/resolve-review"><img src="https://agentmods.dev/badge/skills/p2ergmbh/agentic-coding/resolve-review.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 | $0.00037 | $0.03231 |
| Opus 5.5 | $0.00015 | $0.01292 |
| Sonnet 5.5 | $0.00007 | $0.00646 |
| Haiku 4.5 | $0.00004 | $0.00323 |
Grade C, and why
resolve-review scanned grade C with 1 finding 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 2mo 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf .tmp/task_comment_id_*.txt .tmp/updated_comment_*.md How it starts
The opening of the file, as written. The whole thing — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Resolve Review Workflow
This workflow guides you through resolving review findings (either local reviews or remote Pull Request comments) inside an isolated Git Worktree using an efficient orchestrator-worker pattern. It keeps the main conversation context clean and focused on user-approved planning, while delegating heavy file-parsing and code-modification tasks to specialized subagents.
Trigger
Use this workflow whenever the user asks to "resolve review", "fix review comments", or "address feedback" from a code review.
[!IMPORTANT] Fresh Fetch Mandate (MANDATORY): When this skill is invoked, the agent MUST ALWAYS fetch/refresh the review comments directly from the live GitHub API as the very first action. Under no circumstances may the agent reuse old, cached, or existing threads or analysis files. A fresh unique query file (e.g.
.tmp/pr_threads_<PR_NUMBER>_<TIMESTAMP>.json) must be created, and a fresh query must be executed. Relying on cached comment data is strictly prohibited.
🤖 Orchestration & Delegation Mandate
The primary agent MUST act as the orchestrator of the review resolution workflow. To prevent context clutter and manage token usage, the orchestrator:
- Orchestrates: Handles user approval, high-level task planning, git worktree setup, and final GitHub PR interactions (posting comments and resolving threads).
- Delegates: Spawns specialized subagents for token-heavy phases (gathering/analyzing findings and implementing specific code fixes), keeping the main chat clear of raw compiler output, lint logs, and long JSON payloads.
🌳 Isolated Git Worktree Mandate
To prevent conflicts with ongoing local work and avoid workspace pollution, the agent MUST operate within an isolated Git Worktree:
- Create Git Worktree:
Create an isolated worktree under a designated, git-ignored
/worktrees/pr-<PR_NUMBER>directory.- If the branch already exists (e.g., the PR's feature branch): checkout the existing branch directly:
git worktree add worktrees/pr-<PR_NUMBER> <existing_branch_name> - If creating a new branch: use the
-bflag:git worktree add -b <new_branch_name> worktrees/pr-<PR_NUMBER> origin/main - IMPORTANT: Always use the existing PR branch when resolving review comments. Do NOT create a new
fix/branch.
- If the branch already exists (e.g., the PR's feature branch): checkout the existing branch directly:
- Environment Setup:
- Copy the
.envfile from the root project directory to the worktree directory:cp .env worktrees/pr-<PR_NUMBER>/.env. - Symlink the
node_modulesdirectory from the root project directory to the worktree directory to avoid duplicate installation overhead:ln -s ../../node_modules worktrees/pr-<PR_NUMBER>/node_modules
- Copy the
- Scoped Operations: All subsequent terminal commands, local testing, code modifications, linting, compiling, and git pushes MUST be executed inside the worktree directory.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2mo ago First seen · 213 lines · 37 tokens per session scan C 1613abf53904
resolve-review is a skill published in the GitHub repository P2ERGmbH/agentic-coding (9 stars, last pushed 4mo ago), licensed MIT. It adds 37 tokens to every session and 3,231 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). 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…