Borrowing it
Nothing to install: this file belongs to DIGI-UW/OpenELIS-Global-2. 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/DIGI-UW/OpenELIS-Global-2/develop/.specify/oe/commands/address-pr-comments.mdgit clone --depth 1 https://github.com/DIGI-UW/OpenELIS-Global-2Wrote 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/digi-uw/openelis-global-2/address-pr-comments)<a href="https://agentmods.dev/commands/digi-uw/openelis-global-2/address-pr-comments"><img src="https://agentmods.dev/badge/commands/digi-uw/openelis-global-2/address-pr-comments.svg" alt="Measured on agentmods" 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 | $0.03972 |
| Opus 5 | $0.00000 | $0.01986 |
| Sonnet 5 | $0.00000 | $0.00794 |
| Haiku 4.5 | $0.00000 | $0.00397 |
Grade A, and why
address-pr-comments 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 8d 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 — 461 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Address PR Comments
When the user invokes /address-pr-comments (optionally with a PR number),
perform a structured, interactive workflow to triage and address all review
comments on a pull request. The workflow:
- Fetches all inline review comments, general comments, and thread resolution status using GitHub's REST and GraphQL APIs
- Classifies each unresolved comment into a triage category (blocking, bug, suggestion, question, nitpick, praise, outdated, out-of-scope) with LLM reasoning, then presents the triage table for user override
- Runs a QA session per comment in priority order, where the user decides: fix, defer, reply, skip, or mark as already addressed
- Batches actions: formats and commits code changes, posts reply comments, resolves threads, and optionally posts a PR summary comment
This command is intentionally interactive: every action (commit, reply, resolve) requires explicit user confirmation.
User Input
$ARGUMENTS
Interpret arguments best-effort. Support these patterns:
/address-pr-comments→ auto-detect PR for current branch/address-pr-comments 2767→ target PR #2767/address-pr-comments --unresolved-only→ skip already-resolved threads/address-pr-comments --author ibacher→ filter to comments by a specific reviewer/address-pr-comments --category blocking,bug→ filter to specific categories after classification
If any inputs are unclear, ask a single concise question and continue with safe defaults.
Safety Rules (non-negotiable)
- Never resolve a thread without posting a reply first. Every resolution needs an audit trail — even if just "Fixed in [commit ref]."
- Never force-push. Changes are committed normally; the user pushes when ready.
- Never auto-resolve without per-comment confirmation. Each thread gets its own "Resolve this thread? [y/n]" prompt during the QA session.
- Never post replies without user confirmation. All drafted replies are shown for review before posting. The user can edit any reply before it is sent.
- Never auto-commit. Stage changes and present them for user confirmation. The user writes or approves the commit message.
- Respect the reviewer. Draft replies must be professional, reference specific commits or reasoning, and never be dismissive. Follow Google Engineering Practices: clarify the code itself (rename, restructure, add comments), not just explain in the review tool.
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.
- 8d ago First seen · 461 lines · 0 tokens per session scan A 209f35d0939d
address-pr-comments is a command published in the GitHub repository DIGI-UW/OpenELIS-Global-2 (251 stars, last pushed today), licensed MPL-2.0. It costs nothing until one of its globs matches a file; then it loads 3,972 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
devkit.github.review-pr
Provides comprehensive GitHub pull request review with code quality, security, and best practices analysis. Use when reviewing a PR before merging.
speckit.spex.submit
Push and create PR for team review, with optional watch mode for CI monitoring.
git
The pre-finish status: branch, hygiene findings, message checks, workflow lint, template state.
code-review
Code review for branch changes. Analyzes git diff between branches with multi-level depth (low/medium/high). Matches changes against task description. Returns structured report with severity levels and verdict.
repo-audit
Audit a codebase (local or remote GitHub/GitLab) against architecture principles and requirements, surfacing drift, risk, and missing decisions.
advanced-code-review-context
Advanced Code Review Phase 2: Context Analysis - load previous reviews, PR history, declined items.