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 drn/dots --skill address-commentsgit clone --depth 1 https://github.com/drn/dotsWrote 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/drn/dots/address-comments)<a href="https://agentmods.dev/skills/drn/dots/address-comments"><img src="https://agentmods.dev/badge/skills/drn/dots/address-comments/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/drn/dots/address-comments"><img src="https://agentmods.dev/badge/skills/drn/dots/address-comments.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00079 | $0.03537 |
| Opus 5.5 | $0.00032 | $0.01415 |
| Sonnet 5.5 | $0.00016 | $0.00707 |
| Haiku 4.5 | $0.00008 | $0.00354 |
Grade A, and why
address-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 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 — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Arguments
$ARGUMENTS— Optional. PR number, PR URL, or branch name. Defaults to the PR for the current branch.
Context
- Current branch: !
git branch --show-current - Git status: !
git status --short - Base ref: !
git branch -r 2>/dev/null | grep -oE 'origin/(main|master)' | head -1 - Default remote: !
git remote 2>/dev/null | head -5
Your task
Walk every unresolved review thread on the target PR. For each thread: read the comment in context, decide whether to act on it, make the code change if warranted, post a reply explaining the rationale, then resolve the thread. End with a clean PR (zero unresolved threads) and a one-paragraph summary of what was done.
This skill does not push the branch into CI babysitting or merge it — use /pr or /merge for that. The focused job here is comment hygiene.
Step 1: Identify the PR
First, derive the upstream repo slug. Prefer the upstream remote if it exists, otherwise origin. The rules below all need it.
REPO_SLUG=$(git remote get-url upstream 2>/dev/null | sed -E 's|.*[:/]([^/]+/[^/.]+)(\.git)?$|\1|')
[ -z "$REPO_SLUG" ] && REPO_SLUG=$(git remote get-url origin | sed -E 's|.*[:/]([^/]+/[^/.]+)(\.git)?$|\1|')
Then determine the target PR by applying these rules in order:
$ARGUMENTSis a GitHub PR URL (https://github.com/<owner>/<repo>/pull/<n>) → parse owner/repo/number from the URL.$ARGUMENTSmatches^[0-9]+$(pure digits) → rungh pr view <args> --repo "$REPO_SLUG" --json numberto verify it is a real PR. If that succeeds, treat as a PR number. If it fails, fall through to the branch-name rule (a branch literally named42should still resolve correctly).$ARGUMENTSis any other non-empty string → treat as a branch name and look up the PR for that branch.$ARGUMENTSis empty → use the current branch (git branch --show-current).
Find the PR number with gh pr list --repo <slug> --head '<branch>' --state open --json number,url.
Cross-fork PRs. If gh pr list --head '<branch>' returns zero results AND an upstream remote exists, the branch may live on a fork. Resolve the fork owner from the origin remote and retry with the qualified --head '<fork-owner>:<branch>':
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 · 197 lines · 79 tokens per session scan A 8061230196f2
address-comments is a skill published in the GitHub repository drn/dots (23 stars, last pushed 11d ago), licensed MIT. It adds 79 tokens to every session and 3,537 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…