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 husniadil/ekstend --skill address-pr-reviewgit clone --depth 1 https://github.com/husniadil/ekstendWrote 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/husniadil/ekstend/address-pr-review)<a href="https://agentmods.dev/skills/husniadil/ekstend/address-pr-review"><img src="https://agentmods.dev/badge/skills/husniadil/ekstend/address-pr-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/husniadil/ekstend/address-pr-review"><img src="https://agentmods.dev/badge/skills/husniadil/ekstend/address-pr-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 | $0.00033 | $0.05396 |
| Opus 5.5 | $0.00013 | $0.02158 |
| Sonnet 5.5 | $0.00007 | $0.01079 |
| Haiku 4.5 | $0.00003 | $0.00540 |
Grade A, and why
address-pr-review 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 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.
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 — 464 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Address PR Review
Work through unresolved review comments on a GitHub pull request: fetch each thread, validate the claim against the pinned code, apply fixes where valid, reply with technical reasoning, and resolve the thread.
This skill is a companion to code-review. code-review finds gaps proactively from the diff; address-pr-review reacts to comments already on the PR.
Subagent Mode (argument)
Second $ARGUMENTS slot controls subagent delegation:
| Value | Meaning |
|---|---|
subagent |
Delegate comment validation research and multi-file fixes to Task subagents in parallel |
no-subagent |
Stay in main context — no Task delegation |
auto |
Decide per comment: research-heavy or multi-file → delegate; simple → stay in-context |
| (empty) | Same as auto |
Default: auto. Validation re-reads always run in main context regardless of this mode.
Arguments
$ARGUMENTS is [PR_NUMBER] [subagent|no-subagent|auto]. Either slot may be omitted.
$1— PR number. If omitted, infer from the current branch.$2— subagent mode (see above).
Resolution rules:
- If
$1is a number → treat as PR number. - If
$1is one ofsubagent/no-subagent/auto→ treat as subagent mode; infer PR from branch. - If
$1is empty → infer PR from branch. If on main/master with no PR, ask the user.
Workflow Overview
┌──────────────────────────────────────┐
│ 1. Resolve PR number + repo │
└──────────────┬───────────────────────┘
▼
┌──────────────────────────────────────┐
│ 2. Fetch unresolved review threads │
│ via GraphQL │
└──────────────┬───────────────────────┘
▼
┌──────────────────────────────────────┐
│ 3. Detect stack + dependency versions │
│ (per-package in monorepos) │
└──────────────┬───────────────────────┘
▼
┌──────────────────────────────────────┐
│ 4. Validate each comment │
│ → valid / partial / invalid / │
│ defer / repeat │
└──────────────┬───────────────────────┘
▼
┌──────────────────────────────────────┐
│ 5. Present summary → AskUserQuestion │
│ (Apply / Done — free-form Other) │
└──────────────┬───────────────────────┘
▼
┌──────────────────────────────────────┐
│ 6. Apply fixes (tracked fix loop) │
└──────────────┬───────────────────────┘
▼
┌──────────────────────────────────────┐
│ 7. Push (commits live on origin) │
└──────────────┬───────────────────────┘
▼
┌──────────────────────────────────────┐
│ 8. Reply to each item (cite live SHA) │
│ 8a inline · 8b issue / body │
└──────────────┬───────────────────────┘
▼
┌──────────────────────────────────────┐
│ 9. Resolve inline threads │
│ (carve-out defer) │
└──────────────┬───────────────────────┘
▼
┌──────────────────────────────────────┐
│ 10. Update PR description (optional) │
└──────────────────────────────────────┘
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 · 464 lines · 33 tokens per session scan A 966d24d413cd
address-pr-review is a skill published in the GitHub repository husniadil/ekstend (1 stars, last pushed 9d ago), licensed MIT. It adds 33 tokens to every session and 5,396 once invoked, about $0.0001 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
git-workflow
Manages branches, worktrees, atomic commits, and branch completion by merge, PR, preserve, or discard. Use when starting feature work that needs a branch or an isolated workspace, making commits during development, or finishing a development branch. Also use when the user says "set up worktree", "create PR", "finish…
release
Automates the full release workflow: version bump, git tag, GitHub release, and npm publish.
find
Find the local coding-agent session that wrote the uncommitted changes in a file, or in a pasted snippet of changed code or comment text, and give a one-line command that resumes it. Prefers the session that authored the change over a review session. Use when asked which session, chat, thread, or agent made an edit…
git-workflow
Perform requested Git actions while preserving user work. Triggers on "commit", "提交".
quick-wrap
Short session close: commit, loose ends, stop. Not workstream-complete.
run
The single lifecycle entry point — take one or more tickets and drive each through its whole lifecycle (investigate, red tests, implement, gates, review, PR, merge, archive), interleaving them. Lean by default — one worker per ticket runs red tests, implementation and the gate scripts in one worktree, then…