Borrowing it
Nothing to install: this file belongs to flutter/dart-intellij-third-party. 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/flutter/dart-intellij-third-party/main/.agents/skills/dependabot-pr-review/SKILL.mdgit clone --depth 1 https://github.com/flutter/dart-intellij-third-partyWrote 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/flutter/dart-intellij-third-party/dependabot-pr-review)<a href="https://agentmods.dev/skills/flutter/dart-intellij-third-party/dependabot-pr-review"><img src="https://agentmods.dev/badge/skills/flutter/dart-intellij-third-party/dependabot-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/flutter/dart-intellij-third-party/dependabot-pr-review"><img src="https://agentmods.dev/badge/skills/flutter/dart-intellij-third-party/dependabot-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 | $0.00101 | $0.03872 |
| Opus 5.5 | $0.00040 | $0.01549 |
| Sonnet 5.5 | $0.00020 | $0.00774 |
| Haiku 4.5 | $0.00010 | $0.00387 |
Grade A, and why
dependabot-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 18d 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 — 310 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dependabot PR Review Skill
This skill triages open automated dependency PRs across the two IntelliJ
plugin repositories. It reports build health for each PR, gets explicit user
confirmation for each one, then approves the confirmed PRs and applies the
autosubmit label.
Two kinds of PR are in scope, because they share one lifecycle: opened by automation, labeled for auto-submit, and stalled when that label is stripped.
| Source | Author | Example title |
|---|---|---|
dependabot |
app/dependabot |
Bump org.jetbrains.kotlin.jvm from 2.4.10 to 2.4.20 |
sdk-roll |
flutteractionsbot |
ci: bump pinned Flutter SDK to version 3.47.5 |
SDK rolls appear only in flutter/flutter-intellij; the Dart repo has no SDK
roller, so an empty result there is normal, not a failure.
[!IMPORTANT] Never approve or label a PR that the user has not confirmed. The user may confirm PRs individually or accept the bulk option covering every PR with a passing build, but there is no shortcut that approves failing or pending PRs in bulk.
How the autosubmit Label Works
This skill never merges anything. It approves and labels; the auto-submit bot
does the merging. Understanding the label's lifecycle explains what this skill
is really fixing:
- The opening automation applies
autosubmititself at PR creation. For Dependabot this is configured underlabels:in each repo's.github/dependabot.yml; SDK rolls are labeled by the workflow that files them. - The
auto-submitbot tries to merge, and removes the label if any requirement is unmet, leaving a comment explaining why. - The label does not come back on its own. The PR stalls until a human resolves the blocker and re-applies it.
So an open automated PR without the label has already been rejected once, and the comment says why. The two common cases:
| Build | Bot's reason | What this skill does |
|---|---|---|
PASS |
"At least 1 approving review is required" | Approving and re-labeling unblocks the merge. This is the main win. |
FAIL |
A named check failed | Re-labeling is futile; the bot strips it again within minutes. Fix the check first. |
What ships with it
2 files 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.
- 18d ago Changed · +73 lines · +24 tokens per session d0f45d7a0a8d
- 1mo ago Changed · +45 lines · +13 tokens per session 68365379d823
- 1mo ago First seen · 192 lines · 64 tokens per session scan A 5443e858d6f4
dependabot-pr-review is a skill published in the GitHub repository flutter/dart-intellij-third-party (27 stars, last pushed today), licensed BSD-3-Clause. It adds 101 tokens to every session and 3,872 once invoked, about $0.0004 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 2026-09-22.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…
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"…
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…