power-platform-developer-suite: Skill for Claude Code

.claude/skills/dependabot-triage/SKILL.md

dependabot-triage is a skill for Claude Code from joshsmithxrm/power-platform-developer-suite. It costs 87 tokens per session (4,086 once invoked), scanned A, original, MIT.

A workflow for sorting and merging open Dependabot pull requests. Dependabot is a service that creates pull requests for dependency updates, such as newer library versions.

In plain words
What is it for?
Use it to classify Dependabot requests, enable automatic merging for approved updates, test riskier updates, retry rebases within limits, and flag decisions that need a person.
Why use it?
It reduces a backlog of routine updates while separating safe changes from updates that need tests or human review.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is joshsmithxrm/power-platform-developer-suite's own configuration. It tells Claude Code how to work on power-platform-developer-suite itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything power-platform-developer-suite configures →

Reuse

Borrowing it

Nothing to install: this file belongs to joshsmithxrm/power-platform-developer-suite. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/joshsmithxrm/power-platform-developer-suite/main/.claude/skills/dependabot-triage/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/joshsmithxrm/power-platform-developer-suite

Made for: Claude Code.

Wrote 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.

agentmods badge for dependabot-triage

README.md
[![agentmods](https://agentmods.dev/badge/skills/joshsmithxrm/power-platform-developer-suite/dependabot-triage/github.svg)](https://agentmods.dev/skills/joshsmithxrm/power-platform-developer-suite/dependabot-triage)
Your own site
<a href="https://agentmods.dev/skills/joshsmithxrm/power-platform-developer-suite/dependabot-triage"><img src="https://agentmods.dev/badge/skills/joshsmithxrm/power-platform-developer-suite/dependabot-triage/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.

agentmods 80×15 button for dependabot-triage

Your own site · 80×15
<a href="https://agentmods.dev/skills/joshsmithxrm/power-platform-developer-suite/dependabot-triage"><img src="https://agentmods.dev/badge/skills/joshsmithxrm/power-platform-developer-suite/dependabot-triage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 87 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,086 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00087 $0.04086
Opus 5 $0.00044 $0.02043
Sonnet 5 $0.00017 $0.00817
Haiku 4.5 $0.00009 $0.00409

Measured 8d ago against content hash 9277a5c9c00c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

dependabot-triage 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.

.claude/skills/dependabot-triage/SKILL.md · 285 lines

How it starts

The opening of the file, as written. The whole thing — 285 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Dependabot Triage

Routine drain of open app/dependabot PRs against docs/MERGE-POLICY.md. Codifies the pattern from session a6f07099 (v1-prelaunch retro item B4, finding #9): three-group classification (auto-merge / verify-then-merge / manual review), batched gh pr merge --auto, bounded retry on rebase, and silent completion when nothing needs human input.

This skill assumes allow_auto_merge is enabled at the repo level (it currently is). The skill will halt if it is not — it does not flip the bit itself.

When to Use

  • "Drain the dependabot backlog"
  • "Triage open dependabot PRs"
  • "Check on the dependabot PRs"
  • After a quiet period when several dependabot PRs have accumulated
  • After a release window closes and dependabot work was deferred
  • Periodically as housekeeping (Wednesday afternoons after the Monday dependabot run, etc.)

When NOT to Use

  • During an active release (release branch present, tags being pushed) — wait until the release lands
  • For non-dependabot dependency PRs (human-authored bumps, e.g. a deliberate Microsoft.Identity.Client major bump) — those route through /pr like any feature work
  • For first-time enablement of auto-merge on the repo — that's a one-time admin action, not a triage step
  • For changing the merge policy itself — docs/MERGE-POLICY.md is authoritative; if you find policy gaps, file an issue and stop

Authoritative Reference

docs/MERGE-POLICY.md is the source of truth for what merges automatically and what doesn't. This skill operationalizes it; it does not redefine it. If the skill and the doc disagree, the doc wins and the skill needs a patch.

Pre-conditions

Run all of these checks before touching any PR. Halt on any failure with a clear instruction to the user.

  1. Auto-merge enabled at the repo level.
    gh repo view --json autoMergeAllowed --jq .autoMergeAllowed
    
    Must be true. If false, halt: "Auto-merge is not enabled on this repo. Enable via repo Settings > General > Pull Requests > Allow auto-merge, then retry."

Read the full file on GitHub · 285 lines

Changes

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.

  1. 8d ago First seen · 285 lines · 87 tokens per session scan A 9277a5c9c00c

Subscribe to this mod's changes

dependabot-triage is a skill published in the GitHub repository joshsmithxrm/power-platform-developer-suite (7 stars, last pushed yesterday), licensed MIT. It adds 87 tokens to every session and 4,086 once invoked, about $0.0004 per session on Opus 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.

Related

Other skills, from other repositories