gemini-triage

gemini-triage is an agent for Claude Code from joshsmithxrm/power-platform-developer-suite. It costs 5 tokens per session (319 once invoked), scanned A, original, MIT.

An agent that reviews Gemini's pull-request comments, where a pull request is a proposed code change, one comment at a time.

In plain words
What is it for?
Reading referenced code, fixing valid review findings in separate commits, dismissing invalid findings with reasons, and pushing fixes.
Why use it?
It separates real problems from suggestions that do not apply by checking the code against the project's specifications and rules.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

Install

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.

agentmods
npx agentmods add agents/joshsmithxrm/power-platform-developer-suite/gemini-triage
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 gemini-triage

README.md
[![agentmods](https://agentmods.dev/badge/agents/joshsmithxrm/power-platform-developer-suite/gemini-triage.svg)](https://agentmods.dev/agents/joshsmithxrm/power-platform-developer-suite/gemini-triage)
Your own site
<a href="https://agentmods.dev/agents/joshsmithxrm/power-platform-developer-suite/gemini-triage"><img src="https://agentmods.dev/badge/agents/joshsmithxrm/power-platform-developer-suite/gemini-triage.svg" alt="Measured on agentmods" height="20"></a>
Per session 5 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 319 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00005 $0.00319
Opus 5 $0.00003 $0.00160
Sonnet 5 $0.00001 $0.00064
Haiku 4.5 $0.00001 $0.00032

Measured 5d ago against content hash 455900907d4f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

gemini-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 5d 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/agents/gemini-triage.md · 49 lines

What it actually says

Gemini Triage Agent

Triage Gemini review comments on a pull request. For each comment:

  1. Read the referenced file at the specified line
  2. Check against the spec and constitution for design rationale
  3. Evaluate: is this a valid finding that warrants a code change?
  4. If valid: fix the code and commit with git commit -m "fix(review): <description>"
  5. If invalid: compose a brief dismissal rationale explaining why the suggestion doesn't apply

Output Format

After processing all comments, push any fixes (git push) and output this JSON array:

[
  {
    "id": <comment_id>,
    "action": "fixed" | "dismissed",
    "description": "Brief explanation of what was done",
    "commit": "<sha>" | null
  }
]

Rules

  • Read the full file context, not just the diff line
  • Check the constitution (specs/CONSTITUTION.md) before dismissing
  • Fix real issues; dismiss style preferences and false positives
  • Each fix gets its own commit — don't batch
  • Push all fixes before outputting the JSON summary
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. 5d ago First seen · 49 lines · 5 tokens per session scan A 455900907d4f

Subscribe to this mod's changes

gemini-triage is an agent published in the GitHub repository joshsmithxrm/power-platform-developer-suite (7 stars, last pushed 5d ago), licensed MIT. It adds 5 tokens to every session and 319 once invoked, about $0.0000 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 agents, from other repositories

write-tests-agent

Agent that determines what type of tests to write and invokes the appropriate skill. Currently supports UI tests via write-ui-tests skill and XAML tests via write-xaml-tests skill.

dotnet/maui · 39 tokens

data-model-architect

Use when an orchestrator needs a Dataverse data model proposed (existing-table reuse, new tables in dependency-tier order, Mermaid ER diagram) for embedding in native-app-plan.md. Read-only — proposes, never mutates. Called by native-app-planner and /edit-app; not invoked directly by users.

microsoft/power-platform-skills · 67 tokens

webapi-integration

Use this agent when the user needs to integrate Power Pages Web API for a specific Dataverse table into their frontend code. Trigger examples: "integrate web api for products table", "add api calls for orders", "connect my site to the blog posts table", "implement crud for categories", "set up web api client", "create…

microsoft/power-platform-skills · 182 tokens

canvas-screen-builder

Implements or modifies one Canvas App screen from a shared plan and a screen-specific brief. Writes exactly one .pa.yaml file and performs self-QA without compiling. Called by the orchestrator in parallel with other builders, not directly by users.

microsoft/power-platform-skills · 53 tokens

genpage-edit-planner

Plans edits to an existing generative page. Reads the downloaded page artifacts (source, original prompt, config), analyzes the current implementation against the user's edit intent, presents an edit plan via plan mode, and writes genpage-edit-plan.md for the orchestrator to execute. Called by the genpage skill — not…

microsoft/power-platform-skills · 73 tokens

looping

Re-invoke agents safely with bounded loops, completion evaluators, AI judges, progress feedback, and approval escape behavior.

managedcode/dotnet-skills · 24 tokens