agentmods.dev

review-triager

review-triager is an agent for coding agents from prisma/orm. It costs 59 tokens per session (2,002 once invoked), scanned A, original, Apache-2.0.

An agent role for sorting GitHub pull-request review discussions into a practical action plan. It can also administer review threads, such as replying, reacting, or resolving them.

In plain words
What is it for?
Use it to fetch review state, classify findings as fixes, deferrals, out-of-scope items, or already-fixed issues, and manage the related GitHub threads.
Why use it?
It helps maintainers decide which review findings need work and keeps the discussion state aligned with those decisions. It separates review triage from actually changing the code.

Agent

not rated 48k 2d ago A scan 59 tokens original Apache-2.0
View the source file prisma/orm
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/prisma/orm/review-triager
Clone the repo
git clone --depth 1 https://github.com/prisma/orm

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 review-triager

README.md
[![agentmods](https://agentmods.dev/badge/agents/prisma/orm/review-triager.svg)](https://agentmods.dev/agents/prisma/orm/review-triager)
Your own site
<a href="https://agentmods.dev/agents/prisma/orm/review-triager"><img src="https://agentmods.dev/badge/agents/prisma/orm/review-triager.svg" alt="Measured on agentmods" height="20"></a>
Per session 59 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,002 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 $0.00059 $0.02002
Opus 5 $0.00030 $0.01001
Sonnet 5 $0.00012 $0.00400
Haiku 4.5 $0.00006 $0.00200

Measured yesterday against content hash c06f45d65a41, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

review-triager 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 yesterday.

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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

skills-contrib/review-triage-phase/agents/review-triager.md · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a review triager: an implementer-focused reviewer responsible for shepherding a PR through iterative GitHub review.

Run commands from the review-triage-phase skill directory. Script paths below are relative to it.

You do not implement code changes in this role. You decide what to do by editing a pre-generated scaffold, and keep review threads moving with clear, polite communication.

Inputs you expect from the delegating command

  • PR URL (preferred) or enough context to discover it from the current branch.
  • Output paths:
    • review-state.md + review-state.json (fetched review state; JSON is canonical)
    • review-targets.json (optional helper index derived from review-state)
    • review-actions.md + review-actions.json (your action plan; JSON is canonical)
  • Optional: scope constraints (what is in-scope/out-of-scope for this PR).

Primary responsibilities

  1. Fetch current review state

    • Confirm output directory artifact paths are git-ignored before writing:
      • node ../review-fetch-phase/scripts/guard-review-artifacts-ignored.mjs --dir <output-dir>
    • Use node ../review-fetch-phase/scripts/fetch-review-state.mjs --pr <url> --out-json <review-state.json> to write canonical JSON.
    • Validate and generate derived files using pure scripts:
      • node ../review-fetch-phase/scripts/validate-review-state.mjs --in <review-state.json>
      • node ../review-fetch-phase/scripts/render-review-state.mjs --in <review-state.json> --out <review-state.md>
      • node ../review-fetch-phase/scripts/summarize-review-state.mjs --in <review-state.json> --format text --out <summary.txt>
      • node ../review-fetch-phase/scripts/extract-review-targets.mjs --in <review-state.json> --out <review-targets.json>
    • Treat review-state.json as source of truth; markdown is derived.

  2. Bootstrap action scaffold

    • Generate scaffold with one ordered action per review target:
      • node ./scripts/bootstrap-review-actions.mjs --in <review-state.json> --out <review-actions.json>
    • Do not rewrite structure manually when scaffold exists. Edit action fields in place.

Read the full file on GitHub · 132 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. yesterday First seen · 132 lines · 0 tokens per session scan A c06f45d65a41

Subscribe to this mod's changes

review-triager is an agent published in the GitHub repository prisma/orm (47,594 stars, last pushed 2d ago), licensed Apache-2.0. It adds 59 tokens to every session and 2,002 once invoked, about $0.0003 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 2026-09-03.

Code reviewGit and workflowcockroachdbjavascriptloggy-coreloggy-terminalmariadb
Related

Other agents, from other repositories

review-orchestrator

Orchestrates the iterative PR review loop: fetch → triage → implement → resolve threads → re-fetch until clear. Use when a PR has active review.

prisma/prisma-next · 0 tokens

review-implementer

Implements a PR’s review action list, commits in small logical steps, and resolves GitHub review threads with “Done” replies when finished. Use when review-actions.md exists for a PR.

prisma/prisma-next · 44 tokens

review-triager

Triage GitHub PR review threads into an action plan and administer threads (reply/react/resolve) with an implementer’s pragmatism. Use when a PR has review comments that need deciding: address now, defer, out-of-scope, or already fixed.

prisma/prisma-next · 59 tokens

analyze-pass-impact

Analyzes how a specific topic affects a group of compiler passes. Used by the /plan-update skill to parallelize research across all compiler phases. Use when you need to understand the impact of a cross-cutting concern on specific compiler passes.

react/react · 53 tokens

json-output-reviewer

Reviews JSON output schema design, backwards compatibility, actions arrays, and machine-readability.

fallow-rs/fallow · 21 tokens

mobile-tester

Agent "mobile-tester" from akaszubski/autonomous-dev, covering mission, hard gate: appium mcp availability check, hard gate: environment security (sandbox only), hard gate: screenshot data safety and hard gate: 60-second timeout per test case.

akaszubski/autonomous-dev · 31 tokens