reviewer

reviewer is an agent for coding agents from jcarlosrodicio/opencode-agent-orchestration-kit. It costs 24 tokens per session (1,440 once invoked), scanned A, original, Apache-2.0.

An agent that performs the final review of code changes without editing them.

In plain words
What is it for?
Auditing implementations before handoff, documenting evidence-based findings, and giving the final review verdict.
Why use it?
It checks the actual diff for bugs, security issues, architectural problems, regressions, and whether the requested work was completed.

Agent

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/jcarlosrodicio/opencode-agent-orchestration-kit/reviewer
Clone the repo
git clone --depth 1 https://github.com/jcarlosrodicio/opencode-agent-orchestration-kit

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 reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/jcarlosrodicio/opencode-agent-orchestration-kit/reviewer.svg)](https://agentmods.dev/agents/jcarlosrodicio/opencode-agent-orchestration-kit/reviewer)
Your own site
<a href="https://agentmods.dev/agents/jcarlosrodicio/opencode-agent-orchestration-kit/reviewer"><img src="https://agentmods.dev/badge/agents/jcarlosrodicio/opencode-agent-orchestration-kit/reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,440 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 $0.00024 $0.01440
Opus 5 $0.00012 $0.00720
Sonnet 5 $0.00005 $0.00288
Haiku 4.5 $0.00002 $0.00144

Measured yesterday against content hash d31637d9eec0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

reviewer 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.

opencode/agents/reviewer.md · 154 lines

How it starts

The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the general reviewer and the final review authority. Audit changes; do not edit files or replace the developer.

You act when there is a reviewable diff, implementation, or planning artifact, and cover correctness, security, bugs, regressions, maintainability, and task compliance.

Canonical Review Policy

canonical_policy: required
primary_evidence: diff_and_original_artifacts
developer_summary_is_not_evidence
causality: required
review_stage: final
final_verdict_authority: reviewer
pre_existing_debt: non_blocking

Load code-review-and-quality. Read its canonical policy and the profiles selected by that skill. The core policy is always active. Select generic backend and/or frontend profiles from the changed surface. Activate strict Clean Architecture, DDD, hexagonal, CQRS, or layered profiles only when the task, applicable repository instructions, ADR, specification, or architecture documentation explicitly declares them. Directory layout alone is not enough.

Before deciding:

  1. Confirm the objective, non-goals, success criteria, diff base, and applicable architecture declarations.
  2. Inspect git status, the real diff, relevant specs, manifests, evaluations, tests, logs, screenshots, traces, and other original evidence. A developer summary is context, never primary evidence.
  3. Follow plausible callers, consumers, mappings, and boundaries that the change can causally break. Do not invent external consumers: compatibility blocks only for a declared stable/public contract, a known affected consumer, or an acceptance criterion preserving prior behavior.
  4. Repeat proportionate deterministic checks when safe and already allowed. Record every required check that was not_run and how it limits the decision. Passing tests never override a causal correctness, architecture, security, or contract defect.
  5. If indispensable evidence cannot be obtained safely, return blocked instead of guessing.

For /plan, apply the same contract to the objective, research, plan/spec, assumptions, risks, acceptance criteria, and validation design even when no implementation diff exists. State that limitation.

Read the full file on GitHub · 154 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 Changed · +22 lines d31637d9eec0
  2. 5d ago First seen · 132 lines · 24 tokens per session scan A 09b3619e6371

Subscribe to this mod's changes

reviewer is an agent published in the GitHub repository jcarlosrodicio/opencode-agent-orchestration-kit (107 stars, last pushed yesterday), licensed Apache-2.0. It adds 24 tokens to every session and 1,440 once invoked, about $0.0001 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 2026-08-30.

Related

Other agents, from other repositories

lead

Agent "lead" from enmanuelmag/agent-harness-kit, covering lead agent — @cardor/agent-harness-kit, available research tools, provider delegation guidance, lead agent — @cardor/agent-harness-kit and !! absolute constraint — read before anything else !!.

enmanuelmag/agent-harness-kit · 0 tokens

builder

gent to implement code changes for a task that has already been planned by lead and analyzed by explorer. The builder writes, edits, and creates files based on the plan and the explorer's analysis. Invoke only after the explorer has completed its action. Never invoke without a canonical handoff addressed to builder.

enmanuelmag/agent-harness-kit · 0 tokens

explorer

gent to read and map the codebase for a specific task. The explorer researches relevant files, understands existing patterns, and produces a structured analysis for the builder to use. Invoke after the lead has defined a plan and before the builder starts. Never invoke for tasks that require writing or modifying files.

enmanuelmag/agent-harness-kit · 0 tokens

reviewer

gent to verify that a completed implementation meets all acceptance criteria for the current task. The reviewer reads the builder's compact action record, checks the builder's changes against each criterion, runs the health check, and either approves or blocks with specific, actionable feedback. Invoke only after the…

enmanuelmag/agent-harness-kit · 0 tokens

consultant

Agent "consultant" from enmanuelmag/agent-harness-kit, covering consultant agent — @cardor/agent-harness-kit, available research tools, consultant agent — @cardor/agent-harness-kit, !! absolute constraint !! and direct consultation mode — no harness.

enmanuelmag/agent-harness-kit · 0 tokens

subagents

Lifecycle planning/resume/pause is separate from execution intent. Planning mode does not imply plan-only.

thuandiep1707/codex-harness-javascript · 0 tokens