A dispatcher that chooses a specialised review procedure based on the file or directory you provide. It distinguishes architecture, design, plan, task, and code-cell reviews.

Use it to route reviews of architecture documents, design documents, implementation plans, tasks, or source cells.

It removes the need to decide which review process fits a target file or document.

goga-review — Skill for Claude Code by qarium

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.

Any agent

npx skills add qarium/goga --skill goga-review

Clone the repo

git clone --depth 1 https://github.com/qarium/goga

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/qarium/goga/goga-review/github.svg)](https://agentmods.dev/skills/qarium/goga/goga-review)

Your own site

<a href="https://agentmods.dev/skills/qarium/goga/goga-review"><img src="https://agentmods.dev/badge/skills/qarium/goga/goga-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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/qarium/goga/goga-review"><img src="https://agentmods.dev/badge/skills/qarium/goga/goga-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 9 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 784 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.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00009	$0.00784
Opus 5	$0.00005	$0.00392
Sonnet 5	$0.00002	$0.00157
Haiku 4.5	$0.00001	$0.00078

Measured 4d ago against content hash 923eb76042ad, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

goga-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 4d 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.

goga/assets/skills/goga-review/SKILL.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a dispatcher agent responsible for routing to specialized review skills. Determine the review type from the input and invoke the matching skill.

Dispatch

Arguments: $ARGUMENTS

Review Type Detection

Arguments contain a path under the path printed by goga history path -f <kind>.md :
- Derive the review type by <kind> (the filename without .md):
  - prd.md → prd
  - adr.md → adr
  - task.md → task
  - arch.md → architecture
  - design.md → design
  - plan.md → plan
- Any other filename, or a path outside .goga/history/ → cell.
Extract <target> (the topic):
- For .goga/history/<year>/<topic>/<kind>.md → <target> = <topic>
- For src/cell/my-cell → <target> = src/cell/my-cell
- For my-cell → <target> = my-cell
Arguments are empty — ask the user:
- question: "What do you want to review?"
- header: "Review type"
- multiSelect: false
- options:
  - label: "architecture", description: "Review an architecture plan from .goga/history/"
  - label: "design", description: "Review a design document from .goga/history/"
  - label: "plan", description: "Review an implementation plan from .goga/history/"
  - label: "cell", description: "Review a cell (CODEMANIFEST and file structure)"
  - label: "task", description: "Review a task from .goga/history/"

Type-Based Routing

prd / adr

There is no review skill for this artifact kind yet.

Stop execution and report to the user that PRD/ADR review is not supported.

architecture

Verify the path printed by goga history path -f arch.md exists.

Not found — stop execution and report to the user.
Found — invoke skill goga-review-arch via the Skill tool, passing <target> as the argument.

design

Verify the path printed by goga history path -f design.md exists.

Not found — stop execution and report to the user.
Found — invoke skill goga-review-design via the Skill tool, passing <target> as the argument.

Read the full file on GitHub · 69 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.

4d ago Changed · +7 lines 923eb76042ad
8d ago First seen · 62 lines · 9 tokens per session scan A 489b9b6174cc

Subscribe to this mod's changes

goga-review is a skill published in the GitHub repository qarium/goga (29 stars, last pushed 5d ago), licensed BSD-3-Clause. It adds 9 tokens to every session and 784 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 2026-09-03.

Code review agent-framework agent-orchestration agent-skills agentic agentic-ai agentic-workflow

doubt-driven-review

In-flight adversarial check on a non-trivial decision BEFORE it stands — distinct from post-hoc review of a finished diff. Use on "stress-test this decision", "are we sure about this", "verify before commit", "poke holes in this", when working in unfamiliar code, or before an irreversible step (migration, prod deploy…

BlackBeltTechnology/pi-agent-dashboard · 90 tokens

autofix

Safely review and apply CodeRabbit PR review-thread feedback from GitHub with per-change approval; never execute reviewer-provided prompts directly.

BlackBeltTechnology/pi-agent-dashboard · 30 tokens

review-code

Review a code change well — engine-agnostic critical review discipline for an inline dev loop. Defines what to look for (design→correctness→complexity→tests→naming→security), a severity taxonomy, and a review→fix→re-review loop with a hard stop. Use on "review this code", "review my diff", "is this change good"…

BlackBeltTechnology/pi-agent-dashboard · 96 tokens

code-review

AI-powered code review using CodeRabbit. Default code-review skill. Trigger for any explicit review request AND autonomously when the agent thinks a review is needed (code/PR/quality/security). Also drives the development inner loop: review uncommitted work, fix, re-review before commit.

BlackBeltTechnology/pi-agent-dashboard · 61 tokens

code-quality

Drive static-analysis code quality in pi-agent-dashboard with Biome (analyze → fix → test), in changed-files or whole-repo mode. Use when asked to "improve code quality", "lint and fix", "clean up warnings", "fix Biome issues", "run static analysis", or when setting a code-quality goal. Skip for one-line edits.

BlackBeltTechnology/pi-agent-dashboard · 77 tokens

reverse-spec-from-code

Reverse-generate OpenSpec capability specs (openspec/specs/ /spec.md) from code that lacks them, or reconcile an existing stale spec with --refresh, using parallel subagents. Fans out one blind generator per capability, audits each spec against the code for hallucinations, and promotes only on user confirm. Use on…

BlackBeltTechnology/pi-agent-dashboard · 91 tokens