agentmods.dev

review

review is a command for Claude Code from akka/ai-marketplace. It costs 12 tokens per session (470 once invoked), scanned A, original, Apache-2.0.

A review command that checks implemented code against its feature specification, development plan, project rules, and checklist.

In plain words
What is it for?
Use it to review an Akka feature’s implementation, including its handlers, endpoints, component calls, event design, error handling, and tests.
Why use it?
It helps find missing behavior, unjustified deviations, code-quality problems, and absent tests before the work is accepted.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

Part of the akka-specify plugin — 13 commands shipped together

not rated 6repo today A scan 12 tokens original Apache-2.0

Good fit Use it to review an Akka feature’s implementation, including its handlers, endpoints, component calls, event design, error handling, and tests.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/akka/ai-marketplace/review
View source ↗ akka/ai-marketplace doc.akka.io
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.

Clone the repo
git clone --depth 1 https://github.com/akka/ai-marketplace

Made for: Claude Code.

Or install akka-specify, the plugin that ships this one along with the rest of its 13 commands.

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

README.md
[![agentmods](https://agentmods.dev/badge/commands/akka/ai-marketplace/review/github.svg)](https://agentmods.dev/commands/akka/ai-marketplace/review)
Your own site
<a href="https://agentmods.dev/commands/akka/ai-marketplace/review"><img src="https://agentmods.dev/badge/commands/akka/ai-marketplace/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.

agentmods 80×15 button for review

Your own site · 80×15
<a href="https://agentmods.dev/commands/akka/ai-marketplace/review"><img src="https://agentmods.dev/badge/commands/akka/ai-marketplace/review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 470 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00012 $0.00470
Opus 5 $0.00006 $0.00235
Sonnet 5 $0.00002 $0.00094
Haiku 4.5 $0.00001 $0.00047

Measured 11d ago against content hash 5d5e22e72bb2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

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 11d 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.

plugins/akka-specify/commands/review.md · 62 lines

What it actually says

User Input

$ARGUMENTS

You MUST consider the user input before proceeding (if not empty).

Outline

  1. Setup: Call akka_sdd_list_specs to find the target feature. Load the spec, plan, tasks, and checklist.

  2. Load context: Read the constitution using akka_sdd_constitution. Understand what patterns and rules must be followed.

  3. Review implementation against spec:

    • Are all functional requirements implemented?
    • Are all acceptance criteria met?
    • Are there deviations from the spec? If so, are they justified?

  4. Review implementation against constitution:

    • Event sourcing: Are events designed as facts? Are handlers pure?
    • Effects API: Are command handlers returning Effects? No side effects?
    • ComponentClient: Used for all cross-component calls?
    • ACLs: Defined on all endpoints?
    • Serialization: @TypeName on all state/event classes?
    • Testing: Unit and integration tests present?

  5. Code quality review:

    • No business logic in endpoints
    • No blocking I/O in handlers
    • No shared mutable state
    • Error handling uses effects().error(), not exceptions
    • No fat events (events contain only changed data)

  6. Checklist verification: Walk through the checklist and mark items as passed or failed.

  7. Report:

    • Overall assessment: approved / approved with issues / needs rework
    • Issues found (categorized by severity)
    • Checklist completion percentage
    • Recommendations

Key Rules

  • Be specific: reference file paths and line numbers
  • Every issue must cite the rule it violates
  • Distinguish between must-fix (errors) and should-fix (warnings)
  • Acknowledge good patterns and practices, not just problems
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. 11d ago First seen · 62 lines · 12 tokens per session scan A 5d5e22e72bb2

Subscribe to this mod's changes

review is a command published in the GitHub repository akka/ai-marketplace (6 stars, last pushed today), licensed Apache-2.0. It adds 12 tokens to every session and 470 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 2026-08-31.

Claude CodeCode reviewaiakkagemini-aispec-driven-development
Related

Other commands, from other repositories

deepen

Spare-budget design pass. Make one shallow module deep — smaller interface, behavior held, tests green before & after.

JuliusBrussee/cavekit · 24 tokens

review

Adversarial senior review of the spec before build. Refute, don't rubber-stamp. Ends in a go/no-go gate.

JuliusBrussee/cavekit · 27 tokens

check

Drift detector. Diff SPEC.md against code. Read-only, zero writes.

JuliusBrussee/cavekit · 16 tokens

speckit.companion.living-drift

Report living-spec drift — per capability, the source files changed since the spec was last committed (opt-in, never halts).

alfredoperez/speckit-companion · 26 tokens

speckit.companion.living-coverage

Report living-spec requirement→test coverage — per requirement, whether its coverage tier maps a test (opt-in, read-only, never halts).

alfredoperez/speckit-companion · 29 tokens

validate-impl

Validate implementation against requirements, design, and tasks.

gotalab/cc-sdd · 9 tokens