agentmods.dev

dev

A development-stage command for API Platform projects. It reads an implementation plan, sends the work to an API implementer, and requires code checks and tests such as PHPUnit, PHPStan, and Infection.

In plain words
What is it for?
Use it to implement API resources and related components from .claude/last-api-plan.md, address review feedback, and run the project's required tests and analysis.
Why use it?
It turns an approved API plan into an implementation while checking the result for common errors and regressions.

Command

2 3mo ago A scan 35 tokens original MIT
View the source file gerard-labs/superpowers-api-platform
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 commands/gerard-labs/superpowers-api-platform/dev
Clone the repo
git clone --depth 1 https://github.com/gerard-labs/superpowers-api-platform
Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 458 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 $0.00035 $0.00458
Opus 5 $0.00017 $0.00229
Sonnet 5 $0.00007 $0.00092
Haiku 4.5 $0.00003 $0.00046

Measured yesterday against content hash 2236a26b5a54, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dev 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.

commands/dev.md · 54 lines

What it actually says

You are the Dev stage coordinator. The architecture plan to implement is in .claude/last-api-plan.md.

Step 1 — Read the plan

Read .claude/last-api-plan.md

Note the **API Platform area:** declared in the plan header. The implementer will use it to detect which gerard:* skills to invoke (and which <project>:* overrides to check via Glob).

Step 2 — Read REQUEST_CHANGES feedback if any

If this is an iteration of a REQUEST_CHANGES loop:

Read .claude/last-api-review.md

Pass the reviewer's findings to the implementer so it can address them specifically.

Step 3 — Invoke api-platform-implementer via Task

Pass:

  • The plan (read at step 1)
  • The reviewer feedback (if iteration)

The implementer MUST:

  • Read state files first
  • Detect API Platform area + project skill overrides
  • Read relevant gerard:api-platform-* skills BEFORE editing
  • Implement the change (resource + DTOs + provider/processor + filters + tests)
  • Run ./vendor/bin/phpunit --filter=Api until green
  • Run ./vendor/bin/phpstan analyse
  • Run ./vendor/bin/infection --filter=<critical-classes> on changed critical classes
  • Apply AppSec mitigations from the plan
  • Self-audit Y/N checklist
  • Emit report between ===API-DEV-BEGIN=== / ===API-DEV-END===

Step 4 — Persist state file

Write .claude/last-api-dev-report.md with the full content between ===API-DEV-BEGIN=== and ===API-DEV-END=== (exclude markers themselves).

Surface to the user:

Dev done. Run /test next.
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 · 54 lines · 35 tokens per session scan A 2236a26b5a54

Subscribe to this mod's changes

dev is a command published in the GitHub repository gerard-labs/superpowers-api-platform (2 stars, last pushed 3mo ago), licensed MIT. It adds 35 tokens to every session and 458 once invoked, about $0.0002 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.

Backend and APIsCode reviewTestingapiapi-platformclaudeclaude-codeclaude-code-pluginsymfony
Related

Other commands, from other repositories

sonicjs-pr-fixer

You are a specialized agent that helps fix and merge problematic PRs in the SonicJS repository. This includes PRs from forks that need cherry-picking, Dependabot PRs that need e2e tests enabled, and any PR that needs fixes before merging.

SonicJs-Org/sonicjs · 0 tokens

sonicjs-seo-blog

Generate a high-quality, SEO-optimized blog post for SonicJS on the topic: $ARGUMENTS.

SonicJs-Org/sonicjs · 0 tokens

create-pr

Create a pull request following the official template.

rootstrap/rails_api_base · 0 tokens

templates

Manage locally-stored email templates for composing messages with variable substitution.

nylas/cli · 0 tokens

run-tests

Run unit and integration tests with proper configuration.

nylas/cli · 11 tokens

symfony-cache

Implement caching strategies using Symfony Cache component.

dev-toolings/superpowers-symfony · 7 tokens