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.
npx agentmods add commands/gerard-labs/superpowers-api-platform/api-resource-shipgit clone --depth 1 https://github.com/gerard-labs/superpowers-api-platformWrote 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.
[](https://agentmods.dev/commands/gerard-labs/superpowers-api-platform/api-resource-ship)<a href="https://agentmods.dev/commands/gerard-labs/superpowers-api-platform/api-resource-ship"><img src="https://agentmods.dev/badge/commands/gerard-labs/superpowers-api-platform/api-resource-ship.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00038 | $0.01577 |
| Opus 5 | $0.00019 | $0.00788 |
| Sonnet 5 | $0.00008 | $0.00315 |
| Haiku 4.5 | $0.00004 | $0.00158 |
Grade A, and why
api-resource-ship 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/api-resource-ship — Total autonomy mode
Run the full agentic pipeline on this API Platform feature, without any human intervention, until either:
- the feature is APPROVED → committed + pushed → PR opened (if
ghavailable) - the request_changes cap is reached → escalation block printed for the human to review
Feature description:
$ARGUMENTS
⚠️ Autonomy contract
- You DO NOT ask for confirmation at any step
- You DO NOT print "shall I continue?"
- You DO NOT pause for review
- You DO commit and push automatically on APPROVE
- You DO NOT push to
maindirectly — always a feature branch - You DO NOT use
--force,--no-verify,--no-gpg-sign - You SURFACE every stage's output so the human can audit a posteriori
Pre-flight
-
Verify clean working tree :
git status --porcelainIf output is non-empty → STOP. Print: "Refusing /api-resource-ship on a dirty working tree. Stash or commit first."
-
Slugify the feature (lowercase, kebab-case, max 50 chars). Example:
add-tender-csv-export. -
Detect base branch (
maintypically). Verify we are on it or fork from it :git fetch origin main git checkout -B feat/api-<slug> origin/main
Pipeline
Stage 1 — Architecture
Run /architect $ARGUMENTS (saves to .claude/last-api-plan.md).
Stage 2 — Dev
Run /dev.
Stage 3 — Test
Run /test.
Stage 4 — Review
Run /review (saves verdict to .claude/last-api-review.md).
Loop on REQUEST_CHANGES
If .claude/last-api-review.md first non-empty line is VERDICT: REQUEST_CHANGES:
iteration = 1
while iteration <= 3:
iteration += 1
Run /dev # implementer reads the latest review feedback
Run /test
Run /review
if VERDICT: APPROVE → break
If after 3 iterations still REQUEST_CHANGES → ESCALATE:
- Print the persistent issues
- Print: "Escalation: 3 iterations exhausted. Branch left at
feat/api-<slug>. Read.claude/last-api-review.mdfor the persistent issues." - STOP (do not commit, do not push)
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.
- 3d ago First seen · 164 lines · 38 tokens per session scan A 49b784f521c5
api-resource-ship is a command published in the GitHub repository gerard-labs/superpowers-api-platform (2 stars, last pushed 3mo ago), licensed MIT. It adds 38 tokens to every session and 1,577 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.
Other commands, from other repositories
brainstorm
Start a structured brainstorming session for Symfony project features and architecture.
execute-plan
Execute an implementation plan methodically with TDD and continuous validation.
symfony-api-resources
Configure API Platform resources with operations and pagination.
symfony-check
Run all quality checks (PHP-CS-Fixer, PHPStan, tests) on the Symfony project.
symfony-doctrine-relations
Guide for implementing Doctrine entity relationships (OneToMany, ManyToMany).
symfony-fixtures
Create test fixtures using Foundry factories for realistic test data.