What is api-resource-pipeline?

A semi-automatic workflow for building an API Platform feature in Symfony. It runs planning, implementation, testing, and review stages, then stops before committing so you can inspect the changes.

Use it to plan an API change, implement it, run tests, review the result, inspect the diff, and receive a summary of persistent issues when review does not pass.

It connects the development stages and repeats implementation, testing, and review when the reviewer requests changes, with a limit of three rounds. This reduces manual coordination while keeping the final diff under your control.

api-resource-pipeline — Command for coding agents by gerard-labs: A semi-automatic workflow for building an API Platform feature…

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/api-resource-pipeline

Clone the repo

git clone --depth 1 https://github.com/gerard-labs/superpowers-api-platform

Or install gerard, the plugin that ships this one along with the rest of its 53 skills, 25 commands, 7 agents, 1 hook.

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/commands/gerard-labs/superpowers-api-platform/api-resource-pipeline.svg)](https://agentmods.dev/commands/gerard-labs/superpowers-api-platform/api-resource-pipeline)

Your own site

<a href="https://agentmods.dev/commands/gerard-labs/superpowers-api-platform/api-resource-pipeline"><img src="https://agentmods.dev/badge/commands/gerard-labs/superpowers-api-platform/api-resource-pipeline.svg" alt="Measured on agentmods" height="20"></a>

Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 785 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.

Model	Per session	Once invoked
Fable 5	$0.00033	$0.00785
Opus 5	$0.00016	$0.00392
Sonnet 5	$0.00007	$0.00157
Haiku 4.5	$0.00003	$0.00078

Measured 4d ago against content hash 8f79387a4fd4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

api-resource-pipeline 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.

commands/api-resource-pipeline.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/api-resource-pipeline — semi-autonomous

Run the full agentic pipeline on this API Platform feature:

$ARGUMENTS

Difference vs /api-resource-ship : this command stops before the git commit so you can inspect the diff. /api-resource-ship commits and pushes autonomously.

Steps

Run /architect $ARGUMENTS — saves plan to .claude/last-api-plan.md.
Run /dev — implements + saves to .claude/last-api-dev-report.md.
Run /test — verifies + saves to .claude/last-api-test-report.md.
Run /review — emits verdict, saves to .claude/last-api-review.md.
If verdict = REQUEST_CHANGES :
- Read the change list from .claude/last-api-review.md
- Re-run /dev (the implementer reads the latest review feedback)
- Re-run /test
- Re-run /review
- Cap at 3 iterations. Beyond, output the persistent issues for the user. STOP without commit, branch (if any) left in place.
If verdict = APPROVE :
- Summarize what was built (1 paragraph)
- List the files touched with line counts (git diff --stat)
- Show git diff --stat actual
- Prompt the user: "Diff ready. Inspect with git diff, then commit and push manually OR run /api-resource-ship <description> next time to skip the manual step."

Verdict parsing

The first non-empty line of .claude/last-api-review.md is exactly :

VERDICT: APPROVE → exit loop, surface diff
VERDICT: REQUEST_CHANGES → iter++, loop (cap 3)

No modifier (VERDICT: APPROVE WITH CAVEATS is not recognized and treated as APPROVE by default — but ideally the reviewer respects the strict format).

Output

Streamed per-stage so you can watch progress. Each /architect, /dev, /test, /review reports its outcome.

Final report on APPROVE :

✅ Pipeline complete (semi-auto)
   Verdict:        APPROVE
   Iterations:     <N> (out of 3 max)
   Files modified: <N>
   Lines:          +<X> / -<Y>

   State files (gitignored, persist across sessions):
   - .claude/last-api-plan.md
   - .claude/last-api-dev-report.md
   - .claude/last-api-test-report.md
   - .claude/last-api-review.md

   Diff ready in working tree. Commit when satisfied:
     git diff
     git add <files>
     git commit -m "feat: <subject from plan>"
     git push -u origin feat/<branch>

Read the full file on GitHub · 80 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 First seen · 80 lines · 33 tokens per session scan A 8f79387a4fd4

Subscribe to this mod's changes

api-resource-pipeline is a command published in the GitHub repository gerard-labs/superpowers-api-platform (2 stars, last pushed 3mo ago), licensed MIT. It adds 33 tokens to every session and 785 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 APIs Planning api api-platform claude claude-code claude-code-plugin symfony

api-resource-pipeline

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

/api-resource-pipeline — semi-autonomous

Steps

Verdict parsing

Output

What this file has done since we first saw it

Other commands, from other repositories

brainstorm

execute-plan

symfony-api-resources

symfony-check

symfony-doctrine-relations

symfony-fixtures