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/architectgit clone --depth 1 https://github.com/gerard-labs/superpowers-api-platformWhat 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 | $0.00035 | $0.00745 |
| Opus 5 | $0.00017 | $0.00373 |
| Sonnet 5 | $0.00007 | $0.00149 |
| Haiku 4.5 | $0.00003 | $0.00075 |
Grade A, and why
architect 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 2d 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Architecture stage coordinator. Story to plan:
$ARGUMENTS
Step 0 — Detect API Platform area
Before invoking sub-agents, identify which area(s) the story touches:
resource→ new#[ApiResource], operations, subresourcesfilter→ search, sort, range, full-textprovider→ read transformation, multi-sourceprocessor→ write, async, CQRS bridgingsecurity→ voters, JWT, OIDC, CORSserialization→ groups, BackedEnum, Context, MaxDepthpagination→ partial, cursor, UUID v7versioning→ v1/v2, deprecation, Sunsetmcp→ AI agent exposuremutator→ uniform routePrefix, group injectionerrors→ RFC 7807, ErrorResourceuser→ User entity, /me, password hashingfile-upload→ MediaObject, multipart, S3performance→ cache tags, force_eager, FrankenPHPupgrade→ 3.x → 4.3 migration
Use Glob / Grep if unsure: check the names mentioned in the story against existing #[ApiResource] files.
Step 1 — Invoke api-platform-architect via Task
Pass:
- The story description
- The detected area(s)
- Surface (internal / public)
Capture the plan markdown returned between ===API-PLAN-BEGIN=== / ===API-PLAN-END=== markers.
Step 2 — Invoke api-platform-aligned-reviewer via Task
Pass the plan from step 1. Capture the ## Aligned-Reviewer note (preserve verbatim) block.
Step 3 — Invoke api-platform-appsec via Task
Pass the revised plan. Capture the ## AppSec findings (preserve verbatim — COORDINATOR: include this block as-is) table.
Step 4 — Synthesize
Synthesize the three views into a single self-contained plan. Preserve verbatim the ## Aligned-Reviewer note (preserve verbatim) block and the ## AppSec findings (preserve verbatim) table — do NOT collapse them into citations.
The plan header MUST include:
**Story shape:** feature | refactor | migration | hardening | docs-only
**API Platform area:** <detected area>
**Surface:** internal | public
**Sections that don't apply:** <list or "none">
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.
- 2d ago First seen · 83 lines · 35 tokens per session scan A 816571278cf1
architect 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 745 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
sonicjs-seo-blog
Generate a high-quality, SEO-optimized blog post for SonicJS on the topic: $ARGUMENTS.
finmind
You are a FinMind financial data assistant. Help the user query financial data from the FinMind API based on their natural language request.
execute-plan
Execute an implementation plan methodically with TDD and continuous validation.
generate-tests
Generate unit or integration tests for Go code following project patterns and coverage targets.
encryption
Encrypt outgoing emails with GPG/PGP so only the intended recipient can read them.
jaz-fa-review
Review the fixed asset register in Jaz — check depreciation, identify disposals and write-offs needed.