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 skills add albertoarena/laravel-truss --skill truss-schemagit clone --depth 1 https://github.com/albertoarena/laravel-trussWrote 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/skills/albertoarena/laravel-truss/truss-schema)<a href="https://agentmods.dev/skills/albertoarena/laravel-truss/truss-schema"><img src="https://agentmods.dev/badge/skills/albertoarena/laravel-truss/truss-schema/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.
<a href="https://agentmods.dev/skills/albertoarena/laravel-truss/truss-schema"><img src="https://agentmods.dev/badge/skills/albertoarena/laravel-truss/truss-schema.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00063 | $0.00920 |
| Opus 5.5 | $0.00025 | $0.00368 |
| Sonnet 5.5 | $0.00013 | $0.00184 |
| Haiku 4.5 | $0.00006 | $0.00092 |
Grade A, and why
truss-schema 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 1mo 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Grounding a schema change with Truss
Truss reads the live database structure: tables, columns, types, indexes, and foreign keys. It never returns row data. Read the structure before you change it, and confirm the change after you make it.
1. Read the structure you are about to change
Migration files are a history, not a state. They can be edited, squashed, or run out of order, and they do not show you what the database actually holds now. Read the database instead:
php artisan truss:export --format=llm --focus=orders --depth=1
--focus narrows to one table and its foreign-key neighbourhood, and --depth
controls how many hops of that neighbourhood come with it. Prefer this to a
whole-schema dump: on a large schema the full structure crowds out the task,
and the tables you need are almost always the focused table and its immediate
relations.
Use the whole schema only when the change genuinely spans it:
php artisan truss:export --format=llm --compact
--compact drops defaults and non-unique indexes. Add --connection= when the
application has more than one database and the change is not on the default.
Tables and columns may carry business meaning, declared in config or read from database comments. It arrives with the export, and it is often the difference between a plausible column name and the right one.
The llm format is for your own reading. When the export is for something
else, --format=dbml|json|csv|markdown|mermaid writes it in a form that tool
understands. Send it to a file with --output=, and --check writes nothing
and exits non-zero when that file is out of date, which is how a CI job catches
a schema that has drifted from its committed export.
When the reader is a person rather than a tool, --format=html --output=x.html
writes the whole diagram as one file that opens with no server and no install.
It is around 3.6 MB, --output is required, and it is a poor thing to read
yourself: use llm for that.
2. Check the ground before you build on it
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.
- 1mo ago Changed · +5 lines b1dae6b4ea8a
- 1mo ago First seen · 82 lines · 63 tokens per session scan A 3d0d31485473
truss-schema is a skill published in the GitHub repository albertoarena/laravel-truss (292 stars, last pushed 7d ago), licensed MIT. It adds 63 tokens to every session and 920 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
eloquent-patterns
Eloquent ORM best practices: query builders, scopes, relations, N+1 prevention, batch operations, soft deletes, model events, raw queries when needed. Apply when: writing or reviewing Eloquent queries and model interactions. Activated automatically by laravel-plugin/stack.md as a convention skill for the development…
laravel-migrations
Use when designing a database schema or managing Laravel 13 migrations — Schema Builder, columns, indexes, foreign keys, or seeders.
laravel-database-optimization
Laravel database optimization patterns. Use when writing Eloquent queries, creating migrations, configuring caching, debugging slow queries, or optimizing database performance. Triggers on tasks involving N+1 queries, indexing, Redis caching, pagination, or database transactions.
superpowers-sage:acorn-eloquent
Eloquent, model, migration, relationship, hasMany, belongsTo, belongsToMany, Acorn Eloquent, custom table, wpposts, wpusers, wppostmeta, factory, query scope, scopePublished, global scope, make:model, make:migration, lando acorn migrate, $fillable, $casts, $timestamps, $primaryKey, HasFactory, db:seed, seeder …
check-batch-processing
Analyzes PHP code for batch processing issues. Detects single-item vs bulk operations, missing batch inserts, individual API calls in loops, transaction overhead.
Laravel Migration Safety Review
Reviews Laravel migrations for destructive operations, change() dropping modifiers, locking index creation on large tables (PostgreSQL), and asymmetric down().