Borrowing it
Nothing to install: this file belongs to albertoarena/laravel-truss. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/albertoarena/laravel-truss/main/.claude/commands/code-smell.mdgit 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/commands/albertoarena/laravel-truss/code-smell)<a href="https://agentmods.dev/commands/albertoarena/laravel-truss/code-smell"><img src="https://agentmods.dev/badge/commands/albertoarena/laravel-truss/code-smell/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/commands/albertoarena/laravel-truss/code-smell"><img src="https://agentmods.dev/badge/commands/albertoarena/laravel-truss/code-smell.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00018 | $0.01781 |
| Opus 5.5 | $0.00007 | $0.00712 |
| Sonnet 5.5 | $0.00004 | $0.00356 |
| Haiku 4.5 | $0.00002 | $0.00178 |
Grade A, and why
code-smell 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 29d 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are auditing the codebase in the current working directory for code smells and architectural problems. The goal is an audit the maintainers can act on. Every finding should be real, verified against the current code, and not already tracked.
Inputs. Use these defaults unless the user overrides them:
- Tracker file:
AUDIT.mdat the repo root. Create it if it's missing; add to new file if it exists. - Scope: all first-party source. Exclude vendored, generated and build output (
vendor/,node_modules/,dist/,build/, lockfiles, migrations' generated SQL, compiled assets). - Changes allowed: the tracker file only. Don't edit source or tests, and don't commit.
Before you start
Learn the project before judging it.
- Read the guidance files that exist:
CLAUDE.md,AGENTS.md,CONTRIBUTING.md, the README's architecture or contributing sections, and ADRs ordocs/architecture*. - Read the linter, formatter and type-checker configs (for example
phpstan.neon,pint.json,.eslintrc*,tsconfig.json,pyproject.toml,rector.php,biome.json). Their rules, and especially their ignores, show deliberate choices. - Read the dependency manifest (
composer.json,package.json,go.mod,Cargo.toml,pyproject.toml) so you know the framework, and don't flag its idioms as smells. - Run
git log --oneline -20andgit statusso you know what just changed and what is uncommitted. Trust only what you read in this session. - If the tracker file exists, read it in full. Anything already in it, including items marked won't-do or rejected and their reasons, is out of scope. Don't re-report it in different words.
From these, write down for yourself the project's deliberate conventions. Examples: "no final classes", "immutable value objects", "functions over classes", "errors as return values", "barrel files per module". Treat each one as a design decision, not a smell, but do report code that breaks it. When a convention is only implied by consistent practice across the codebase, follow it too.
Then map the structure: top-level modules or packages, entry points (HTTP routes, CLI commands, jobs, exported public API), and the rough size of each area.
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.
- 29d ago First seen · 97 lines · 18 tokens per session scan A 5acfb2b61746
code-smell is a command published in the GitHub repository albertoarena/laravel-truss (291 stars, last pushed 4d ago), licensed MIT. It adds 18 tokens to every session and 1,781 once invoked, about $0.0001 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 2026-09-26.
Other commands, from other repositories
pg-indexes
Review unused indexes that are safe to drop (pgbot).
dba
Invoke the Database Administrator for schema design, indexing, query tuning, safe migrations, replication, and backups (Postgres/MySQL OLTP).
data
Invoke the Data Engineer for ETL/ELT, dbt, warehouses, streaming, orchestration, and data quality.
pn-audit-data
Design or review database schema — normalization, indexing strategy, migration plan, and data model decisions. Surgical command for database design. Use standalone or as part of pn-backend-audit.
db-object-audit-review
Internal RA review of db object audit.
dbt-carveout-relocate-review
Human adjudication gate for relocated carve-out dbt models.