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 specsnl/agent-specs --skill php-checksgit clone --depth 1 https://github.com/specsnl/agent-specsWrote 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/specsnl/agent-specs/php-checks)<a href="https://agentmods.dev/skills/specsnl/agent-specs/php-checks"><img src="https://agentmods.dev/badge/skills/specsnl/agent-specs/php-checks/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/specsnl/agent-specs/php-checks"><img src="https://agentmods.dev/badge/skills/specsnl/agent-specs/php-checks.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 | $0.00132 | $0.01657 |
| Opus 5.5 | $0.00053 | $0.00663 |
| Sonnet 5.5 | $0.00026 | $0.00331 |
| Haiku 4.5 | $0.00013 | $0.00166 |
Grade A, and why
php-checks 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 — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PHP / Laravel checks
Prerequisite — Command execution rules apply. The
executing-commandsskill governs how every command in this skill must be run. Never runphp,composer,npm,node,docker, ordocker composedirectly on the host. Always usetask <task-name>; runtask --listfirst to see what this project actually exposes.
This skill is the stack-specific half of ci-green-check. That skill discovers which checks exist
(Taskfile + .github/workflows), drives the fix loop and writes the final report. This one provides
the environment setup and the exact commands.
Check that task is installed:
task --version 2>/dev/null || echo "task not installed"
If task is not installed, do not attempt to run commands directly. Stop and alert the user — task
is required. Ask the user to install it first (brew install go-task/tap/go-task on macOS).
Task naming in Specs Laravel projects
The Taskfile is split into namespaces (composer, artisan, npm, db, md, setup, e2e,
cleanup, worktrees). Wildcard tasks take the rest of the name as their argument, and everything
after -- is forwarded to the underlying command:
| Task | Runs |
|---|---|
task composer:script:<name> |
a composer script from composer.json (checkall, checkstyle, checktype, test, …) |
task composer:cmd:<name> |
a raw composer command (outdated, audit, why, …) |
task composer:install |
composer install inside the php service |
task composer:update |
composer update --with-all-dependencies |
task artisan:run:<command> |
php artisan <command> (colons included: artisan:run:migrate:fresh) |
task npm:script:<name> |
an npm script from package.json (build, test:e2e, …) |
task npm:cmd:<name> |
a raw npm command (audit, outdated, …) |
task md:checkstyle |
markdownlint over the repo |
task md:fixstyle |
fix table spacing, then markdownlint --fix |
task checkall |
composer:script:checkall + md:checkstyle |
task dc:run:<service> -- … |
last-resort escape hatch into a compose service |
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 First seen · 158 lines · 132 tokens per session scan A 5ae07d365c70
php-checks is a skill published in the GitHub repository specsnl/agent-specs (2 stars, last pushed 1mo ago), licensed MIT. It adds 132 tokens to every session and 1,657 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
integration-fixture
Add a .test integration fixture for one behavior.
behat-skill
Generates Behat BDD tests for PHP with Gherkin feature files and MinkContext for browser testing. Use when user mentions "Behat", "PHP BDD", "Mink", "behat.yml". Triggers on: "Behat", "PHP BDD", "Mink", "behat.yml", "FeatureContext PHP".
Behat BDD Testing
PHP BDD testing with Behat framework using Gherkin feature files, Mink browser extension, context classes, and Symfony integration for behavior-driven acceptance testing.
Codeception Testing
Expert-level Codeception testing skill for PHP applications. Covers acceptance, functional, and unit testing with the Actor pattern, BDD-style syntax, Page Objects, API testing, and database helpers.
Laravel Dusk Testing
Expert-level Laravel Dusk browser testing skill for PHP/Laravel applications. Covers Chrome-based E2E testing, browser assertions, Page Objects, component testing, authentication helpers, and database integration.
phel-lang
Building applications WITH Phel (Lisp that compiles to PHP). Triggers on .phel files, phel-config.php, phel CLI commands (init, run, repl, test, build), or requests to build a Phel app. Skip when working on the Phel compiler itself.