agentmods.dev

php-agents-boilerplate: Skill for Claude Code

.claude/skills/work-conventions/SKILL.md

work-conventions is a skill for Claude Code from velesnitski/php-agents-boilerplate. It costs 16 tokens per session (445 once invoked), scanned A, original, MIT.

A shared set of team rules for code, Git commits, documentation, reviews, and communication. It includes checks for PHP formatting, static analysis, tests, migrations, and sensitive information.

In plain words
What is it for?
Use it when planning changes, naming branches, writing commits, reviewing code, creating database migrations, or running project checks.
Why use it?
It gives contributors consistent standards and catches common problems before code is pushed or reviewed.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

This is velesnitski/php-agents-boilerplate's own configuration. It tells Claude Code how to work on php-agents-boilerplate itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything php-agents-boilerplate configures →

not rated 2repo changed 11d ago A scan 16 tokens original MIT
View source ↗ velesnitski/php-agents-boilerplate
Reuse

Borrowing it

Nothing to install: this file belongs to velesnitski/php-agents-boilerplate. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/velesnitski/php-agents-boilerplate/main/.claude/skills/work-conventions/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/velesnitski/php-agents-boilerplate

Made for: Claude Code.

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.

agentmods badge for work-conventions

README.md
[![agentmods](https://agentmods.dev/badge/skills/velesnitski/php-agents-boilerplate/work-conventions/github.svg)](https://agentmods.dev/skills/velesnitski/php-agents-boilerplate/work-conventions)
Your own site
<a href="https://agentmods.dev/skills/velesnitski/php-agents-boilerplate/work-conventions"><img src="https://agentmods.dev/badge/skills/velesnitski/php-agents-boilerplate/work-conventions/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.

agentmods 80×15 button for work-conventions

Your own site · 80×15
<a href="https://agentmods.dev/skills/velesnitski/php-agents-boilerplate/work-conventions"><img src="https://agentmods.dev/badge/skills/velesnitski/php-agents-boilerplate/work-conventions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 16 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 445 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00016 $0.00445
Opus 5.5 $0.00006 $0.00178
Sonnet 5.5 $0.00003 $0.00089
Haiku 4.5 $0.00002 $0.00044

Measured 11d ago against content hash c1737bd62e79, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

work-conventions 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 11d 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.

.claude/skills/work-conventions/SKILL.md · 49 lines

What it actually says

Work Conventions

Git

  • Branch naming: feature/TICKET-123-short-desc, fix/TICKET-456-short-desc, hotfix/...
  • Commit messages: imperative mood, reference ticket ID (e.g. PROJ-178: add subscription endpoint)
  • One logical change per commit – don't mix refactoring with features
  • Never force-push to shared branches

Code Style

  • Laravel Pint (PSR-12) – run ./vendor/bin/pint before committing
  • Larastan / PHPStan – run ./vendor/bin/phpstan analyse for static analysis
  • Check both before pushing: make check

Code Review Checklist

  • Tests pass (make test)
  • Pint clean (./vendor/bin/pint --test)
  • PHPStan passes
  • No new warnings or deprecations
  • No hardcoded credentials, IPs, or domains
  • No env() outside config files
  • Migrations have down() method
  • API changes documented
  • No sensitive data in code or commit messages

Architecture Decision Records (ADR)

  • Every significant decision gets an ADR in docs/adr/
  • Format: NNN-short-title.md (e.g. 001-uuid-generation-from-password.md)
  • Every commit that introduces architectural changes must include the ADR
  • ADR should explain: context, decision, consequences

Communication

  • Agent output must be structured (use the defined output format)
  • Flag blockers immediately – don't silently skip steps
  • Destructive actions require explicit user confirmation
  • Always include a rollback plan for production changes

Sensitive Data

  • Never commit credentials, tokens, API keys, or passwords
  • Never hardcode IPs, domains, or internal hostnames
  • Use .env for all environment-specific values
  • Scan for leaks before pushing to remote
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.

  1. 11d ago Changed · +1 lines c1737bd62e79
  2. 2mo ago First seen · 48 lines · 16 tokens per session scan A 5fdab799cec1

Subscribe to this mod's changes

work-conventions is a skill published in the GitHub repository velesnitski/php-agents-boilerplate (2 stars, last pushed 11d ago), licensed MIT. It adds 16 tokens to every session and 445 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 2026-08-31.

CommitsGit and workflow
Related

work-conventions compared with skills from other repositories

work-conventions next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
work-conventionsvelesnitski/php-agents-boilerplateSkill211d agoMITA16Claude Code
create-prprisma/ormSkill48kyesterdayApache-2.0A48Claude Code, Codex
git-commitThinkInAIXYZ/deepchatSkill6.4kyesterdayApache-2.0A15Claude Code, Codex
repo-syncdavidondrej/skillsSkill4.3k3d agoMITA25Claude Code, Codex
engineer-bot-opsmakecindy/cindySkill9.3kyesterdayApache-2.0A57Claude Code, Codex
mcore-split-prNVIDIA/skillsSkill3.9kyesterdayApache-2.0A25Claude Code
git-commit-writermergisi/awesome-openclaw-agentsSkill4.1k2d agoMITA53Claude Code, Codex