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 instructions/vilnacrm-org/php-service-template/agents-mdgit clone --depth 1 https://github.com/VilnaCRM-Org/php-service-templateWrote 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/instructions/vilnacrm-org/php-service-template/agents-md)<a href="https://agentmods.dev/instructions/vilnacrm-org/php-service-template/agents-md"><img src="https://agentmods.dev/badge/instructions/vilnacrm-org/php-service-template/agents-md.svg" alt="Measured on agentmods" 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 | $0.00513 | $0.00513 |
| Opus 5 | $0.00257 | $0.00257 |
| Sonnet 5 | $0.00103 | $0.00103 |
| Haiku 4.5 | $0.00051 | $0.00051 |
Grade A, and why
php-service-template AGENTS.md 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 4d 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
php-service-template is a Symfony and API Platform microservice template for VilnaCRM services. It targets PHP 8.2+, uses Doctrine ORM migrations, ships OpenAPI and GraphQL snapshots under .github/, and keeps architecture aligned with Hexagonal, DDD, and CQRS patterns.
This file is documentation-only guidance for coding assistants. It does not add runtime AI agent features to the template.
Mandatory Workflow For AI Agents
Before making non-trivial changes:
- Read
.claude/skills/AI-AGENT-GUIDE.md. - Read
.claude/skills/SKILL-DECISION-GUIDE.md. - Open the matching skill file under
.claude/skills/<skill>/SKILL.md. - Follow the workflow in that skill before claiming the task is complete.
Working Rules
- Use
maketargets first. If a target does not exist, usedocker compose exec php .... - Do not run PHP tooling directly on the host when the repository already wraps it in Docker.
- Fix code to satisfy checks. Do not weaken
phpinsights.php,deptrac.yaml, PHPUnit coverage setup, or Infection settings to make failures disappear. - Keep Domain code framework-free. Validation, Doctrine mapping, and API Platform metadata belong outside Domain classes.
- When API behavior changes, regenerate
.github/openapi-spec/spec.yamland.github/graphql-spec/spec. - When architecture changes, update
workspace.dsl.
Verification Baseline
For application changes, run the relevant parts of this stack:
make composer-validate
make check-requirements
make check-security
make phpcsfixer
make psalm
make psalm-security
make phpinsights
make deptrac
make setup-test-db
make unit-tests
make integration-tests
make behat
make infection
make generate-openapi-spec
make generate-graphql-spec
For documentation-only changes, run the smallest relevant subset and rely on GitHub Actions for the full matrix.
Skill Inventory
This template currently ships these Claude skills:
api-platform-crudci-workflowcomplexity-managementdeptrac-fixerdocumentation-syncload-testingopenapi-developmentquality-standardsstructurizr-architecture-synctesting-workflow
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.
- 4d ago First seen · 65 lines · 513 tokens per session scan A b18d4f811662
php-service-template AGENTS.md is an instructions file published in the GitHub repository VilnaCRM-Org/php-service-template (24 stars, last pushed 2mo ago), licensed CC0-1.0. It adds 513 tokens to every session, about $0.0026 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 2026-08-30.
Other instructions, from other repositories
instructor-php AGENTS.md
AGENTS.md instructions for cognesy/instructor-php, covering key reference files, monorepo root, individual subpackages, code style and agents package style.
marko CLAUDE.md
Instructions for marko-php/marko, covering marko framework, core principles, commands, run all tests including destructive integration tests and run with coverage.
vizra-adk CLAUDE.md
Instructions for vizra-ai/vizra-adk, covering vizra adk - laravel ai agent development kit, project overview, key concepts, agents and tools.
FreshRSS php.instructions.md
Instructions for FreshRSS/FreshRSS, covering php files and autoloader.
FreshRSS _general.instructions.md
Instructions for FreshRSS/FreshRSS, covering freshrss general instructions, kiss principle: keep it simple, style and formatting and spelling.
FreshRSS css.instructions.md
Instructions for FreshRSS/FreshRSS, covering css files and right-to-left css files.