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/friendsofhyperf/components/agents-mdgit clone --depth 1 https://github.com/friendsofhyperf/componentsWhat 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 | $0.01674 | $0.01674 |
| Opus 5 | $0.00837 | $0.00837 |
| Sonnet 5 | $0.00335 | $0.00335 |
| Haiku 4.5 | $0.00167 | $0.00167 |
Grade A, and why
components 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 2d 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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines for AI Agents
Scope and Source of Truth
- This repository is the source monorepo for 49 independently installable
friendsofhyperf/*Composer packages. - Treat component source, component
composer.jsonfiles, and tests as authoritative. Do not invent public APIs, configuration keys, defaults, or framework behavior from documentation alone. - Read the target component's
composer.json, public source, tests found withrg, README, and published configuration before changing behavior or documentation. - Preserve user changes and unrelated diffs. Do not revert, reformat, or regenerate files outside the requested scope.
- Do not create commits, push branches, split repositories, or publish releases unless the user explicitly requests it.
Repository Model
src/<component>/: independent kebab-case Composer packages with PSR-4 namespaces underFriendsOfHyperf\*.tests/<Component>/: shared Pest tests. Groups are registered intests/Pest.php; not every component has a group.docs/{en,zh-cn,zh-hk,zh-tw}/: four synchronized VitePress locales. Simplified Chinese is the translation source.types/: PHP stubs checked independently at PHPStan max level.bin/: maintenance, generation, repository split, and release scripts.- Root
composer.json: generated aggregation of component dependencies, PSR-4 mappings, autoload files, ConfigProviders, andreplaceentries.
Most components expose a src/ConfigProvider.php that registers Hyperf dependencies,
listeners, aspects, commands, or publishable resources. Some components are framework-
independent libraries and intentionally have no ConfigProvider.
Change Workflow
- Inspect
git status --shortand identify the exact allowed write scope. - Read the target component's
composer.json, relevant source, tests, README, and docs. - Search with
rgfor usages, contracts, configuration keys, and existing tests. - Make the smallest change consistent with local patterns.
- Add or update focused tests for public behavior changes.
- Update affected README and documentation snippets without adding unverified claims.
- Run targeted verification first, then broader checks proportional to the change.
- Finish with
git diff --check,git status --short, and a path-scoped diff review.
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.
- 2d ago First seen · 166 lines · 1,674 tokens per session scan A a8325b520bcf
components AGENTS.md is an instructions file published in the GitHub repository friendsofhyperf/components (115 stars, last pushed 11d ago), licensed MIT. It adds 1,674 tokens to every session, about $0.0084 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
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
buildNext
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
Instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
Instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.