agentmods.dev

solidifier AGENTS.md

Repository guidance for Solidifier, a skill that helps coding agents apply SOLID design principles. It explains the repository layout and how its copies for different agents must stay synchronized.

In plain words
What is it for?
Use it when editing Solidifier's Claude Code, OpenCode, GitHub Copilot, or Codex versions, especially when syncing shared skill content.
Why use it?
It gives agents the project context and prevents shared changes from being made in only one agent-specific copy.

Instructions file for CodexOpenCode

37 1mo ago A scan 414 tokens original MIT
View the source file FernandoJRR/solidifier
Install

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.

agentmods
npx agentmods add instructions/fernandojrr/solidifier/agents-md
Clone the repo
git clone --depth 1 https://github.com/FernandoJRR/solidifier

Made for: Codex, OpenCode.

Per session 414 This file is loaded in full into every session.
When invoked 414 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00414 $0.00414
Opus 5 $0.00207 $0.00207
Sonnet 5 $0.00083 $0.00083
Haiku 4.5 $0.00041 $0.00041

Measured 2d ago against content hash 0846fc17531f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

solidifier 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.

AGENTS.md · 44 lines

What it actually says

AGENTS.md

This file provides context for AI agents working inside this repository.

What this repo is

solidifier is a multi-agent SOLID principles skill. It ships one self-contained copy of the skill per agent so each drops straight into the directory that agent scans.

Structure

  • claude-code/plugins/solidifier/ — Claude Code plugin and skill
  • opencode/solidifier/ — OpenCode skill
  • copilot/solidifier/ — GitHub Copilot skill
  • codex/solidifier/ — OpenAI Codex skill
  • install.sh — installs the right copy for a given agent
  • sync.sh — propagates shared content across all four copies

Rules

  • Never edit only one agent copy and leave the others behind. Run sync.sh after any change to shared skill content.
  • Do not modify .solidifier.json — that file lives in the project being worked on, not here.
  • Do not add abstraction for its own sake. The prime directive of this skill is restraint — apply it to the repo itself.
  • Agent-specific files (agents/openai.yaml, frontmatter variants) are intentionally not synced. Leave them alone unless you are targeting that specific agent.

Skills available in this repo

This repo does not install skills into itself. It is a skill.

AI-generated contributions

If you are an AI agent generating a PR against this repository:

  • You MUST add the label ai-generated to the PR.

  • You MUST include the following block at the top of the PR description:

    > ⚠️ AI-GENERATED PR — requires human review before merge.

  • Do NOT auto-merge. Do NOT approve your own PR.

  • A human maintainer must review and approve all AI-generated changes before they are merged.

Failure to follow these rules does not block the PR from being submitted, but it will be closed without review if the label and notice are missing.

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. 2d ago First seen · 44 lines · 414 tokens per session scan A 0846fc17531f

Subscribe to this mod's changes

solidifier AGENTS.md is an instructions file published in the GitHub repository FernandoJRR/solidifier (37 stars, last pushed 1mo ago), licensed MIT. It adds 414 tokens to every session, about $0.0021 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.

Code reviewagent-skillsclaude-codeclaude-skillscode-qualitycodex
Related

Other instructions, from other repositories

agent-skills AGENTS.md

Instructions for AsyrafHussin/agent-skills, covering agent skills repository, skills overview, usage and contributing.

AsyrafHussin/agent-skills · 533 tokens

dxkit CLAUDE.md

Instructions for vyuh-labs/dxkit, covering claude.md — dxkit development rules, architecture rules, 1. tool invocation goes through the registry, 2. never duplicate tool invocation logic and 3. language facts come from detect.ts.

vyuh-labs/dxkit · 24,268 tokens

arai CLAUDE.md

Instructions for taniwhaai/arai, covering claude.md — arai, commands, architecture, prompt-collector module (src/promptcollector.rs) and extending the match pipeline.

taniwhaai/arai · 3,491 tokens

evolve-loop GEMINI.md

Instructions for mickeyyaya/evolve-loop, covering project instructions (gemini cli), skill discovery, runtime adapter (tier-1-hybrid), tool name translation and invariants (apply to gemini context too).

mickeyyaya/evolve-loop · 801 tokens

anchorlaw AGENTS.md

Instructions for unknowbug/anchorlaw, covering anchorlaw 项目 agents.md（项目级常驻指令）, 〇、开始工作前（每个 session 必做）, 一、项目定位（一句话）, 二、主工作流（judge 驱动流水线，v0.11） and 三、技能与宿主入口.

unknowbug/anchorlaw · 2,141 tokens

devkit CLAUDE.md

Instructions for 5uck1ess/devkit, covering claude.md, layout, architectural invariants, conventions and fixing this file.

5uck1ess/devkit · 1,620 tokens