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/thiagofmaranhao/tech-toolkit/claude-mdgit clone --depth 1 https://github.com/thiagofmaranhao/tech-toolkitWrote 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/thiagofmaranhao/tech-toolkit/claude-md)<a href="https://agentmods.dev/instructions/thiagofmaranhao/tech-toolkit/claude-md"><img src="https://agentmods.dev/badge/instructions/thiagofmaranhao/tech-toolkit/claude-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 | $0.00719 | $0.00719 |
| Opus 5 | $0.00360 | $0.00360 |
| Sonnet 5 | $0.00144 | $0.00144 |
| Haiku 4.5 | $0.00072 | $0.00072 |
Grade A, and why
tech-toolkit CLAUDE.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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — tech-toolkit · Thiago Maranhão
Language
All content in this repository — documentation, README files, artifact descriptions, and AI-generated output — must be written in English. Code was always in English; now documentation follows the same rule.
Repository context
Public repository by Thiago Maranhão (Software Architecture Manager) with engineering artifacts extracted from real production environments — templates, prompts, and practical examples across AI, distributed systems, and software architecture.
Artifacts are technical references first, content second: each one was validated in a real context before being published. Many are linked to posts on LinkedIn and Medium, but the repository stands on its own as a reference and reuse source.
Open for community use and contribution.
Structure
/
├── README.md # Repository and author overview
├── adr/ # Templates and instructions for Architecture Decision Records
├── prompts/ # Reusable prompts for AI tools (LLMs, Gems, etc.)
├── claude-code/ # Skills and hooks for Claude Code
├── dotnet/ # Production .NET/C# code examples
└── distributed-systems/ # Distributed systems patterns and examples
The structure grows as new artifacts are published. Each folder represents a technical domain, not a file type.
Rules for new artifacts
- Each folder groups artifacts by domain/context, not by file type
- Every artifact must be originated or validated in production — no purely theoretical content
- Every folder must have a
README.mdwith:- What it is and what it's for
- Production context where it was used (without exposing sensitive data)
- How to use it
- "Origin and references" section with links to posts that originated or mention the artifacts
- Artifacts must be self-contained — someone arriving from a post link should be able to use them without additional context
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 · 75 lines · 719 tokens per session scan A 43beb2ed7497
tech-toolkit CLAUDE.md is an instructions file published in the GitHub repository thiagofmaranhao/tech-toolkit (5 stars, last pushed 2mo ago), licensed MIT. It adds 719 tokens to every session, about $0.0036 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 2026-08-31.
Other instructions, from other repositories
adrkit AGENTS.md
Instructions for mbeacom/adrkit, covering adrkit, visual adr graph, inbound @adr markers (v0.5.0: explain, check, and ci), the spec kit extension (packages/adapters/spec-kit) and adr queue.
codebase-intel CLAUDE.md
Instructions for MutharasuArchunan13/codebase-intel, covering codebase intel — project claude.md, project overview, tech stack, architecture and module responsibilities.
adrkit copilot-instructions.md
Instructions for mbeacom/adrkit, covering adrkit — github copilot and github copilot specifics.
adrkit CLAUDE.md
Instructions for mbeacom/adrkit, covering adrkit — claude code and claude code specifics.
adr copilot-instructions.md
Instructions for zircote-plugins/adr, covering copilot instructions, project overview, key components, plugin structure and development guidelines.
docflow AGENTS.md
Instructions for EvolveHQ/docflow, covering agents.md, what this repository is, repository structure, hard rules when editing adrs and domain-specific hard rules.