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/inetgas/arch-compiler/agents-mdgit clone --depth 1 https://github.com/inetgas/arch-compilerWhat 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 | $0.01204 | $0.01204 |
| Opus 5 | $0.00602 | $0.00602 |
| Sonnet 5 | $0.00241 | $0.00241 |
| Haiku 4.5 | $0.00120 | $0.00120 |
Grade A, and why
arch-compiler 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Guide — Architecture Compiler
Read this before using any skill in this repo.
Repo Contract
arch-compiler/
├── README.md
├── AGENTS.md
├── README-AGENTS.md
├── tools/ <-- read-only for agents
├── schemas/ <-- read-only for agents
├── config/ <-- read-only for agents
├── scripts/ <-- read-only for agents
├── patterns/ <-- read-only for agents
└── skills/
├── using-arch-compiler/
│ └── SKILL.md
├── compiling-architecture/
│ └── SKILL.md
└── implementing-architecture/
└── SKILL.md
The important split is:
AGENTS.md= canonical global agent rulesskills/using-arch-compiler/SKILL.md= entrypoint/router skillskills/compiling-architecture/SKILL.md= compile and finalise architectureskills/implementing-architecture/SKILL.md= implement an already-approved architecture
What This Repo Does
Given a YAML spec, the compiler selects applicable architecture patterns and produces deterministic architecture decision artifacts. Same input produces the same output every time. No LLM inference happens inside the compiler.
Which Skill To Use
| Situation | Skill |
|---|---|
| User wants help choosing the correct architecture workflow | skills/using-arch-compiler/SKILL.md |
| User wants to compile a spec, select patterns, or finalise an architecture | skills/compiling-architecture/SKILL.md |
User wants to implement a system from an approved docs/architecture/ folder |
skills/implementing-architecture/SKILL.md |
If you are unsure, start with skills/using-arch-compiler/SKILL.md.
Read-Only Boundaries
Agents may read any file in this repo.
Unless the human explicitly asks for compiler-maintenance work in this repo:
- treat
tools/as read-only - treat
schemas/as read-only - treat
config/as read-only - treat
patterns/as read-only
Agents may:
- run the compiler
- run audit tools
- run tests
Agents may not, unless explicitly directed by the human:
- edit an existing pattern in
patterns/ - edit
schemas/canonical-schema.yaml - edit
schemas/pattern-schema.yaml - edit
config/defaults.yaml - place a newly authored pattern directly into
patterns/just because the human asked to "author" it
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 · 117 lines · 1,204 tokens per session scan A 237b974e80b4
arch-compiler AGENTS.md is an instructions file published in the GitHub repository inetgas/arch-compiler (10 stars, last pushed 3mo ago), licensed MIT. It adds 1,204 tokens to every session, about $0.0060 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
mcp-adr-analysis-server copilot-instructions.md
Instructions for tosin2013/mcp-adr-analysis-server, covering mcp adr analysis server - ai coding agent instructions, project overview, critical technical conventions, esm-only module system and typescript configuration.
boffin copilot-instructions.md
Instructions for MicSm/boffin, covering parselfire core portable routing contract, default workflow, stage pipeline and pre-flight review.
ai-software-architect AGENTS.md
AGENTS.md instructions for codenamev/ai-software-architect, covering agents.md - ai software architect framework, project overview, framework development setup, repository structure and installation for framework development.
loadbearing AGENTS.md
AGENTS.md instructions for andypgray/loadbearing, covering loadbearing — architecture for agents, the self-hosting principle, architecture (loadbearing), layers and rules.
ai-software-architect CLAUDE.md
Claude Code instructions for codenamev/ai-software-architect, covering claude.md - claude code integration, core framework documentation, about this structure, claude code-specific features and 1. claude skills integration.
boffin AGENTS.md
Instructions for MicSm/boffin, covering parselfire core portable routing contract, default workflow, stage pipeline and pre-flight review.