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/thejacksoncode/agent-architecture/claude-mdgit clone --depth 1 https://github.com/TheJacksonCode/Agent-ArchitectureWhat 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 | $0.00610 | $0.00610 |
| Opus 5 | $0.00305 | $0.00305 |
| Sonnet 5 | $0.00122 | $0.00122 |
| Haiku 4.5 | $0.00061 | $0.00061 |
Grade A, and why
Agent-Architecture 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 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md - Agent Architecture Designer
What is this project
Single-HTML visual designer and encyclopedia for multi-agent AI systems. 35 agents, 42 team presets, PL/EN bilingual. Zero dependencies.
Primary purpose: education - understand how each agent thinks, what it does, how teams collaborate, and what it costs before you spend a token.
Current version
v32 (build v32.16 "Universal Bilingual") - 27,478 lines, 5.7 MB, 35 agents, 42 presets, full PL/EN encyclopedia parity.
- Source:
v32/AGENT_TEAMS_CONFIGURATOR_v32.html - Live demo:
index.html(root, mirrors v32 for GitHub Pages)
Agent infrastructure
The project includes a complete agent orchestration layer for Claude Code:
| Component | Location | Count | Purpose |
|---|---|---|---|
| Skills | ~/.claude/skills/*.md |
35 | Individual agent prompts (global) |
| Commands | ~/.claude/commands/*.md |
42 | Team preset orchestration (global) |
| Catalog | ~/.claude/PRESET_CATALOG.md |
1 | Auto-routing: task description -> best preset |
| Routing | ~/.claude/CLAUDE.md |
1 | 7-line routing instruction (always loaded) |
How it works: User describes a task -> Claude reads the catalog -> proposes the best preset -> user confirms -> preset loads skill files for each agent -> agents run as subagents.
Regeneration from source HTML:
node generate_skills.js # 35 skill files from AGENT_EDU_PL
node generate_commands.js # 42 command files from PR data
Versioning
- Each major version = its own folder with a single HTML file
- Current shipped: v32
- Historical builds (v1-v32.15) are preserved in git history
File map
index.html # Live demo (= v32 copy)
v32/ # Current version
AGENT_TEAMS_CONFIGURATOR_v32.html
docs/ # Architecture documentation
SKILLS_ARCHITECTURE.md # 35 agents: format, fields, model routing
ROUTING_SYSTEM.md # Auto-routing: catalog, token budget, flow
screenshots/
Research/research-preset-routing/ # Research reports (R1-R7 + synthesis)
generate_skills.js # Regenerate skills from HTML
generate_commands.js # Regenerate commands from HTML
VERSIONS.md # Full version history (v1-v32)
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 · 63 lines · 610 tokens per session scan A 98be82b399b7
Agent-Architecture CLAUDE.md is an instructions file published in the GitHub repository TheJacksonCode/Agent-Architecture (74 stars, last pushed 4mo ago), licensed MIT. It adds 610 tokens to every session, about $0.0030 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
takt CLAUDE.md
Instructions for nrslib/takt, covering claude.md, project overview, development commands, test pool behavior (worth knowing before "fixing" flakes) and cli surface.
takt AGENTS.md
Instructions for nrslib/takt, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.
oh-my-subagents AGENTS.md
Instructions for ringlochid/oh-my-subagents, covering oh my subagents coding agent contract, product purpose, design philosophy, principles and authority split.
dos-kernel AGENTS.md
Instructions for anthony-chaudhary/dos-kernel, covering what dos is (the 30-second version), run it yourself first — the 60-second proof, when the user asks you about dos (the consumer moves), build, test, and check your work and the layout in one screen.
dos-kernel CLAUDE.md
Instructions for anthony-chaudhary/dos-kernel, covering dos — the dispatch operating system, the layering — keep these apart, the syscall abi, install & test and dos on dos — dogfood the kernel here.
PuPu AGENTS.md
Instructions for haoxiang-xu/PuPu, covering gitnexus — code intelligence, always do, never do, resources and cli.