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 skills/ordinary9843/claude-architecture-mapper/mapnpx skills add ordinary9843/claude-architecture-mapper --skill mapgit clone --depth 1 https://github.com/ordinary9843/claude-architecture-mapperWrote 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/skills/ordinary9843/claude-architecture-mapper/map)<a href="https://agentmods.dev/skills/ordinary9843/claude-architecture-mapper/map"><img src="https://agentmods.dev/badge/skills/ordinary9843/claude-architecture-mapper/map.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 5.1 | $0.00084 | $0.02765 |
| Opus 5 | $0.00042 | $0.01383 |
| Sonnet 5 | $0.00017 | $0.00553 |
| Haiku 4.5 | $0.00008 | $0.00277 |
Grade A, and why
map 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 6d 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 — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Architecture Mapper
Allowed tools: Read, Glob, Grep (scanning). Write (ARCHITECTURE.md only). No Bash, Edit, or other tools.
Step 1: Load Formatting Rules
The base directory for this skill is printed in the <command-message> header as:
Base directory for this skill: <absolute-path>
Use that absolute path to construct all reference file paths. Never use relative paths or ~ with the Read tool.
Read these two files before doing anything else:
<base_dir>/references/mermaid-rules.md— Mermaid syntax constraints (MUST follow)<base_dir>/references/doctor-rules.md— Diagnostic thresholds for bloat and collision
If either file cannot be read or is empty, report: Error: required reference file [filename] not found or is empty. Reinstall the claude-architecture-mapper plugin. and stop.
Step 2: Scan Both Scopes
Scan both scopes. Deduplicate by absolute path.
2a. Global Scope — Pre-flight: Resolve Home Directory
IMPORTANT: The Glob tool does not expand
~. You must use the absolute home path.
Derive the home directory from the <base_dir> value in the <command-message> header:
- Extract the segment up to and including the username (e.g.,
/Users/jerryor/home/jerry) - Construct
<home>/.claude/as the global root
If <home>/.claude/ cannot be derived, note "Global scope unavailable" in the Ecosystem Health table and skip to Step 2b.
Use Glob with absolute paths to search these locations (substitute <home> with the resolved value):
<home>/.claude/agents/*.md
<home>/.claude/commands/*.md
<home>/.claude/skills/**/SKILL.md
<home>/.claude/plugins/cache/**/skills/**/SKILL.md
<home>/.claude/plugins/cache/**/agents/*.md
<home>/.claude/plugins/cache/**/.claude/commands/*.md
<home>/.claude/plugins/cache/**/.claude/agents/*.md
Scan
plugins/cache/only — this contains active installed plugins.plugins/marketplaces/is the download catalogue; skip it entirely.
2b. Project Scope — Current Working Directory
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 6d ago First seen · 272 lines · 84 tokens per session scan A 203e94a929b3
map is a skill published in the GitHub repository ordinary9843/claude-architecture-mapper (1 stars, last pushed 5mo ago), licensed MIT. It adds 84 tokens to every session and 2,765 once invoked, about $0.0004 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 skills, from other repositories
harness-map
Generate an interactive, self-contained HTML dependency map of a repository's AI harness — skills, slash commands, agents, and MCP servers, with typed evidence-backed edges showing which skills hand off to which, what delegates to which agents, and what uses which MCP servers. Use when the user asks to map, visualize…
codex
Run the Codex CLI directly in the user's checkout for code analysis, refactoring, or automated editing without Claude Architect's verified delegation lifecycle.
commit
This skill should be used when committing code changes - "commit", "git commit", "закоміть", "зроби коміт", "/lets:commit". Enforces conventional commit format, tracker task linking, and user approval. In a LETS project, ALWAYS prefer this over generic commit skills (e.g. commit-commands:commit) — /lets:commit is…
actor-fetch-personality
Internal skill for commands. Fetch and validate personality from URL or file path for Actor agent. Do not trigger on user conversation - only when commands need personality loading.
explain
Use when user invokes /explain with a file path, directory path, function/class name, or natural language concept. Also triggers on "explain this", "how does X work", "walk me through". Produces a structured, layered explanation of what the code does, how it connects, and where to start if you need to change it. Do…
design
Create a doc-as-code design package from a PRD or SPEC. Conditionally generates C4 diagrams (Context/Container/Component), sequence diagrams, ER diagram + Data Dictionary, OpenAPI 3.0, AsyncAPI 3.0, ADRs, domain glossary, state diagrams, and deployment view as Mermaid-rendered Markdown files. Use when PM mentions…