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 skills add autohandai/code-cli --skill architecture-breakdowngit clone --depth 1 https://github.com/autohandai/code-cliWrote 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/autohandai/code-cli/architecture-breakdown)<a href="https://agentmods.dev/skills/autohandai/code-cli/architecture-breakdown"><img src="https://agentmods.dev/badge/skills/autohandai/code-cli/architecture-breakdown/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/autohandai/code-cli/architecture-breakdown"><img src="https://agentmods.dev/badge/skills/autohandai/code-cli/architecture-breakdown.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00051 | $0.00434 |
| Opus 5.5 | $0.00020 | $0.00174 |
| Sonnet 5.5 | $0.00010 | $0.00087 |
| Haiku 4.5 | $0.00005 | $0.00043 |
Grade A, and why
architecture-breakdown 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 1mo 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.
What it actually says
Break the architecture down
Produce a map, not a summary. The reader should be able to open the right file for any responsibility without searching.
Survey
- Entry points: binaries,
main, CLI commands, HTTP routes, jobs, event handlers. Find them from the build config and manifests, then follow imports. - Layers and boundaries: what talks to what. Note the direction of dependencies and any cycles.
- State: where data lives (stores, caches, files), who owns each piece, and how it moves between layers.
- Cross-cutting concerns: config, auth, logging, errors, retries, feature flags, i18n.
- Hot spots: largest files, most-changed files (
git_log --statstyle viarun_command), most-imported modules. These are where changes hurt.
Write the breakdown
- One-paragraph shape: what the system is and its top three modules.
- Module table: module, responsibility, key files, depends on, depended on by, owner if known.
- Data flow: two or three end-to-end traces from entry point to effect, with file:line references.
- Boundaries to respect: the seams that keep layers separate and the rules the code already follows.
- Risks: cycles, god files, duplicated logic, missing tests, hidden global state, with evidence.
- Where to start for the change the user has in mind.
Keep every claim tied to a path. Mark inferences. Do not propose rewrites unless asked; the breakdown exists so changes fit the structure that is there.
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.
- 1mo ago First seen · 40 lines · 51 tokens per session scan A dda1e951d10c
architecture-breakdown is a skill published in the GitHub repository autohandai/code-cli (205 stars, last pushed today), licensed Apache-2.0. It adds 51 tokens to every session and 434 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-15.
Other skills, from other repositories
neuron-laravel-integration
Integrate Neuron AI agents into a Laravel 13 app the framework-native way — setup checklist (App\Neuron layout, config/services.php keys, one migration, NeuronServiceProvider, bootstrap/app.php exception mapping, neuron:evaluate), container-built agents bound per thread with for(), thread authorization, JSON and…
neuron-evaluation
Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…
neuron-agent
Create, configure, and extend Neuron AI agents in PHP using providers, tools, chat history, memory, and custom workflow nodes. Use for Neuron Agent implementation, configuration, conversation lifecycle, and input/output extensions.
neuron-rag
Implement RAG (Retrieval-Augmented Generation) with Neuron AI including vector stores, embeddings providers, document loaders, retrieval strategies, and metadata filtering. Use this skill whenever the user mentions RAG, retrieval, vector search, document retrieval, semantic search, knowledge bases, chat with…
neuron-structured-output
Design and implement structured output classes for Neuron AI agents using SchemaProperty attributes and validation rules. Use this skill when the user mentions structured output, JSON schema extraction, data validation, output classes, DTOs for AI responses, extracting structured data from LLM, or configuring property…
neuron-tool-approval
Implement human-in-the-loop tool approval flows with Neuron AI agents — gating risky tools behind approve/deny decisions, rendering approval UIs from chat history, submitting decisions, and building a single endpoint that handles both conversation turns and approval continuations. Use this skill whenever the user…