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 Jacoby6000/Smithplates --skill analyze-codebase-architecturegit clone --depth 1 https://github.com/Jacoby6000/SmithplatesWrote 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/jacoby6000/smithplates/analyze-codebase-architecture)<a href="https://agentmods.dev/skills/jacoby6000/smithplates/analyze-codebase-architecture"><img src="https://agentmods.dev/badge/skills/jacoby6000/smithplates/analyze-codebase-architecture/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/jacoby6000/smithplates/analyze-codebase-architecture"><img src="https://agentmods.dev/badge/skills/jacoby6000/smithplates/analyze-codebase-architecture.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 | $0.00076 | $0.01003 |
| Opus 5.5 | $0.00030 | $0.00401 |
| Sonnet 5.5 | $0.00015 | $0.00201 |
| Haiku 4.5 | $0.00008 | $0.00100 |
Grade A, and why
analyze-codebase-architecture 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 2mo 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analyze Codebase Architecture
Reverse-engineer an existing codebase into a current Conceptual Architecture
Document (CAD). Capture what is, with evidence — not what should be. Read the
shared schema at .ai-doc-reference/cad-contract.md (repo root) before emitting one;
producing a valid CAD with Kind: current is what lets
plan-architecture-refactor diff it against a target later.
Describe the system faithfully. Do not redesign, fix, or editorialize beyond the
Risks & Trade-offs section. Every structural claim must cite evidence as
path/to/file.ext:Symbol.
Inputs required (do not guess)
- Codebase scope: which repo/paths are in scope (and any out of scope).
- Commit/ref: the state being analyzed (record it in
Source).
If scope is unclear, ask. Where the code's intent is ambiguous, record it in Open Questions rather than guessing.
Workflow
Copy this checklist and track progress:
- [ ] 1. Confirm scope and commit
- [ ] 2. Survey structure (entry points, modules, layers, build files)
- [ ] 3. Catalog abstractions (interfaces/traits/protocols/abstract types)
- [ ] 4. Catalog implementations and how dependencies are wired
- [ ] 5. Identify design patterns and conventions
- [ ] 6. Map relationships (dependency direction, data flow, coupling)
- [ ] 7. Record risks/smells, then emit the current CAD
1. Confirm scope
Establish the paths and commit. Detect the primary language(s) and build system from the manifests; state them rather than assuming.
2. Survey structure
Find entry points, top-level modules, and layer boundaries. Read manifests and
build files to understand dependencies and module graph. Prefer broad
exploration first (e.g. an explore subagent or glob/grep over the tree),
then drill into the parts that carry the architecture.
3. Catalog abstractions
List the key interfaces/traits/protocols/abstract classes and the core domain types. For each, capture responsibility and signatures, citing the source. These become the CAD's Interfaces and Domain Model sections.
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.
- 2mo ago First seen · 105 lines · 76 tokens per session scan A ad8b51c58fa1
analyze-codebase-architecture is a skill published in the GitHub repository Jacoby6000/Smithplates (2 stars, last pushed 20d ago), licensed MIT. It adds 76 tokens to every session and 1,003 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…