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 boparaiamrit/skills-by-amrit --skill architecture-auditgit clone --depth 1 https://github.com/boparaiamrit/skills-by-amritWrote 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/boparaiamrit/skills-by-amrit/architecture-audit)<a href="https://agentmods.dev/skills/boparaiamrit/skills-by-amrit/architecture-audit"><img src="https://agentmods.dev/badge/skills/boparaiamrit/skills-by-amrit/architecture-audit/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/boparaiamrit/skills-by-amrit/architecture-audit"><img src="https://agentmods.dev/badge/skills/boparaiamrit/skills-by-amrit/architecture-audit.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 | $0.00043 | $0.02150 |
| Opus 5.5 | $0.00017 | $0.00860 |
| Sonnet 5.5 | $0.00009 | $0.00430 |
| Haiku 4.5 | $0.00004 | $0.00215 |
Grade A, and why
architecture-audit 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.
How it starts
The opening of the file, as written. The whole thing — 258 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architecture Audit
Overview
Evaluate the structural health of a codebase — patterns, coupling, cohesion, and alignment between what the code claims to be and what it actually is.
Core principle: Architecture is not what's drawn on a whiteboard. It's what's in the code.
The Iron Law
NO ARCHITECTURAL CLAIMS WITHOUT READING THE ACTUAL CODE
When to Use
- "Audit this codebase"
- "Is this well-architected?"
- "What's the technical debt situation?"
- System feels hard to change or understand
- New team member needs to understand the system
- Before a major refactoring or migration
When NOT to Use
- First encounter with a codebase (use
codebase-mappingfirst) - Debugging a specific bug (use
systematic-debugging) - Performance bottleneck investigation only (use
performance-audit) - Need to understand what the codebase does (use
codebase-mapping)
Anti-Shortcut Rules
YOU CANNOT:
- Assess architecture from directory names alone — read the actual code in each layer
- Claim "clean architecture" because folders are named well — check dependency direction
- Say "patterns are consistent" without checking EVERY module — inconsistency hides in corners
- Skip dependency graph analysis — coupling only reveals itself through imports
- Accept "it works" as architectural validation — working ≠ well-architected
- Audit only the happy path — error handling architecture matters equally
- Skip cross-cutting concerns — auth, logging, config are architecture too
- Trust documentation over code — code is the source of truth, docs drift
Common Rationalizations (Don't Accept These)
| Rationalization | Reality |
|---|---|
| "The folder structure looks clean" | Folder structure ≠ architecture. Check dependency direction. |
| "We're using MVC/Clean Architecture" | Claiming a pattern ≠ implementing it. Verify with imports. |
| "Only the core modules matter" | Utility modules, middleware, and config can rot the architecture. |
| "It's a small project, architecture doesn't matter" | Small projects become large projects. Foundation matters. |
| "We'll fix the architecture later" | Later never comes. Architectural debt compounds exponentially. |
| "The tests prove the architecture is fine" | Tests can pass in a poorly architected system. |
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 · 258 lines · 43 tokens per session scan A 2e26a693307f
architecture-audit is a skill published in the GitHub repository boparaiamrit/skills-by-amrit (5 stars, last pushed 7mo ago), licensed MIT. It adds 43 tokens to every session and 2,150 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 2026-09-03.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…