Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/nishilbhave/codeprobenpx agentmods add skills/nishilbhave/codeprobe/codeprobe-architectureWrote 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/nishilbhave/codeprobe/codeprobe-architecture)<a href="https://agentmods.dev/skills/nishilbhave/codeprobe/codeprobe-architecture"><img src="https://agentmods.dev/badge/skills/nishilbhave/codeprobe/codeprobe-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/nishilbhave/codeprobe/codeprobe-architecture"><img src="https://agentmods.dev/badge/skills/nishilbhave/codeprobe/codeprobe-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 | $0.00065 | $0.02751 |
| Opus 5.5 | $0.00026 | $0.01100 |
| Sonnet 5.5 | $0.00013 | $0.00550 |
| Haiku 4.5 | $0.00006 | $0.00275 |
Grade A, and why
codeprobe-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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Standalone Mode
If invoked directly (not via the orchestrator), you must first:
- Read
../codeprobe/shared-preamble.md(resolve relative to this SKILL.md's location — the siblingcodeprobeskill directory — not the user's project) for the output contract, execution modes, and constraints. - Load applicable reference files from
../codeprobe/references/(same resolution) based on the project's tech stack. - Default to
fullmode unless the user specifies otherwise.
Architecture & Structure Analyzer
Domain Scope
This sub-skill detects architectural and structural issues across these categories:
- Layer Violations — Business logic in controllers, presentation logic in models, database access in views
- Circular Dependencies — Direct or transitive circular imports between modules
- God Objects — Oversized files and classes that do too much
- Anemic Domain Model — Entity classes with no behavior, all logic in service classes
- Missing Boundaries — No clear module/domain separation, cross-feature coupling
- Directory Structure — Framework convention violations, flat directory anti-patterns
- Config/Environment — Hardcoded environment values, missing config abstraction
What It Does NOT Flag
- Small projects/scripts with fewer than 5 files — flat structure is appropriate for small codebases and adding layers would be over-engineering.
- Microservices that intentionally have thin layers — a microservice with a single controller, single service, and single repository is fine by design.
- Framework-standard monolith patterns that are idiomatic — e.g., Laravel's default structure for small-to-medium apps, Rails convention-over-configuration patterns, Next.js app directory conventions.
- Prototypes and proof-of-concept code clearly marked as such.
- Generated code directories (e.g.,
dist/,build/,.next/,__pycache__/).
Detection Instructions
Layer Violations
| ID Prefix | What to Detect | How to Detect | Severity |
|---|---|---|---|
ARCH |
Controllers containing business logic | Scan files in controller directories (controllers/, Controllers/, routes/, api/). Flag controllers that contain: database queries (SQL, ORM query builders beyond simple find()/findById()), complex conditionals with business rules (3+ branches), calculations, data transformations, or validation logic beyond simple field presence checks. Controllers should delegate to services/actions. |
Major |
ARCH |
Models/entities containing presentation logic | Scan model/entity files. Flag models that contain: HTML generation, string formatting for display (e.g., toHtml(), formatForDisplay()), view-specific transformations, CSS class computation, or response formatting. Models should contain domain logic, not presentation. |
Major |
ARCH |
Views/components calling database directly | Scan view files (.blade.php, .vue, .jsx/.tsx components, .ejs, .pug, Jinja templates). Flag views that contain: direct database queries, ORM calls, raw SQL, or repository method calls. Views should receive data from controllers/props, never fetch it themselves. |
Major |
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 · 145 lines · 65 tokens per session scan A 953e4fc0925f
codeprobe-architecture is a skill published in the GitHub repository nishilbhave/codeprobe (5 stars, last pushed 3mo ago), licensed MIT. It adds 65 tokens to every session and 2,751 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
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…
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"…
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…
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…