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 strikersam/autonomous-ai-agency --skill modularity-reviewgit clone --depth 1 https://github.com/strikersam/autonomous-ai-agencyWrote 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/strikersam/autonomous-ai-agency/modularity-review)<a href="https://agentmods.dev/skills/strikersam/autonomous-ai-agency/modularity-review"><img src="https://agentmods.dev/badge/skills/strikersam/autonomous-ai-agency/modularity-review/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/strikersam/autonomous-ai-agency/modularity-review"><img src="https://agentmods.dev/badge/skills/strikersam/autonomous-ai-agency/modularity-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00091 | $0.01709 |
| Opus 5.5 | $0.00036 | $0.00684 |
| Sonnet 5.5 | $0.00018 | $0.00342 |
| Haiku 4.5 | $0.00009 | $0.00171 |
Grade A, and why
modularity-review 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 18d 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 — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: modularity-review
The Core Principle
Modularity is about change. A codebase is modular when it is crystal-clear which components need to change for a given requirement, and ideally that number is small — preferably one. If change radiates unpredictably, the system is coupled.
A secondary modern concern: modularity makes code accessible to AI. LLMs have finite context windows. Tightly coupled codebases force large, entangled contexts onto every reasoning task. Well-modularized code lets AI (and humans) reason about one bounded piece at a time.
When to Use
- Before designing a new module, service, or capability
- When a change requires touching 5+ files across unrelated modules
- When tests are hard to write because of dependency tangles
- When a new team member can't understand a module without reading 3 others
- When the AI agent loop requires large context to accomplish a focused task
Part A: Reviewing Existing Code for Modularity Problems
Step 1 — Map the dependency graph
For each module in the repo, list what it imports:
# Python: list all internal imports
grep -r "^from\|^import" --include="*.py" . | grep -v ".venv" | grep -v "test_"
Build a mental (or written) graph: which modules depend on which.
Step 2 — Identify coupling smells
Look for these patterns:
| Smell | Description | Example in this repo |
|---|---|---|
| Feature envy | Module A uses many internals of module B | app.py reaching into agent/runner.py internals |
| Shotgun surgery | One change requires edits in 5+ files | Adding a new model type requires editing registry, classifier, router, and tests |
| Divergent change | One module changes for many unrelated reasons | app.py handles auth, routing, streaming, rate limiting all at once |
| Improper abstraction | Implementation detail leaks through module boundary | Caller knows which HTTP client the callee uses |
| Circular dependency | A imports B, B imports A | Usually causes import errors in Python |
| God module | One file does everything | app.py risks becoming this |
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.
- 18d ago Changed · -1 lines 2efb729af60c
- 2mo ago First seen · 211 lines · 91 tokens per session scan A 8f7f471c0301
modularity-review is a skill published in the GitHub repository strikersam/autonomous-ai-agency (11 stars, last pushed yesterday), licensed MIT. It adds 91 tokens to every session and 1,709 once invoked, about $0.0004 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.
modularity-review compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| modularity-reviewstrikersam/autonomous-ai-agency | Skill | 11 | yesterday | MIT | A | 91 | Claude Code, Codex |
| codebase-synca5c-ai/babysitter | Skill | 1.9k | 5d ago | MIT | A | 32 | Claude Code |
| code-review-pipelinea5c-ai/babysitter | Skill | 1.9k | 5d ago | MIT | A | 28 | Claude Code |
| code-review-patternsa5c-ai/babysitter | Skill | 1.9k | 5d ago | MIT | A | 33 | Claude Code |
| code-review-orchestrationa5c-ai/babysitter | Skill | 1.9k | 5d ago | MIT | A | 31 | Claude Code |
| adversarial-reviewa5c-ai/babysitter | Skill | 1.9k | 5d ago | MIT | A | 31 | Claude Code |
| orchestrated-executiona5c-ai/babysitter | Skill | 1.9k | 5d ago | MIT | A | 37 | Claude Code |