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 agentmods add skills/andrewsrigom/agent-skills/improve-codebase-architecturenpx skills add andrewsrigom/agent-skills --skill improve-codebase-architecturegit clone --depth 1 https://github.com/andrewsrigom/agent-skillsWrote 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/andrewsrigom/agent-skills/improve-codebase-architecture)<a href="https://agentmods.dev/skills/andrewsrigom/agent-skills/improve-codebase-architecture"><img src="https://agentmods.dev/badge/skills/andrewsrigom/agent-skills/improve-codebase-architecture.svg" alt="Measured on agentmods" 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 | $0.00041 | $0.00493 |
| Opus 5 | $0.00020 | $0.00246 |
| Sonnet 5 | $0.00008 | $0.00099 |
| Haiku 4.5 | $0.00004 | $0.00049 |
Grade A, and why
improve-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 6d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Improve Codebase Architecture
Use this skill when the user wants architectural improvement ideas before touching implementation.
Scope
- finding shallow or tightly coupled modules
- identifying poor seams between features
- spotting places where boundaries are hard to test
- proposing deeper modules and simpler public interfaces
- generating concrete architectural refactor candidates
Default path
- Explore the codebase like a new contributor would.
- Note where understanding one concept requires too much file-hopping.
- Find boundaries where interfaces are almost as complex as the internals.
- Group friction into architectural candidates instead of isolated complaints.
- For each candidate, describe:
- current friction
- likely deeper boundary
- testing impact
- tradeoffs
- Recommend the best candidate to pursue first.
When to deviate
- Zoom into one subsystem only when one boundary clearly dominates the architectural pain.
- Recommend no architectural change if the main issue is local implementation quality rather than a bad seam.
- Escalate to a refactor plan once one candidate is clearly worth pursuing.
Guardrails
- Do not propose broad rewrites without a specific boundary problem.
- Favor deeper modules over just moving files around.
- Focus on seams that improve testability and change safety.
- Keep recommendations tied to user-facing or developer-facing pain, not aesthetics.
Avoid
- proposing a rewrite without a concrete boundary failure
- confusing file shuffling with architecture improvement
- optimizing for conceptual neatness while ignoring testability or change safety
- generating a long complaint list without grouping it into candidates
Verification checklist
- each candidate is tied to a real friction point
- the stronger boundary is described in terms of what it would hide
- testability or change-safety impact is explicit
- tradeoffs are named, not implied
- one candidate is recommended as the best first move
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.
- 6d ago First seen · 71 lines · 41 tokens per session scan A bb4e78f1451a
improve-codebase-architecture is a skill published in the GitHub repository andrewsrigom/agent-skills (2 stars, last pushed 5mo ago), licensed MIT. It adds 41 tokens to every session and 493 once invoked, about $0.0002 per session on Opus 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
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
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"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.