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 SetraTheXX/Codex-Engineering-Workflow-Pack --skill improve-codebase-architecturegit clone --depth 1 https://github.com/SetraTheXX/Codex-Engineering-Workflow-PackWrote 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/setrathexx/codex-engineering-workflow-pack/improve-codebase-architecture)<a href="https://agentmods.dev/skills/setrathexx/codex-engineering-workflow-pack/improve-codebase-architecture"><img src="https://agentmods.dev/badge/skills/setrathexx/codex-engineering-workflow-pack/improve-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/setrathexx/codex-engineering-workflow-pack/improve-codebase-architecture"><img src="https://agentmods.dev/badge/skills/setrathexx/codex-engineering-workflow-pack/improve-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 | $0.00059 | $0.01030 |
| Opus 5.5 | $0.00024 | $0.00412 |
| Sonnet 5.5 | $0.00012 | $0.00206 |
| Haiku 4.5 | $0.00006 | $0.00103 |
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 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 — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Improve Codebase Architecture
Find architectural friction and propose small, verifiable refactor opportunities.
This skill is analysis-first. Do not edit code, create reports, or start refactors until the user approves the report path and next action.
Read First
Inspect repo context:
CONTEXT.mddocs/agents/domain.mddocs/adr/docs/agents/test-commands.md- relevant source files,
- relevant test files.
If setup docs are missing, infer from the repo and state what is unknown.
Use fast search when possible:
rg --files
rg "<domain-term-or-module-name>"
Keep Windows paths with spaces quoted when showing commands or report paths.
Output Location
Default local report directory:
docs/agents/architecture/
Suggested file:
docs/agents/architecture/YYYY-MM-DD-architecture-audit.md
Before writing a report:
- propose the target path,
- summarize what the report will contain,
- ask for approval.
Scope
Use this skill for hard-to-change code, tangled module relationships, unclear ownership, shallow pass-through modules, broad interfaces, weak test surfaces, domain naming mismatch, and risky refactor sequencing.
Do not recommend a big rewrite. Prefer small changes that can be verified.
Workflow
1. Define Audit Focus
Identify the area to inspect:
- folder,
- module group,
- feature path,
- bug-prone area,
- domain concept,
- PRD or issue scope.
If the focus is too broad, propose a narrower audit slice.
2. Map Current Structure
Read code and tests enough to understand:
- main modules,
- callers and callees,
- dependency direction,
- public interfaces,
- test entry points.
Use zoom-out first if the area is unfamiliar and the user only needs orientation.
3. Check Domain And Decisions
Compare code structure with:
- domain terms in
CONTEXT.mdordocs/agents/domain.md, - ADR constraints,
- existing test command docs,
- related PRDs or issues.
Report mismatches:
- code uses different names than domain docs,
- module boundaries cut across domain concepts,
- ADR assumptions no longer match current implementation,
- tests verify internals instead of behavior.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 195 lines · 59 tokens per session scan A de5ab072cd6f
improve-codebase-architecture is a skill published in the GitHub repository SetraTheXX/Codex-Engineering-Workflow-Pack (1 stars, last pushed 28d ago), licensed MIT. It adds 59 tokens to every session and 1,030 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 2026-08-31.
Other skills, from other repositories
pdlc-review
A code-review workflow that checks an implementation against its design, tests, coding rules, quality checks, and common security concerns. It requires the implementation to exist and its tests to pass before reviewing it.
code-review
Reviews diffs by severity to produce actionable feedback.
pr-workflow
Prepares branches and PRs for clean, reviewable merges.
receiving-code-review
Processes review feedback until the change is approved.
requesting-code-review
Self-reviews work against the plan before sign-off.
pdlc-refactor
A refactoring workflow for improving a program's internal structure while keeping its observable behavior the same. It uses existing tests, small changes, and repeated test runs to reduce risk.