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 macintog/codex-spine --skill improve-codebase-architecturegit clone --depth 1 https://github.com/macintog/codex-spineWrote 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/macintog/codex-spine/improve-codebase-architecture)<a href="https://agentmods.dev/skills/macintog/codex-spine/improve-codebase-architecture"><img src="https://agentmods.dev/badge/skills/macintog/codex-spine/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/macintog/codex-spine/improve-codebase-architecture"><img src="https://agentmods.dev/badge/skills/macintog/codex-spine/improve-codebase-architecture.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 | $0.00063 | $0.00378 |
| Opus 5.5 | $0.00025 | $0.00151 |
| Sonnet 5.5 | $0.00013 | $0.00076 |
| Haiku 4.5 | $0.00006 | $0.00038 |
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 19d 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.
What it actually says
Architecture audit
Goal: less effort to use, change, and debug the code, with required behavior preserved. Fewer files or lines is not by itself an improvement.
- Establish the need first. Read callers, docs, ADRs, tests, and history before judging a mechanism; code that looks redundant may encode a domain rule.
- Look for:
- One rule implemented in two places that disagree, especially across languages or processes (a pre-check here, an enforcer there). Name the inputs on which they diverge.
- Sibling paths (create/update, push/PR, CLI/API) whose names, owners, validation, or failure handling differ without a domain reason. Keep asymmetries the domain justifies.
- Shallow modules whose callers must know their internals (protocols, sentinels, ordering). Deepen; do not split.
- Deletion test: if a module were removed, would its responsibility vanish or move into callers? Name what would move.
- Avoid: new interfaces or ports with one implementation, merging code that changes for different reasons, rewrites, cosmetic renames, invented metrics.
- Report a few ranked candidates, each with file:line evidence, the concrete friction, the change, its migration cost, and the test that pins current behavior. "Keep as is" and "insufficient evidence" are valid results. Write in the project's own vocabulary, not architecture jargon.
- Stop at recommendations unless the user selected a candidate to implement.
What ships with it
2 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.
- 19d ago Changed · -73 lines · -22 tokens per session a4ee87dcfe6f
- 1mo ago Changed · +3 lines · +9 tokens per session f3d786eb28ea
- 1mo ago First seen · 89 lines · 76 tokens per session scan A 554e8daf4c61
improve-codebase-architecture is a skill published in the GitHub repository macintog/codex-spine (12 stars, last pushed yesterday), licensed MIT. It adds 63 tokens to every session and 378 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
auto-test-code
A structured process for critically reviewing and testing software code. It records review findings, test plans, commands, results, and supporting files in a project workspace.
git-pr-review
A read-only reviewer for GitHub pull requests, which are proposed code changes submitted for review. It produces an evidence-based report about whether a pull request should be merged.
code-reviewer
A code-review workflow that checks completed work against its requirements or plan before merging. It groups findings by severity and gives each issue a fix and a way to verify it.
codebase-migrate
Run large codebase migrations and multi-file refactors. Uses the Composio CLI to coordinate issue tracking, batched PRs, and CI verification while the agent executes the transforms locally across hundreds of files.
iac-reviewer
Review infrastructure-as-code changes for safety and correctness. Use when a mid-level developer needs a second look on IaC.
pr-reviewer
Review a pull request for correctness, regressions, and missing tests. Use when a mid-level developer needs structured review guidance.