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 toBzh30/Claude-Project-Bootstrap --skill improve-codebase-architecturegit clone --depth 1 https://github.com/toBzh30/Claude-Project-BootstrapWrote 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/tobzh30/claude-project-bootstrap/improve-codebase-architecture)<a href="https://agentmods.dev/skills/tobzh30/claude-project-bootstrap/improve-codebase-architecture"><img src="https://agentmods.dev/badge/skills/tobzh30/claude-project-bootstrap/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/tobzh30/claude-project-bootstrap/improve-codebase-architecture"><img src="https://agentmods.dev/badge/skills/tobzh30/claude-project-bootstrap/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 | $0.00080 | $0.01219 |
| Opus 5.5 | $0.00032 | $0.00488 |
| Sonnet 5.5 | $0.00016 | $0.00244 |
| Haiku 4.5 | $0.00008 | $0.00122 |
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.
This is a copy
69% identical to improve-codebase-architecture — 78 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Improve Codebase Architecture
Surface architectural friction and propose deepening opportunities — refactors that turn shallow modules into deep ones. The aim is testability and AI-navigability.
Glossary
Use these terms exactly in every suggestion. Consistent language is the point — don't drift into "component," "service," "API," or "boundary." Full definitions in LANGUAGE.md.
- Module — anything with an interface and an implementation (function, class, package, slice).
- Interface — everything a caller must know to use the module: types, invariants, error modes, ordering, config. Not just the type signature.
- Implementation — the code inside.
- Depth — leverage at the interface: a lot of behaviour behind a small interface. Deep = high leverage. Shallow = interface nearly as complex as the implementation.
- Seam — where an interface lives; a place behaviour can be altered without editing in place. (Use this, not "boundary.")
- Adapter — a concrete thing satisfying an interface at a seam.
- Leverage — what callers get from depth.
- Locality — what maintainers get from depth: change, bugs, knowledge concentrated in one place.
Key principles (see LANGUAGE.md for the full list):
- Deletion test: imagine deleting the module. If complexity vanishes, it was a pass-through. If complexity reappears across N callers, it was earning its keep.
- The interface is the test surface.
- One adapter = hypothetical seam. Two adapters = real seam.
This skill is informed by the project's domain model. The domain language gives names to good seams; the decision log records what the skill should not re-litigate.
Process
1. Explore
Read the project's domain glossary (.claude/rules/glossary.md) and any decisions in .claude/rules/decisions.md for the area you're touching first.
Then use the Agent tool with subagent_type=Explore to walk the codebase. Don't follow rigid heuristics — explore organically and note where you experience friction:
What ships with it
3 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 · 72 lines · 80 tokens per session scan A 1ea32df90d8c
improve-codebase-architecture is a skill published in the GitHub repository toBzh30/Claude-Project-Bootstrap (3 stars, last pushed 2mo ago), licensed MIT. It adds 80 tokens to every session and 1,219 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 69% identical to improve-codebase-architecture, differing in 78 lines, and is treated as a copy.
Other skills, from other repositories
fix-ci-train
Batch-fix the CI on every open pull request whose required checks are red — CI only, no review, no merge. From a GitHub PRs URL (or the current repo), enumerate every open PR with failing required checks, fetch each PR's failing-check logs, consolidate a per-PR CI-fix checklist, dispatch a team of parallel fixer…
issue-train
Batch-process every open GitHub issue in a list — triage, detect existing PR linkage, detect silent fixes in already-merged PRs, close issues that are no longer pertinent, then plan + build + open one PR per remaining actionable issue with Closes.
project-standard-spec
Spec maintainer for Big Emotion Project Standard. Reads Confluence (Requirements / Decisions / Architecture) as the source of truth, helps you investigate a problem, structures the reflection, and produces drafts — Pending REQ/DEC/ARCH sections on Confluence + matching Jira tickets in the Jira project configured in…
blueprint
Extract a complete specs/ directory from any frontend codebase. Covers all 12 axes needed to rebuild or migrate a frontend app. Produces 80% quality on first pass, refined to 95% through guided iteration.
fix-train
Batch-apply the requested changes on every open pull request in a GitHub list — fix only, no merge. From a GitHub PRs URL (or the current repo), enumerate every open PR, collect each PR's requested changes (formal CHANGESREQUESTED reviews, inline review comments, and "Issues requiring changes" comments /…
project-standard-bootstrap-confluence
One-shot bootstrap of the Confluence spec tree (Requirements / Decisions / Architecture / Obsolete) for Big Emotion Project Standard. Creates the four skeleton subpages under the project's engineering root page, records their IDs in the spec config, writes the sentinel, then refuses second runs. Use only when…