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/panda850819/verbs/improve-codebase-architecturenpx skills add panda850819/verbs --skill improve-codebase-architecturegit clone --depth 1 https://github.com/panda850819/verbsWrote 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/panda850819/verbs/improve-codebase-architecture)<a href="https://agentmods.dev/skills/panda850819/verbs/improve-codebase-architecture"><img src="https://agentmods.dev/badge/skills/panda850819/verbs/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 | $0.00046 | $0.00835 |
| Opus 5 | $0.00023 | $0.00417 |
| Sonnet 5 | $0.00009 | $0.00167 |
| Haiku 4.5 | $0.00005 | $0.00084 |
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 3d 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Improve Codebase Architecture
Survey a repository for modules worth deepening. Produce one visual report; do not edit repository files or design the chosen interface in this run.
Read lib/codebase-design.md first and use its module, interface, depth, seam,
adapter, leverage, locality, deletion-test, and test-surface definitions.
1. Bind the scan
Use a user-named subsystem, pain point, path, or upcoming spec as the scope. If
none is named, inspect at most the latest 100 commits and rank repeatedly changed
paths before reading code. Read CONTEXT.md and relevant repository
architecture-decision records when present. Record missing history or domain documents as evidence gaps.
Done when the report can name its scope, why those paths were selected, and which domain and ADR evidence constrained the scan.
2. Find deepening candidates
Trace concepts through callers, implementation, tests, and external effects. Look for wide interfaces, knowledge scattered across callers, pass-through modules, seams crossed by concrete dependencies, and behavior that tests cannot alter through the caller-facing interface.
Keep a candidate only when repository evidence identifies all of:
- current friction and the files that demonstrate it;
- the responsibility that should gain locality;
- a smaller plausible seam, without proposing its final interface;
- leverage across named callers or tests;
- the deletion-test result: removal would let responsibility concentrate behind the proposed seam rather than scatter required knowledge across callers.
Merge candidates with the same seam. Exclude style cleanup, dormant code with no named future pressure, generic layering advice, and ADR-rejected directions without new evidence. Done when every retained candidate passes every item or is discarded.
3. Rank honestly
Assign exactly one strength:
- Strong: repeated friction plus concrete caller/test evidence makes the locality and leverage gain clear.
- Worth exploring: the seam is evidenced, but payoff depends on an upcoming change or one unresolved constraint.
- Speculative: plausible signal with a named evidence gap; never choose one as the top recommendation.
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.
- 3d ago First seen · 95 lines · 46 tokens per session scan A 4e5c3b481720
improve-codebase-architecture is a skill published in the GitHub repository panda850819/verbs (5 stars, last pushed 11d ago), licensed MIT. It adds 46 tokens to every session and 835 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
markstream-react
Integrate the beta markstream-react package into a React 18+ or Next app. Use when Codex needs to add the React renderer, choose the root, next, or server entrypoint, import CSS correctly, choose between content and nodes, keep client boundaries safe, add renderer-local streamingComponents or htmlComponents, use…
decided-import
Reformat ONE existing document (a decision, requirement, design, roadmap, or prompt) into ONE valid RAC (requirements-as-code) artifact, with a mandatory human-review step before any file is written and decided validate as the deterministic close. Use when a user wants to add or import a single existing decision or…
nba
Read the live cycle state and return the single highest-leverage next best action, not a menu. Use when a project is between phases, the author asks what to do next, too many valid threads are open, or the work needs re-entry into frame, build, drive, re0-memo, hate, re0-work, or ship.
dependabot-review
Analyzes a Dependabot PR to determine what actually changed in each bumped package and whether those changes affect this repo. Reports changed APIs/methods, which doc pages use them, and the realistic probability of any visible impact on the docs site.
review-validation
Validate review findings from specialist agents by reading the actual repo file content and checking each finding for accuracy, applicability, and false positives.
markdown-exporter
Convert Markdown text to DOCX, PPTX, XLSX, PDF, PNG, SVG, HTML, IPYNB, MD, CSV, JSON, JSONL, XML files, and extract code blocks in Markdown to Python, Bash,JS and etc files.