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 owainlewis/blueprint --skill improvegit clone --depth 1 https://github.com/owainlewis/blueprintWrote 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/owainlewis/blueprint/improve)<a href="https://agentmods.dev/skills/owainlewis/blueprint/improve"><img src="https://agentmods.dev/badge/skills/owainlewis/blueprint/improve/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/owainlewis/blueprint/improve"><img src="https://agentmods.dev/badge/skills/owainlewis/blueprint/improve.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 | $0.00033 | $0.00353 |
| Opus 5.5 | $0.00013 | $0.00141 |
| Sonnet 5.5 | $0.00007 | $0.00071 |
| Haiku 4.5 | $0.00003 | $0.00035 |
Grade A, and why
improve 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.
What it actually says
Improve
Make code easier to understand without changing what it does. Reduce the layers a reader must trace and the hidden state they must remember.
Process
- Identify the target from the request, current diff, or recently changed code.
- Read the target, its tests, and relevant surrounding code. State the behavior that must not change.
- If that behavior lacks tests, add focused coverage and run it against the unchanged code. Commit the passing test-only change before refactoring. If automated tests cannot exercise the behavior, explain why and give other evidence.
- Find unnecessary complexity, duplication, dead code, weak names, awkward boundaries, and abstractions that cost more than they help.
- Make focused improvements by deleting, deduplicating, renaming, simplifying, extracting, or inlining.
- Preserve public interfaces, data shapes, errors, and user-visible behavior unless the user explicitly asks to change them.
- Run tests and checks that cover behavior the refactor can affect. Report what improved, what behavior was preserved, and the evidence.
Return
State what became simpler, what behavior stayed the same, and which checks prove it. Name any behavior that remains unverified.
Boundaries
- Do not add product scope or absorb unrelated cleanup.
- Prefer a few clear edits over a broad rewrite.
- Preserve behavior even when a redesign would be easier.
What ships with it
1 file 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.
- 6d ago Changed · +1 lines a2109603812f
- 1mo ago First seen · 31 lines · 33 tokens per session scan A 3fa3a7093181
improve is a skill published in the GitHub repository owainlewis/blueprint (416 stars, last pushed 2d ago), licensed MIT. It adds 33 tokens to every session and 353 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
code-reviewer
Review completed implementation batches for spec compliance and code quality. Invoke after execution batches complete, before merging, or when a review gate is reached in the workflow.
review
Adversarial senior review of the spec before any code is written. Constructs a skeptical reviewer whose authority comes from the codebase, §R research, and live best-practice — then tries to REFUTE the spec, not rubber-stamp it. Every finding cites evidence (file:line or source); unverifiable ones are flagged.…
speq-code-review
Code review tag taxonomy and findings output format — guardrail violations, dead code, test quality, bad comments, optimizations, YAGNI/over-engineering, error handling, and design depth. Used by the speq code-reviewer agent during a speq implement run. Not for general code review.
review-spd
Findings-first code review workflow for AI coding agents. Use when the user asks to review uncommitted changes, commits in a date range, or a branch compared to the main branch / PR-style diff. Focuses on bugs, regressions, correctness risks, missing tests, security/data-safety issues, and other behavior-changing…
deepen
Optional design-improvement pass for when you have spare usage to drain. Finds the shallowest modules in the code the spec touches, researches a deeper design, and proposes refactors that shrink interfaces and hide decisions — behavior held constant, tests green before and after. Proposes §I/§V/§T edits, never silent…
code-simplifier
Always-active simplicity rules: no speculative abstractions, one job per function, max 30 lines, flat over nested with early returns, descriptive names, comments explain why.