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 joao-aires/agent-skills-public --skill improvegit clone --depth 1 https://github.com/joao-aires/agent-skills-publicWrote 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/joao-aires/agent-skills-public/improve)<a href="https://agentmods.dev/skills/joao-aires/agent-skills-public/improve"><img src="https://agentmods.dev/badge/skills/joao-aires/agent-skills-public/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/joao-aires/agent-skills-public/improve"><img src="https://agentmods.dev/badge/skills/joao-aires/agent-skills-public/improve.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 | $0.00042 | $0.00513 |
| Opus 5.5 | $0.00017 | $0.00205 |
| Sonnet 5.5 | $0.00008 | $0.00103 |
| Haiku 4.5 | $0.00004 | $0.00051 |
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 yesterday.
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 — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Improve
Read task guidance. Read deliver-reliable-changes for baseline and verification, git-contributions for implementation when requested. Load the optional stack/domain guidance selected by task guidance only when relevant and available.
Assess opportunities
Use the relevant codebase and history to find a problem that matters in practice. Look for changes that repeatedly touch unrelated modules, expensive operations in an important journey, failures that are difficult to diagnose, inconsistent interactions, or slow and unreliable development checks. Follow the evidence far enough to distinguish a cause from a disliked coding style.
For each worthwhile opportunity, explain who is affected, what evidence shows the problem, and how a bounded change could improve it. State how improvement would be measured and what behavior needs protection. Compare likely value with implementation and maintenance cost; no finding or no worthwhile change is valid. A bare request returns a short prioritized set of proposals rather than rewriting unrelated areas or creating tickets automatically.
Implement an authorized improvement
A specific requested improvement can authorize bounded implementation. Keep a bare improvement assessment read-only; do not force another approval for routine choices already authorized.
- Establish a baseline, diagnose the cause and define the desired outcome.
- Make focused changes within scope. Preserve behavior through incremental refactoring and regression checks.
- Compare results with the baseline and report the evidence.
Choose the relevant analysis without imposing another process:
| Concern | Examine and use |
|---|---|
| UX | Establish interaction intent before changing screens; account for all affected surfaces. Use available interface assessment and interface-language expertise for craft and task copy. |
| Usability evidence | Use available research expertise for a requested study or actual observations. |
| Architecture | Examine responsibilities, dependency direction, ownership, coupling/change hotspots, seams and testability. Use codebase-design/domain-modeling where useful, without forcing deep-module vocabulary, HTML reports or interviews. |
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.
- yesterday Changed · +20 lines 1659f5d472b3
- 2d ago Changed ea9cfeca420c
- 5d ago Changed a96f42d6fc98
- 7d ago First seen · 22 lines · 42 tokens per session scan A bdb68f6907f9
improve is a skill published in the GitHub repository joao-aires/agent-skills-public (2 stars, last pushed yesterday), licensed MIT. It adds 42 tokens to every session and 513 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 2026-10-15.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
deck-retro
Run a fully local agent-deck retrospective over the user's own transcripts, Recall index and logs. Use when a user wants to find recurring failures or take their own finding from investigation through synthetic reproduction, a user-filed issue, a test-first fix and contributor PR handoff. Also use for weekly usage…
incident-response-incident-response
Coordinate production incident triage, mitigation, investigation, recovery, and follow-up. Use when responding to outages or other incidents that require structured operational coordination.
cwv-optimizer
Diagnose and fix Core Web Vitals issues on AEM Edge Delivery Services pages. Goes deeper than generic CWV advice by understanding EDS-specific performance patterns including the 100KB LCP budget, E-L-D loading phases, block rendering behavior, and third-party script impact. Produces specific fixes for LCP, CLS, and…