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 tomzx/agents --skill improve-skillgit clone --depth 1 https://github.com/tomzx/agentsWrote 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/tomzx/agents/improve-skill)<a href="https://agentmods.dev/skills/tomzx/agents/improve-skill"><img src="https://agentmods.dev/badge/skills/tomzx/agents/improve-skill.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 5.1 | $0.00048 | $0.01293 |
| Opus 5 | $0.00024 | $0.00647 |
| Sonnet 5 | $0.00010 | $0.00259 |
| Haiku 4.5 | $0.00005 | $0.00129 |
Grade A, and why
improve-skill 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 4d 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TODAY=!date +%Y-%m-%d
Improve Skill
Inspects one skill end to end, reasons about concrete improvements, and applies them in place. Designed for the Skill Refresher workflow that improves a random skill every day, but also useful when a human points it at a specific skill that feels weak.
Prerequisites
- Working directory is the root of the
tomzx/agentsrepository (the skill library root) $1— the name of the skill directory underskills/to improve (e.g.git-commit)- The target skill exists at
skills/$1/SKILL.md
What Counts as an Improvement
Keep only improvements that are high-value and low-risk. Prefer concrete, surgical edits over rewrites.
| Category | What to Look For |
|---|---|
| Clarity and precision | Steps that are ambiguous, easy to get wrong, or could be misread by an agent |
| Completeness | Missing prerequisites, steps, edge cases, error handling, or acceptance checks |
| Correctness | Examples, commands, or file paths that are wrong, outdated, or would fail if followed literally |
| Examples and templates | Missing, vague, or broken example usage, output format templates, or code blocks |
| Structure | Poor section ordering, redundant sections, verbosity, or content that should be split or merged |
| Frontmatter | Description that does not match the body, missing allowed-tools or argument-hint, broken argument-hint signature |
| References | Broken cross-references to other skills, files, scripts, or environment variables |
| Safety | Missing guards before destructive actions, re-run safety concerns, rollback guidance |
What Counts as Churn (Avoid)
Do not change things for the sake of change. These are not improvements:
| Anti-pattern | Why to Avoid |
|---|---|
| Rewriting working prose into different working prose | Adds review burden with no functional gain |
| Introducing new dependencies or tools not used in the project | Bloats the skill with unavailable tools |
| Adding speculative edge cases the skill will never hit | Inflates length without value |
| Restyling or reformatting that does not fix a real problem | Noise in the diff |
| Splitting or renaming sections that are already clear | Breaks muscle memory and references |
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.
- 4d ago First seen · 134 lines · 48 tokens per session scan A ab5367ed2844
improve-skill is a skill published in the GitHub repository tomzx/agents (6 stars, last pushed 4d ago), licensed MIT. It adds 48 tokens to every session and 1,293 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 2026-09-03.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…