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.
git clone --depth 1 https://github.com/Cristhianzl/claude-skills-czlWrote 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/commands/cristhianzl/claude-skills-czl/evolve)<a href="https://agentmods.dev/commands/cristhianzl/claude-skills-czl/evolve"><img src="https://agentmods.dev/badge/commands/cristhianzl/claude-skills-czl/evolve/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/commands/cristhianzl/claude-skills-czl/evolve"><img src="https://agentmods.dev/badge/commands/cristhianzl/claude-skills-czl/evolve.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 | $0.00022 | $0.00286 |
| Opus 5 | $0.00011 | $0.00143 |
| Sonnet 5 | $0.00004 | $0.00057 |
| Haiku 4.5 | $0.00002 | $0.00029 |
Grade A, and why
evolve 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 12d 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
Look at the knowledge that has piled up in learnings/ and decide what has earned promotion into a first-class artifact. Run this occasionally (e.g. when a skill's learnings/ is getting crowded), not every session.
- Scan every
skills/*/learnings/*.md(skip theREADME.mdtemplates) and anyMEMORY.md. - Cluster related learnings — the same topic recurring across dates or skills is the signal.
- Pick the artifact per cluster:
- 3+ related learnings on one topic → a new
references/<topic>.mdunder the owning skill (or a new skill if it's a distinct domain). - A recurring multi-step workflow → a new
commands/<name>.md. - A one-off → leave it as a learning.
- 3+ related learnings on one topic → a new
- Propose before creating. Show the user what you'd promote, where, and why (cite the source learnings). On approval, write the artifact and record
evolved from:the source learning files in its frontmatter or a footer.
Don't delete the source learnings unless the user asks. Keep promoted artifacts short and in the repo's style. Never run git.
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.
- 12d ago First seen · 16 lines · 22 tokens per session scan A 35b882e00ac9
evolve is a command published in the GitHub repository Cristhianzl/claude-skills-czl (5 stars, last pushed yesterday), licensed MIT. It adds 22 tokens to every session and 286 once invoked, about $0.0001 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 commands, from other repositories
color-palette
Generate an accessible colour palette from a hex value.
ux-extract
Exhaustively extract UX patterns from a reference web app into a reusable pattern library.
tanstack-start
Build a full-stack TanStack Start app on Cloudflare Workers from scratch.
surgical
Enforce strict scope on a task — build only what was explicitly asked, nothing more.
adr
Write an architecture decision record as Markdown in the user's repository. Use when invoked as /document-design-system:adr. Produce designed HTML or PDF only when asked.
evaluate
Execute Evaluate stage to validate generated framework artifacts.