What is skill-evolve?

A process for improving the instructions used by coding agents when repeated mistakes or useful patterns are discovered. It updates the relevant skill, records what was learned, and distributes the change across devices.

Use it after a skill gives wrong or incomplete advice, the same correction is needed twice, a reusable technique is found, or a new workflow is added.

It prevents the same correction from being made repeatedly and keeps agent guidance accurate as workflows change.

skill-evolve — Skill for Claude Code and Codex by fthsrbst/mnema

Install

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.

Any agent

npx skills add fthsrbst/mnema --skill skill-evolve

Clone the repo

git clone --depth 1 https://github.com/fthsrbst/mnema

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/fthsrbst/mnema/skill-evolve/github.svg)](https://agentmods.dev/skills/fthsrbst/mnema/skill-evolve)

Your own site

<a href="https://agentmods.dev/skills/fthsrbst/mnema/skill-evolve"><img src="https://agentmods.dev/badge/skills/fthsrbst/mnema/skill-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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/fthsrbst/mnema/skill-evolve"><img src="https://agentmods.dev/badge/skills/fthsrbst/mnema/skill-evolve.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 926 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00070	$0.00926
Opus 5.5	$0.00028	$0.00370
Sonnet 5.5	$0.00014	$0.00185
Haiku 4.5	$0.00007	$0.00093

Measured 1mo ago against content hash da07ed5e3079, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

skill-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 1mo 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.

skills/skill-evolve/SKILL.md · 37 lines

How it starts

The opening of the file, as written. The whole thing — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill Evolve — Kendini Geliştiren Sistem

Skiller statik doküman değil, yaşayan sistem. Sen (agent) bu sistemin bakımcısısın. Kaynak: C:\Users\fatih\Desktop\dev\ai-hub\skills\ (git repo) → hub sync ile dağıtılır.

Ne zaman tetiklenir

Kullanıcı aynı düzeltmeyi/tercihi ikinci kez söylediğinde (bir kez = hafıza, iki kez = skill'e işlenir)
Bir skill'in yönlendirmesi seni yanlış yola soktuğunda (örn. yanlış workflow önerisi, eskimiş komut)
Zor bir problemde işe yarayan genellenebilir bir teknik bulduğunda
Yeni bir araç/workflow eklendiğinde (envanter tabloları güncel kalmalı)

Döngü

Teşhis: Hangi skill sorumlu? Yoksa: yeni skill mi gerekiyor, yoksa mevcut birine bölüm mü? (Yeni skill çıtası yüksek tut — az sayıda güçlü skill > çok sayıda cılız skill.)
Güncelle: Repo'daki skills/<ad>/SKILL.md dosyasını düzenle. Kural: değişiklik davranış değiştirmeli — "daha iyi ol" gibi laf kalabalığı ekleme; somut kural/tablo/komut ekle veya yanlışı sil.
Kaydet: memory_save(type=howto, tags=["skill-evolve"]) — ne öğrenildi, hangi skill nasıl değişti. Bu, değişikliğin gerekçe kaydıdır.
Dağıt: git add skills/ && git commit -m "skill: <ad> — <değişiklik>" && git push, sonra hub sync. Diğer cihazlar bir sonraki hub sync'te alır.
Kullanıcıya tek satır bildir: "X skill'ine şunu işledim" — onay bekleme, geri alınabilir.

Güvenlik: "ya daha kötü hale getirirsem?"

Her skill değişikliği git commit'i olduğu için hiçbir değişiklik kalıcı hasar değildir:

Geri alma: git log -- skills/<ad>/ ile geçmişi gör, git revert <commit> (veya git checkout <eski-sha> -- skills/<ad>/SKILL.md) + push + hub sync → eski hal tüm cihazlara döner.
Küçük diff kuralı: Tek commit'te tek skill, tek konu. Toptan yeniden yazma YASAK — kötüleşmeyi fark etmeyi ve geri almayı zorlaştırır.
Silme yerine daraltma: Var olan bir kuralı silmeden önce neden yanlış olduğunu commit mesajında kanıtla. Emin değilsen kuralı silme, "eskimiş olabilir" notu düş.
Kötüleşme sinyali: Bir skill güncellemesinden sonra aynı türde iş 2+ kez daha kötü giderse, ilk şüphen son skill değişikliği olsun → git log'a bak, revert et, hafızaya ders yaz.
Kullanıcı "bu skill eskiden daha iyiydi" derse: tartışma, önce revert, sonra konuş.

Read the full file on GitHub · 37 lines

Changes

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.

1mo ago First seen · 37 lines · 70 tokens per session scan A da07ed5e3079

Subscribe to this mod's changes

skill-evolve is a skill published in the GitHub repository fthsrbst/mnema (2 stars, last pushed 1mo ago), licensed MIT. It adds 70 tokens to every session and 926 once invoked, about $0.0003 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 2026-08-31.

Building agents ai-agents claude cli codex local-first mcp

zootopia-ppt

A presentation-making workflow that turns a speech or slide content into images showing an animated world of human-like animals. It first plans each slide and then generates the slide images.

jin-bo/agentao · 152 tokens

kanban-tasks

A task-board workflow for breaking work into cards and moving them through stages such as inbox, ready, doing, review, and done. It also includes a background service and a web interface for the board.

jin-bo/agentao · 221 tokens

ocr

OCR image files using the Qwen VL model via the bundled scripts/ocr.py (lives in this skill's directory, NOT your cwd). Use when the user asks to extract text from an image, perform OCR on a photo or screenshot, or recognize characters in an image file (.jpg, .jpeg, .png, .gif, .webp). Requires QWENAPIKEY and…

jin-bo/agentao · 99 tokens

skill-evolve