skill-evolve

skill-evolve is a skill for Claude Code, Codex from fthsrbst/mnema. It costs 70 tokens per session (926 once invoked), scanned A, original, MIT.

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.

In plain words
What is it for?
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.
Why use it?
It prevents the same correction from being made repeatedly and keeps agent guidance accurate as workflows change.

Skill for Claude CodeCodex

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.

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

agentmods badge for skill-evolve

README.md
[![agentmods](https://agentmods.dev/badge/skills/fthsrbst/mnema/skill-evolve.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.svg" alt="Measured on agentmods" 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. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00070 $0.00926
Opus 5 $0.00035 $0.00463
Sonnet 5 $0.00014 $0.00185
Haiku 4.5 $0.00007 $0.00093

Measured 4d ago against content hash da07ed5e3079, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 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.

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

  1. 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.)
  2. 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.
  3. Kaydet: memory_save(type=howto, tags=["skill-evolve"]) — ne öğrenildi, hangi skill nasıl değişti. Bu, değişikliğin gerekçe kaydıdır.
  4. Dağıt: git add skills/ && git commit -m "skill: <ad> — <değişiklik>" && git push, sonra hub sync. Diğer cihazlar bir sonraki hub sync'te alır.
  5. 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.

  1. 4d 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 4d ago), licensed MIT. It adds 70 tokens to every session and 926 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

hr-onboarding

A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".

nexu-io/open-design · 62 tokens

html-ppt-taste-brutalist

16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).

nexu-io/open-design · 78 tokens

ligandmpnn

Inverse-fold a backbone with ligand, nucleic-acid, and metal context using LigandMPNN (Dauparas et al. 2023, github.com/dauparas/LigandMPNN). Reach for this skill to redesign the residues lining a binding pocket around a bound small molecule or cofactor, to design metal-coordinating sites where the geometry must be…

aipoch/open-science · 100 tokens

evo2

Score, embed, and generate DNA sequences with Evo 2, a long-context genomic foundation model. Use this skill when: (1) Computing per-nucleotide or per-sequence likelihoods for variant effect scoring, (2) Embedding genomic windows for downstream classification, (3) Generating DNA conditioned on a prefix, (4) Scoring…

aipoch/open-science · 83 tokens

package-author

当用户要把手头的工具打包/标准化成 pinvou 插件包时使用——包括纯技能(SKILL.md)、纯 MCP 服务或它们的组合包。用户说"打包/做成插件包/标准化这个工具/给我一个能上传的标准包/写 plugin.json/加个图标"等,或给了散乱脚本/目录要整理成可上传 zip 时,用本技能把内容规范成 plugin-protocol 标准包(补 plugin.json、补 mcp/manifest.json、补 SKILL.md、补图标、校验命名)。.

Pinvou/pinvou-agent · 133 tokens

google-meet

Google Meet via gws: create spaces, fetch join links, list recordings.

Open-Curiosity/gini-agent · 20 tokens