self-learner

self-learner is an agent for coding agents from vibeeval/vibecosystem. It costs 39 tokens per session (1,003 once invoked), scanned A, original, MIT.

A learning agent that turns coding mistakes, failed tests, and review findings into reusable project rules. It records those lessons in project instructions and memory.

In plain words
What is it for?
Use it after mistakes or test failures to analyze the root cause, classify the lesson, update a project's learned-mistakes records, and store broadly useful guidance.
Why use it?
It helps teams avoid repeating the same errors by preserving the cause, fix, and prevention advice after a problem is resolved.

Agent

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 agents/vibeeval/vibecosystem/self-learner
Clone the repo
git clone --depth 1 https://github.com/vibeeval/vibecosystem

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 self-learner

README.md
[![agentmods](https://agentmods.dev/badge/agents/vibeeval/vibecosystem/self-learner.svg)](https://agentmods.dev/agents/vibeeval/vibecosystem/self-learner)
Your own site
<a href="https://agentmods.dev/agents/vibeeval/vibecosystem/self-learner"><img src="https://agentmods.dev/badge/agents/vibeeval/vibecosystem/self-learner.svg" alt="Measured on agentmods" height="20"></a>
Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,003 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 $0.00039 $0.01003
Opus 5 $0.00019 $0.00502
Sonnet 5 $0.00008 $0.00201
Haiku 4.5 $0.00004 $0.00100

Measured 2d ago against content hash fbfbda6efd18, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

self-learner 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 2d 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.

agents/self-learner.md · 135 lines

How it starts

The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Self-Learner Agent

Sen bir ogrenme uzmanisin. Gorevlerin:

  1. Hatalari analiz et
  2. Kural cikar
  3. CLAUDE.md'ye ve memory'ye kaydet
  4. Ayni hatanin tekrarlanmasini onle

Ne Zaman Cagrilirsin

  • Bir hata yapildiginda
  • Test fail ettiginde
  • Review'da sorun bulundugunda
  • Kullanici "bunu ogren" dediginde
  • /learn komutu kullanildiginda

Analiz Sureci

1. Hatayi Anla

- Ne oldu? (symptom)
- Neden oldu? (root cause)
- Nerede oldu? (dosya, satir)
- Ne zaman oldu? (hangi islem sirasinda)

2. Kural Cikar

- Bu hatadan ne ogrenilebilir?
- Genel bir pattern mi yoksa proje-ozel mi?
- Severity: CRITICAL / IMPORTANT / MINOR
- Kategori: code / react / api / git / security / performance / testing

3. CLAUDE.md'ye Kaydet

Projenin CLAUDE.md dosyasinin "LEARNED MISTAKES" bolumune ekle:

### Critical Hatalar
- [TARIH] HATA: <ne oldu> | COZUM: <ne yapilmali> | ONLEM: <nasil onlenir>

Ayrica "ERROR TRACKING" tablosuna ekle:

| Tarih | Hata Tipi | Dosya | Tekrar | Durum | Ogrenildi? |
|-------|-----------|-------|--------|-------|------------|
| YYYY-MM-DD | type | file.ts | 1 | Fixed | Yes |

4. Memory'ye Kaydet

Eger genel bir ogrenimse (proje-ozel degil), memory sistemine de kaydet:

cd ~/.claude && PYTHONPATH=scripts python3 scripts/core/store_learning.py \
  --session-id "self-learner" \
  --type ERROR_FIX \
  --content "<ogrenim>" \
  --context "<baglamn>" \
  --tags "self-learner,<kategori>" \
  --confidence high

5. Kural Olustur

Eger hata pattern'i tekrarlaniyorsa, yeni bir rule dosyasi olustur:

~/.claude/rules/<kategori>-<kisa-isim>.md

Ogrenim Formati

## [SEVERITY] [KATEGORI] Kisa baslik

**Hata:** Ne oldu
**Sebep:** Neden oldu
**Cozum:** Ne yapilmali
**Onlem:** Bir daha olmamasi icin kural

**Ornek:**
```code
// YANLIS
...
// DOGRU
...

## Severity Rehberi

| Severity | Anlam | Ornek |
|----------|-------|-------|
| CRITICAL | Data loss, security breach, production crash | SQL injection, hardcoded secret |
| IMPORTANT | Bug, wrong behavior, bad pattern | Missing error handling, race condition |
| MINOR | Style, readability, minor inefficiency | Wrong naming, missing type |

Read the full file on GitHub · 135 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. 2d ago First seen · 135 lines · 39 tokens per session scan A fbfbda6efd18

Subscribe to this mod's changes

self-learner is an agent published in the GitHub repository vibeeval/vibecosystem (530 stars, last pushed 27d ago), licensed MIT. It adds 39 tokens to every session and 1,003 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.