Aller au contenu
TakoAPI
Retour aux skills

mulch-self-improving-agent

par runeweaverstudios

Coding Agents & IDEs
—Pas encore noté
Ta note

Résumé

Mulch Self Improver — Let your agents grow 🌱.

Description

Ce que fait ce skill

Mulch is a CLI tool that records agent learnings (failures, conventions, decisions, patterns) to a git-tracked append-only store. Agents run `mulch prime` at session start to load prior expertise and `mulch record` during work to capture new knowledge. Learnings persist across sessions and are shared across teammates working in the same project.

Unlike in-session memory or ad-hoc notes, Mulch stores learnings in git-tracked JSONL files that are queryable, linkable, and visible to all agents and teammates in the same project.

Quand l'utiliser

  • Recording why an API call failed so future sessions skip the same mistake
  • Capturing a corrected coding convention after user feedback mid-session
  • Loading accumulated project expertise before starting a complex debugging task
  • Documenting an architectural decision and its rationale for future reference
  • Promoting a repeatedly useful pattern to shared CLAUDE.md or AGENTS.md

Exemple de workflow

ENTRÉE

User corrects agent: 'No, use pnpm not npm in this project'

AGENT
  1. 1

    Runs mulch search "npm" to check for existing related records

  2. 2

    Determines no existing record covers this convention

  3. 3

    Runs mulch record backend --type convention --content "Use pnpm not npm" to save the learning

  4. 4

    Flags the convention as a candidate for promotion to CLAUDE.md

SORTIE

Convention saved to `.mulch/backend.jsonl`; future sessions load it automatically via `mulch prime`

Prérequis

  • mulch-cli (npm install -g mulch-cli or npx mulch-cli)

Installation

clawhub install runeweaverstudios/mulch-self-improving-agent

Exécute la commande CLI, ou colle l'instruction dans Claude Code, Cursor, Codex ou l'agent de code que tu utilises.

Liens