Learning Scribe — Development agent for Claude Code
Gate-7 capture agent.
How to install Learning Scribe
Installs to ~/.claude/agents/effortlessmetrics-perl-lsp-learning-scribe.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/EffortlessMetrics/perl-lsp/HEAD/.claude/agents/learning-scribe.md -o ~/.claude/agents/effortlessmetrics-perl-lsp-learning-scribe.md Restart Claude Code, or start a new session, for it to be picked up.
What Learning Scribe does
name: learning-scribe description: Gate-7 capture agent. Converts every deep-review fix or observable incident into a durable docs/learnings/ entry. Runs after wisdom or independently whenever a fix-forward, post-merge incident, or deep-review correction occurs. model: haiku color: yellow isolation: worktree
You are the learning-scribe for perl-lsp. Your job is Gate 7 capture: every time a deep-review finds a real bug, a fix-forward is filed after a merged PR, or an incident (gate malfu
Alternatives in Development
- Chronicler — You are a specialized session analyst 3.6k ★
- Harvest Curator — Draft session learnings from harvest staging into lizard-ready adoption notes 1k ★
- Lumen Learning — Use this agent when the user wants to capture knowledge for later retention, review spaced-repetition facts, q 523 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Memory Writer
Budgeted reflection scribe — merges a parent agent's distilled session summary into its checkpoint file and st
Feature Flow Builder
Reducer subagent (layer 4). Composes per-feature user-observable behaviour from entry-point sidecar chains. Re
Vc Update Process Agent
UPDATE PROCESS MODE - Analyze execution, generate rule improvements, update plan files and context. Use after
Plan Adversary
Red-teams a proposed implementation plan before any code is written. Use proactively whenever a plan or approa
Incident Scribe
When a workflow fails 3+ times in same session or a prod/client-facing issue happens, writes a structured inci
Learning Reviewer
Internal agent for reviewing learnings and promoting them to rules or skills. Spawned automatically when unrev
Related Skills
Craft Reflect
Apply captured learnings to improve the Craft harness and project patterns. Converts .learnings.yaml into perm
Model Forward
Restate the model-forward stance — go with Claude, not against it; skills are scaffolding; the durable core is
Bullpen Learning
Switch self-learning on or off. When on, the matching Intern logs durable learnings (decisions, patterns, pref
