Parse Memory — Development agent for Claude Code
Step agent that parses input into a chunk manifest for memory storage.
How to install Parse Memory
Installs to ~/.claude/agents/danielstewart77-hivemind-plugin-parse-memory.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/danielstewart77/hivemind-plugin/HEAD/agents/parse-memory.md -o ~/.claude/agents/danielstewart77-hivemind-plugin-parse-memory.md Restart Claude Code, or start a new session, for it to be picked up.
What Parse Memory does
name: parse-memory description: Step agent that parses input into a chunk manifest for memory storage. Handles both manual triggers (remember this) and automated session transcript ingestion. Writes chunk-manifest.md to the session temp path. tools: Read, Write, Bash model: sonnet maxTurns: 20
parse-memory
Parse input into discrete memory chunks and write a chunk manifest.
Input
Parse from the prompt:
trigger:manualorautomatedcontent: the item, thread, or transcr
Alternatives in Development
- Frontend Convention Checker — Use this agent when a logical chunk of frontend code has been written or modified and you need to verify it ag 109 ★
- Guidelines Extractor — Given a URL or raw text of journal author guidelines, extracts structured requirements into a guidelines/jour 67 ★
- Broca Memory For Claude Desktop — Get persistent memory in Claude Desktop in under 5 minutes 61 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Doc Ingestion Agent
Parses docs/ into REQ-ID indexed requirement slices, enforces the bug-RCA hard gate (blocks bug requirements l
Wiki Canvas
Use this agent when generating Obsidian Canvas visualizations during automated maintenance cycles. Typical tri
Schedule Scout
Stage 1 of the LectureLoop pipeline. Reads Google Calendar for a given date, parses each lecture event into {s
Save Memory
Step agent that executes memory writes from the routing manifest. Loads save specs once per run, processes eac
Manual Rule Liveness Prober
Probes a manifest manual rule for liveness via with/without-rule fresh-subagent dispatch, capturing a RED→GREE
ChatGPT Plan Review
ChatGPT implementation-plan review targeting tasks/builds/{slug}/plan.md; manual / automated / parallel modes,
Related Skills
Cjm Harness Transcripts
Parse agent-harness session transcripts (Claude Code JSONL first): the append-only record DAG, derived active
Source Ingestion
Skill for ingesting raw sources into the knowledge base with proper storage, metadata, and provenance tracking
Manifest
Real-time cost observability for OpenClaw agents — track tokens, costs, messages, and model usage. Includes Cl