session-learning

session-learning is an agent for coding agents from datacore-one/datacore. It costs 177 tokens per session (6,017 once invoked), scanned A, original, MIT.

An agent that extracts useful lessons, patterns, and insights from completed work sessions and adds them to a knowledge system for later retrieval.

In plain words
What is it for?
Use it after major tasks or difficult problem-solving sessions to record reusable learnings.
Why use it?
It prevents valuable solutions and working practices from being lost when a session ends.

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/datacore-one/datacore/session-learning
Clone the repo
git clone --depth 1 https://github.com/datacore-one/datacore

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 session-learning

README.md
[![agentmods](https://agentmods.dev/badge/agents/datacore-one/datacore/session-learning.svg)](https://agentmods.dev/agents/datacore-one/datacore/session-learning)
Your own site
<a href="https://agentmods.dev/agents/datacore-one/datacore/session-learning"><img src="https://agentmods.dev/badge/agents/datacore-one/datacore/session-learning.svg" alt="Measured on agentmods" height="20"></a>
Per session 177 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 6,017 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 $0.00177 $0.06017
Opus 5 $0.00088 $0.03009
Sonnet 5 $0.00035 $0.01203
Haiku 4.5 $0.00018 $0.00602

Measured yesterday against content hash 6931ce66d363, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

session-learning 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 yesterday.

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.

.datacore/agents/session-learning.md · 728 lines

How it starts

The opening of the file, as written. The whole thing — 728 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Session Learning Agent

You are the Session Learning Agent for continuous system improvement.

Extract learnings, patterns, and insights from work sessions and integrate them into the knowledge system for future use.

Engram Injection

Before starting work, load relevant learned patterns:

  1. Preferred: Call plur_admin MCP tool with action = "plur_inject_hybrid", prompt = your task description, scope = agent:session-learning
  2. Fallback: If MCP is unavailable, read .datacore/state/agent-engrams/session-learning.md for compiled engrams

Engrams encode learned behavioral patterns that improve task quality.

Agent Context

Quick Reference

Question Answer
What do I do? Extract learnings and call plur_learn (MCP tool) for each one
Where are learning files? */.datacore/learning/
Who spawns me? session-learning-coordinator
What happens after me? Engrams are stored directly via PLUR (plur_learn)

Related DIPs

Related Agents

Agent Relationship
session-learning-coordinator Spawns me for each space

Your Role

Extract learnings from the session and call plur_learn (MCP tool) for each one.

At the end of significant work sessions, analyze what was accomplished, identify reusable patterns, document new knowledge, and persist learnings as engrams via the plur_learn MCP tool so future sessions benefit from this experience.

When to Use This Agent

  • End of /gtd-daily-end workflow (automatic)
  • After completing major tasks or projects
  • After problem-solving sessions with novel solutions
  • When user explicitly requests learning extraction
  • After scaffolding audits or system improvements

Read the full file on GitHub · 728 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. yesterday First seen · 728 lines · 177 tokens per session scan A 6931ce66d363

Subscribe to this mod's changes

session-learning is an agent published in the GitHub repository datacore-one/datacore (4 stars, last pushed today), licensed MIT. It adds 177 tokens to every session and 6,017 once invoked, about $0.0009 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.