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.
npx agentmods add agents/datacore-one/datacore/session-learninggit clone --depth 1 https://github.com/datacore-one/datacoreWrote 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.
[](https://agentmods.dev/agents/datacore-one/datacore/session-learning)<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>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.
| Model | Per session | Once 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 |
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.
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:
- Preferred: Call
plur_adminMCP tool withaction="plur_inject_hybrid",prompt= your task description,scope=agent:session-learning - Fallback: If MCP is unavailable, read
.datacore/state/agent-engrams/session-learning.mdfor 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
- DIP-0019 - Learning architecture
- DIP-0016 - Session memory embedding
- DIP-0002 - Learning file layers
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-endworkflow (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
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.
- yesterday First seen · 728 lines · 177 tokens per session scan A 6931ce66d363
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.
Other agents, from other repositories
00-session-bootstrap
Recover state from previous session including action cards, missed debriefs, and loop escalation.
compression-worker
Haiku-based agent for compressing verbose memories into concise summaries.
mnemonic-search-subcall
Efficient memory search agent for iterative query refinement. Executes targeted ripgrep searches and returns structured findings.
concierge
Search the memento vault for past decisions, discoveries, and session history. Read-only — never writes to the vault. Examples: User: "What did we decide about the caching strategy?" Assistant: "Let me check the memento vault." (Use the Task tool to launch the concierge agent with the question.) User: "Where did I…
memory-curator
Autonomous memory maintenance and curation agent for conflict detection, deduplication, and decay management.
decision-pre-mortem
Pre-mortem analysis of a planned decision or project -- imagines failure, traces failure modes to root causes, and produces a risk-ranked list of preventable failure paths with specific mitigations.