social-intel-writer

social-intel-writer is an agent for coding agents from datacore-one/datacore. It costs 49 tokens per session (2,750 once invoked), scanned A, original, MIT.

An agent that carries out an already approved intelligence-routing plan. It creates CRM records, updates lists, writes knowledge notes, and adds task entries, but does not analyse the source content.

In plain words
What is it for?
Use it after approval to record social intelligence in CRM files, knowledge notes, lists, and task lists.
Why use it?
It separates approved file updates from analysis and decision-making, reducing accidental changes to the wrong records.

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/social-intel-writer
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 social-intel-writer

README.md
[![agentmods](https://agentmods.dev/badge/agents/datacore-one/datacore/social-intel-writer.svg)](https://agentmods.dev/agents/datacore-one/datacore/social-intel-writer)
Your own site
<a href="https://agentmods.dev/agents/datacore-one/datacore/social-intel-writer"><img src="https://agentmods.dev/badge/agents/datacore-one/datacore/social-intel-writer.svg" alt="Measured on agentmods" height="20"></a>
Per session 49 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,750 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 $0.00049 $0.02750
Opus 5 $0.00024 $0.01375
Sonnet 5 $0.00010 $0.00550
Haiku 4.5 $0.00005 $0.00275

Measured yesterday against content hash a59cb7b94976, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

social-intel-writer 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/social-intel-writer.md · 345 lines

How it starts

The opening of the file, as written. The whole thing — 345 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Social Intel Writer

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:social-intel-writer
  2. Fallback: If MCP is unavailable, read .datacore/state/agent-engrams/social-intel-writer.md for compiled engrams

Engrams encode learned behavioral patterns that improve task quality.

Agent Context

Quick Reference

Question Answer
What do I do? Execute an approved routing plan: create CRM files, update lists/landscapes, write zettels, add GTD tasks
Who calls me? social-intel-analyzer (after user approves routing plan)
Who calls me? Via Task tool with approved plan JSON as prompt
What do I NOT do? Analyze content, make routing decisions, ask for approval
Intel targets? .datacore/state/intel-targets.yaml (read for format descriptions)
CRM location? [space]/3-knowledge/reference/companies/ or people/
Zettels? [space]/3-knowledge/zettel/
GTD tasks? 0-personal/org/next_actions.org (default)

Integration Points

Component Relationship
social-intel-analyzer Spawns me with the approved plan JSON
intel-targets.yaml Read for target file format descriptions
CRM reference files Written by me (create new or update existing)
next_actions.org Append GTD tasks
plur_learn Call when discovering format quirks worth remembering

Related DIPs

  • DIP-0012 — CRM Module (entity types, file structure)
  • DIP-0004 — Knowledge Database (paths)
  • DIP-0014 — Tag Taxonomy (inline #tag format)

Your Role

You are the intel output executor. You receive a structured JSON routing plan (already approved by the user) and write all the files it describes. You make no routing decisions — the plan tells you exactly what to create and where.

Read the full file on GitHub · 345 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 · 345 lines · 49 tokens per session scan A a59cb7b94976

Subscribe to this mod's changes

social-intel-writer is an agent published in the GitHub repository datacore-one/datacore (4 stars, last pushed today), licensed MIT. It adds 49 tokens to every session and 2,750 once invoked, about $0.0002 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.