strategic-prioritizer

strategic-prioritizer is an agent for Claude Code from datacore-one/datacore. It costs 43 tokens per session (1,341 once invoked), scanned A, original, MIT.

An agent that scores tasks against an Intent Graph, which is a map of goals and the work connected to them. It uses keyword and tag matches to produce a strategic alignment score.

In plain words
What is it for?
Use it when building a work queue or processing an inbox to provide priority hints for tasks.
Why use it?
It helps prioritisation systems distinguish tasks that support current goals from tasks with no clear goal match.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter.

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

Made for: Claude Code.

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 strategic-prioritizer

README.md
[![agentmods](https://agentmods.dev/badge/agents/datacore-one/datacore/strategic-prioritizer.svg)](https://agentmods.dev/agents/datacore-one/datacore/strategic-prioritizer)
Your own site
<a href="https://agentmods.dev/agents/datacore-one/datacore/strategic-prioritizer"><img src="https://agentmods.dev/badge/agents/datacore-one/datacore/strategic-prioritizer.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,341 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 5.1 $0.00043 $0.01341
Opus 5 $0.00022 $0.00671
Sonnet 5 $0.00009 $0.00268
Haiku 4.5 $0.00004 $0.00134

Measured 2d ago against content hash 2fd14946ad9e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

strategic-prioritizer 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 2d ago.

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/strategic-prioritizer.md · 131 lines

How it starts

The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Strategic Prioritizer Agent

You evaluate tasks against the Datacore Intent Graph to compute strategic alignment scores.

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:strategic-prioritizer
  2. Fallback: If MCP is unavailable, read .datacore/state/agent-engrams/strategic-prioritizer.md for compiled engrams

Engrams encode learned behavioral patterns that improve task quality.

Agent Context

When to Reference

Called by:

  • queue-optimizer — during nightshift queue building
  • gtd-inbox-processor — during inbox triage for priority hints

Key decisions:

  • Intent scoring uses deterministic keyword + tag overlap (no LLM call for scoring)
  • Multi-intent tasks get priority bonus
  • Default score is 5 (neutral) when no intent match found

Quick Reference

Question Answer
Scoring method? Keyword overlap + tag bonus (deterministic)
Score range? 0-10
Default score? 5
Multi-intent bonus? +2 when task matches 2+ intents
What DIPs govern this? DIP-0009 (GTD), DIP-0011 (Nightshift)

Behavior

  1. Receive task title, description, and tags
  2. Load all four priority layers via .datacore/lib/priority_score.py
  3. Score content (title/tags) and container (space directory) separately
  4. Apply tag bonuses
  5. Apply multi-parent bonus if applicable
  6. Return: { intent: string, score: number, reasoning: string, multi_intent: boolean }

Priority layers

Scoring is not the Intent Graph alone. priority_score.Scorer layers four sources, highest band wins:

Band Source Meaning
1000 .datacore/cos/priorities.yaml restated at weekly planning — what matters NOW
500 0-personal/goals.yaml (open, with keywords) quarter-horizon commitments
200 [N]-*/venture.yaml stage + autonomy standing weight; paused ventures score below neutral
100 gtd/skills/intent-routing.md mission intents — why the work matters at all

Read the full file on GitHub · 131 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. 2d ago First seen · 131 lines · 43 tokens per session scan A 2fd14946ad9e

Subscribe to this mod's changes

strategic-prioritizer is an agent published in the GitHub repository datacore-one/datacore (4 stars, last pushed today), licensed MIT. It adds 43 tokens to every session and 1,341 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.