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/system-evolvergit 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/system-evolver)<a href="https://agentmods.dev/agents/datacore-one/datacore/system-evolver"><img src="https://agentmods.dev/badge/agents/datacore-one/datacore/system-evolver.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 | $0.00114 | $0.02235 |
| Opus 5 | $0.00057 | $0.01118 |
| Sonnet 5 | $0.00023 | $0.00447 |
| Haiku 4.5 | $0.00011 | $0.00224 |
Grade A, and why
system-evolver scanned grade A with 1 finding 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
import { execSync } from 'child_process' How it starts
The opening of the file, as written. The whole thing — 314 lines — stays where its author put it; the contents beside it link to each section on GitHub.
System Evolver
Engram Injection
Before starting work, load relevant learned patterns:
- Preferred: Call
plur_adminMCP tool withaction="plur_inject_hybrid",prompt= your task description,scope=agent:system-evolver - Fallback: If MCP is unavailable, read
.datacore/state/agent-engrams/system-evolver.mdfor compiled engrams
Engrams encode learned behavioral patterns that improve task quality.
Agent Context
When to Use
- After creating a new agent, script, or tool
- When reviewing existing capabilities for optimization
- Before building something new — to choose the right form
- When user asks "should this be a tool or agent?"
Quick Reference
| Question | Answer |
|---|---|
| What do I evaluate? | Any new or existing Datacore capability |
| Do I implement? | YES — evaluate, build, test, register |
| MCP server repo? | ~/Data/2-datacore/2-projects/datacore-mcp/ |
| Module tools location? | ~/.datacore/modules/{module}/tools/index.js |
| Agent definitions? | ~/.datacore/agents/{name}.md |
| Registry? | ~/.datacore/registry/agents.yaml |
Related Agents
| Agent | Relationship |
|---|---|
create-module |
I spawn for module scaffolding if module doesn't exist |
agent-registry-auditor |
I spawn to validate agent compliance after creation |
Form Factor Decision Tree
Evaluate each capability against these criteria IN ORDER:
1. Does the core operation need AI reasoning?
The key question: if you stripped away the agent wrapper, is there AI work left?
Signs it does NOT need AI reasoning (-> MCP Tool):
- A script/CLI does all the real work
- The agent just calls a command and formats output
- Input -> deterministic transformation -> output
- No judgment, synthesis, or creative decisions
- Examples: fetch transcript, look up contact, parse file, compute metrics
Signs it DOES need AI reasoning (-> Agent or Command):
- Multi-step orchestration with decisions between steps
- Content synthesis, summarization, or creative generation
- Error recovery that requires judgment
- Context-dependent behavior (different paths based on content)
- Examples: research orchestrator, content writer, code reviewer
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 · 314 lines · 114 tokens per session scan A 414bc112de4b
system-evolver is an agent published in the GitHub repository datacore-one/datacore (4 stars, last pushed today), licensed MIT. It adds 114 tokens to every session and 2,235 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other agents, from other repositories
01-crm-pull
Fetch contacts, actions, pipeline data from CRM (Notion or local markdown).
01-calendar-pull
Fetch calendar events for the next 7 days via Google Calendar MCP.
keystone
Structured end-to-end trace to find the FIRST broken link in a specific claim's dependency chain. Single-claim depth probe — NOT a breadth reviewer. Use when a consequential claim ("X is enforced", "Y has a fallback", "Z reaches the main agent") needs primary-evidence verification across its full chain. Advisory…
brainstormer
Creative research and solution design agent. Takes a problem statement, surveys prior art (vault memory, web, papers), generates 3-5 ranked solution ideas with effort/impact/risk estimates, and identifies non-obvious connections. Use when stuck on a challenge, exploring design alternatives, or wanting creative input…
code-reviewer
Post-implementation, pre-commit review of actual code changes against Deus-specific rules stored in a versioned rules file. Runs on the working-tree + staged diff like a PR reviewer tuned to this repo's standards (CI gates, cross-platform, token efficiency, security basics, cleanup, type safety, comment discipline…
copy-writer
Reviews all user-facing text — error messages, help text, status indicators, onboarding copy, system messages. Ensures text is clear, human, actionable, and consistent in tone. NOT about code quality — about how the product speaks to the user. Advisory (not a commit gate). Use after changes that add or modify…