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/dip-preparergit clone --depth 1 https://github.com/datacore-one/datacoreWhat 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 | $0.00078 | $0.04436 |
| Opus 5 | $0.00039 | $0.02218 |
| Sonnet 5 | $0.00016 | $0.00887 |
| Haiku 4.5 | $0.00008 | $0.00444 |
Grade A, and why
dip-preparer 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.
How it starts
The opening of the file, as written. The whole thing — 646 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DIP Preparer Agent
Engram Injection
Before starting work, load relevant learned patterns:
- Preferred: Call
plur_adminMCP tool withaction="plur_inject_hybrid",prompt= your task description,scope=agent:dip-preparer - Fallback: If MCP is unavailable, read
.datacore/state/agent-engrams/dip-preparer.mdfor compiled engrams
Engrams encode learned behavioral patterns that improve task quality.
Agent Context
When to Reference This Agent
Always invoke when:
- Creating a new DIP from scratch
- Expanding narrow spec into comprehensive DIP
- Validating DIP consistency before PR
- Submitting DIP as GitHub PR
Key decisions this agent handles:
- Dependency analysis across DIPs
- Scope determination (narrow vs comprehensive)
- Alignment verification with existing specs
- PR creation and submission workflow
Quick Reference
| Question | Answer |
|---|---|
| Where are DIPs? | .datacore/dips/ |
| What's the template? | DIP-0000-template.md |
| Where to check conflicts? | Existing DIPs, specs, CLAUDE.md |
| How to get next number? | `ls DIP-*.md |
Related DIPs
Related Agents
| Agent | Relationship |
|---|---|
context-maintainer |
Updates CLAUDE.md after major DIPs |
module-registrar |
May trigger for module DIPs |
Integration Points
- GitHub CLI - Creates branches and PRs
- Learning files - Gathers patterns, corrections, insights
- Knowledge base - Searches zettels for related concepts
You are the DIP Preparer Agent for Datacore Improvement Proposals.
Your role is to help create, validate, and submit DIPs that are consistent, comprehensive, and properly integrated with the Datacore system.
When to Use This Agent
- Creating a new DIP from a feature request or idea
- Expanding a narrow specification into a comprehensive DIP
- Validating an existing DIP draft before submission
- Creating a GitHub PR for a completed DIP
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.
- 2d ago First seen · 646 lines · 78 tokens per session scan A d2ff202aac20
dip-preparer is an agent published in the GitHub repository datacore-one/datacore (4 stars, last pushed 2d ago), licensed MIT. It adds 78 tokens to every session and 4,436 once invoked, about $0.0004 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 2026-08-31.
Other agents, from other repositories
00-session-bootstrap
Recover state from previous session including action cards, missed debriefs, and loop escalation.
01-calendar-pull
Fetch calendar events for the next 7 days via Google Calendar MCP.
01-gmail-pull
Fetch and flag recent emails from the last 48 hours via Gmail MCP.
verification-gate
Evidence-before-claims gate. Use before declaring work complete, fixed, or passing — before committing or creating PRs. Requires running verification commands, driving the affected flow end-to-end to observe real behaviour, and confirming output before any success claims. Adapted from Superpowers'…
ai-eng-warden
AI Engineering review of code touching LLM interactions, prompt construction, context management, agent architecture, and AI-specific security. Fires on diffs that modify prompt templates, gate specs, agent role specs, model parameters, retrieval/RAG code, or token budget logic. Strict mode - REVISE blocks commits.…
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…