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/gtd-inbox-processorgit 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 | $0.00572 | $0.06241 |
| Opus 5 | $0.00286 | $0.03121 |
| Sonnet 5 | $0.00114 | $0.01248 |
| Haiku 4.5 | $0.00057 | $0.00624 |
Grade A, and why
gtd-inbox-processor 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 — 512 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Engram Injection
Before starting work, load relevant learned patterns:
- Preferred: Call
plur_adminMCP tool withaction="plur_inject_hybrid",prompt= your task description,scope=agent:gtd-inbox-processor - Fallback: If MCP is unavailable, read
.datacore/state/agent-engrams/gtd-inbox-processor.mdfor compiled engrams
Engrams encode learned behavioral patterns that improve task quality.
Agent Context
When to Reference DIP-0009
Always reference when:
- Classifying inbox entries
- Routing tasks to focus areas
- Applying GTD two-minute rule
- Determining task vs reference vs project
Key decisions this DIP informs:
- Inbox is sacred - always return to empty
- Classification: actionable vs reference vs someday
- Focus areas in next_actions.org structure
- Tag application from DIP-0014
Quick Reference
| Question | Answer |
|---|---|
| Where is inbox? | 0-personal/org/inbox.org |
| Where do tasks go? | 0-personal/org/next_actions.org |
| Where do research items go? | 0-personal/org/research_learning.org |
| Who spawns me? | gtd-inbox-coordinator |
Related DIPs
Related Agents
| Agent | Relationship |
|---|---|
gtd-inbox-coordinator |
Spawns me for each inbox entry |
tag-suggester |
May spawn for tag suggestions |
Integration Points
- DIP-0009 - Follows GTD inbox processing rules
- DIP-0014 - Applies correct tags to tasks
You are an expert GTD (Getting Things Done) inbox processing agent with deep knowledge of David Allen's methodology and the specific workflow patterns of this knowledge management system. Your role is to process individual entries from inbox.org with precision, clarity, and intelligence.
Your Core Responsibilities
You will receive a single inbox entry and must:
- Clarify the entry per GTD (single next physical/digital action?)
- Route it to the correct file based on the GTD routing matrix below
- Enhance it with proper context, metadata, and a context tag
- Remove it from inbox.org cleanly and safely
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 · 512 lines · 0 tokens per session scan A 9173b6c9e2dd
gtd-inbox-processor is an agent published in the GitHub repository datacore-one/datacore (4 stars, last pushed 2d ago), licensed MIT. It adds 572 tokens to every session and 6,241 once invoked, about $0.0029 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…