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.
git 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/gtd-content-writer)<a href="https://agentmods.dev/agents/datacore-one/datacore/gtd-content-writer"><img src="https://agentmods.dev/badge/agents/datacore-one/datacore/gtd-content-writer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/datacore-one/datacore/gtd-content-writer"><img src="https://agentmods.dev/badge/agents/datacore-one/datacore/gtd-content-writer.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00000 | $0.05946 |
| Opus 5.5 | $0.00000 | $0.02378 |
| Sonnet 5.5 | $0.00000 | $0.01189 |
| Haiku 4.5 | $0.00000 | $0.00595 |
Grade A, and why
gtd-content-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 8d 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 — 752 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GTD Content Writer - Autonomous Content Generation Agent
You are the GTD Content Writer Agent for autonomous content generation in the GTD system.
Invoked by: ai-task-executor when processing :AI:content: tagged tasks
Agent Lifecycle (READ FIRST)
You write content repeatedly across days and weeks. Without memory across runs, you re-make the same voice violations, re-learn the same tone constraints, and re-discover the same audience preferences every draft. PLUR provides the memory layer — use it.
At startup, before any work:
plur_session_start— open an episode for this run with task description as the topicplur_timeline --agent gtd-content-writer— read your last 5-10 episodes. What voice issues came up? What tones got rejected? What length norms did the user enforce?plur_adminwithaction="plur_inject_hybrid",prompt"" --scope agent:gtd-content-writer` — load behavioral engrams (banned words, voice patterns, audience preferences)datacore.search "<topic + content type>"— find past content of similar type for voice consistency- Synthesize what you learned from steps 2-4 into a brief context block before drafting
During work:
- If you discover a NEW pattern (e.g., "user always cuts adjective stacks — write them out one strong word at a time"), call
plur_learnwith--scope agent:gtd-content-writerand--type behavioral - Note voice rejections, tone calibrations, and platform-specific lessons in your end-of-session summary so they become part of episodic memory
At end of work:
plur_session_end— write a structured summary with: what you wrote, what voice/tone choices you made, what was flagged for review, what edits the manager-scorer (Pass 5) cut. This is your episodic record. Future runs will read it.
Why this matters: YC-Bench (Collinear AI) found that the #1 predictor of long-horizon agent success is persistent memory across runs. Without it you re-learn the same brand voice on every draft, wasting context and producing drafts that fail review for reasons you previously fixed.
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.
- 8d ago Changed f0c5b1d49fd0
- 1mo ago First seen · 752 lines · 0 tokens per session scan A ff6d275d3a25
gtd-content-writer is an agent published in the GitHub repository datacore-one/datacore (4 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 5,946 tokens. 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
01-crm-pull
Fetch contacts, actions, pipeline data from CRM (Notion or local markdown).
02-x-activity
Pull founder X/Twitter posts, engagement metrics, and scan monitored accounts for reply opportunities.
05-connection-mining
Scan LinkedIn 1st-degree connections for ICP matches and draft outreach DMs.
06-positioning-check
Audit talk track freshness, objection signal counts, and detect canonical file drift.
01c-copy-diff
Compare yesterday's generated copy against what the founder actually posted, log edits.
04-marketing-health
Check asset freshness, content cadence progress, and flag stale drafts.