knowledge-promoter

An agent that reviews journal entries and suggests which useful ideas should become permanent knowledge notes.

In plain words
What is it for?
It scans a chosen period of journals, scores possible candidates, asks for approval, creates knowledge notes for approved sections, and links them back to the journal.
Why use it?
It reduces the chance that reusable information remains buried in old daily notes.

Agent

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/knowledge-promoter
Clone the repo
git clone --depth 1 https://github.com/datacore-one/datacore
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 606 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 $0.00000 $0.00606
Opus 5 $0.00000 $0.00303
Sonnet 5 $0.00000 $0.00121
Haiku 4.5 $0.00000 $0.00061

Measured 2d ago against content hash 8075872f32d3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

knowledge-promoter 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/knowledge-promoter.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Knowledge Promoter

Scans journal entries for high-value content and promotes it to permanent knowledge artifacts via knowledge-extractor.

When to Use

  • Weekly review (automated scan of past week's journals)
  • Manual /promote command for on-demand promotion
  • Nightshift weekly task (scheduled Sunday night)

Inputs

  • Space: Target space to scan (default: detect from cwd)
  • Period: How far back to scan (default: 7 days)
  • Threshold: Minimum promotion score (default: 0.4)

Workflow

  1. Scan: Run journal_scanner.py on journal entries within the period
  2. Present: Show scored sections to user with promotion recommendations
  3. Confirm: User approves/rejects each candidate (or auto-approve in nightshift mode)
  4. Extract: For each approved section, spawn knowledge-extractor with:
    • Input: the journal section text
    • Source type: "journal entry"
    • Target space: same space as journal
    • Instruction: create zettels for reusable concepts, skip literature note (journal IS the source record)
  5. Link back: Add Promoted: [[Zettel Name]] annotation to original journal section
  6. Log: Append promotion record to journal for the day

Heuristics (journal_scanner.py)

The scanner uses pattern matching, not LLM inference:

  • Positive: root cause analysis, architecture decisions, research findings, wiki-links, code blocks, paper references, substantial bullet lists
  • Negative: standup notes, WIP items, quick syncs
  • Length bonus: longer sections score higher (capped)
  • Threshold 0.4 = moderate confidence. Adjust per space.

Modes

Interactive (/promote)

  • Shows each candidate with score and preview
  • User confirms or skips each one
  • Can override threshold: /promote --threshold 0.6
  • Can target specific date: /promote --date 2026-04-01

Nightshift (autonomous)

  • Runs with threshold 0.6 (higher bar for unsupervised)
  • Auto-approves all candidates above threshold
  • Creates promotion summary in morning briefing
  • Skips sections already annotated with Promoted:

Read the full file on GitHub · 67 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 · 67 lines · 0 tokens per session scan A 8075872f32d3

Subscribe to this mod's changes

knowledge-promoter 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 606 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.

Related

Other agents, from other repositories