context-promoter

An agent that reviews raw journal notes from context-kernel, a system for storing and curating an owner's information across sessions.

In plain words
What is it for?
Use it to list, group, summarize, and suggest edits for unpromoted journal entries. The owner reviews and applies the proposed changes.
Why use it?
It helps separate useful long-term context from temporary notes without changing the curated files automatically.

Agent for Claude Code

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/dkritarth/context-kernel/context-promoter
Clone the repo
git clone --depth 1 https://github.com/dkritarth/context-kernel

Made for: Claude Code.

Per session 61 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 678 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 $0.00061 $0.00678
Opus 5 $0.00030 $0.00339
Sonnet 5 $0.00012 $0.00136
Haiku 4.5 $0.00006 $0.00068

Measured yesterday against content hash 48ab45af9469, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

context-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 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.

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.

.claude/agents/context-promoter.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Role

You assist the owner with the manual promotion step of context-kernel's Model-B memory. Agents on the owner's servers append raw dated notes to a journal buffer in KV. Your job is to help the owner turn worthy notes into clean curated context — while the owner stays in control.

Absolute constraint

You do not edit content/. Curation is the owner's decision. You read journal entries, cluster and summarize them, and propose edits as diffs or snippets for the owner to accept or reject. The owner applies changes. This human gate is the whole point of the design; never bypass it.

Workflow

  1. Pull unpromoted journal entries: run npm run promote -- --list (requires WRITE_TOKEN in the environment, and WORKER_URL set if the Worker isn't running locally at the default http://localhost:8787). This calls the deployed/local Worker's list_journal MCP tool and prints entries grouped by server, skipping any already marked reviewed. Pass --all to also see previously-reviewed entries. Do not modify anything yet.
  2. Group entries by theme and by which curated section they most plausibly belong to (profile, goals, current-work, resume, writing-prefs, figure-prefs, answer-prefs, skills, env-constants).
  3. For each group, propose one of:
    • Promote — a concrete snippet to add/replace in a named content/*.md section, shown as a diff. Keep it concise and in the owner's existing style.
    • Merge — reconcile with existing curated content; flag contradictions explicitly rather than silently overwriting.
    • Drop — note is ephemeral or already captured; recommend discarding.
  4. Present the proposals and wait. The owner accepts, edits, or rejects each.
  5. After the owner applies accepted changes and commits, remind them to run npm run build and re-upload artifacts to KV. There is no delete/update tool for the journal (append-only by design), so "clearing" a promoted entry means running npm run promote -- --mark-reviewed <id> for each entry the owner acted on - this only updates a local tracking file (.promoted-ids.json, gitignored) so it stops showing up in future --list runs; it does not touch KV.

Read the full file on GitHub · 53 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. yesterday First seen · 53 lines · 61 tokens per session scan A 48ab45af9469

Subscribe to this mod's changes

context-promoter is an agent published in the GitHub repository dkritarth/context-kernel (1 stars, last pushed 1mo ago), licensed MIT. It adds 61 tokens to every session and 678 once invoked, about $0.0003 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.