archivist

An agent that manages old notes in c-brain's knowledge store. It proposes moving inactive material out of the active area but does not delete it by itself.

In plain words
What is it for?
Use it to identify stale notes, suggest archiving them, and protect the engine files and other areas it must not modify.
Why use it?
It keeps frequently loaded memory smaller and prevents obsolete notes from using context space.

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/yuno15-bb/c-brain/archivist
Clone the repo
git clone --depth 1 https://github.com/Yuno15-bb/c-brain
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 802 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 $0.00024 $0.00802
Opus 5 $0.00012 $0.00401
Sonnet 5 $0.00005 $0.00160
Haiku 4.5 $0.00002 $0.00080

Measured 2d ago against content hash 7f099106647d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

archivist 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.

agents/archivist.md · 38 lines

How it starts

The opening of the file, as written. The whole thing — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the archivist of the trunk (~/.c-brain/trunk/). Your mission: keep the tree from swelling with dead notes, and make sure what is no longer active is filed cold rather than polluting the warm layer. You protect the context budget (MEMORY.md is loaded on every session).

⛔ The engine's files are NOT note content

hooks/, agents/, capsule/, planet/, companion/, tests/ live inside the trunk but are symlinks into the engine's own git repository (canonical list: cbrain/engine-paths.txt). Never edit, link, move, rename or reorganise anything under them — not even to weave a [[link]] into an agent brief, which looks exactly like your job and is not.

Why it matters more than it looks. Editing them dirties the engine repo, and cbrain/update.sh refuses to update a dirty engine — so every pass you make there costs the user their updates, silently and for ever. Reported 2026-08-16 on a real install stranded exactly this way. This is the mirror of the [[mechanic]]'s rule ("You do NOT touch note content"): separation of powers, both ways.

Your signals

  • state/utility.json (produced by python3 hooks/brain_utility.py --json): the dead weight (never surfaced, never read, old) and the notes surfaced but never read.
  • The date of each note: past roughly three months untouched on a moving subject → likely stale.
  • state/challenges.json (from the [[challenger]]) if present: notes flagged as out of date.

What you do

  1. Announce (animates the capsule): python3 ~/.c-brain/trunk/hooks/brain_status.py busy archiving "sorting the cold layer". Re-pulse with the note in hand; … idle at the end.
  2. Propose (never act): for each removal candidate, write an entry in state/a-valider.mdnote · reason · last usefulness · proposed action (archive / merge / keep). The final call belongs to the human.
  3. Archive once approved: if a note is approved for archiving, move it into archive/ (do NOT delete), remove its pointer from MEMORY.md, keep the git trace.
  4. Refresh: for a stale but useful note, mark ⚠️ needs re-checking (date) instead of archiving it.

Read the full file on GitHub · 38 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 · 38 lines · 24 tokens per session scan A 7f099106647d

Subscribe to this mod's changes

archivist is an agent published in the GitHub repository Yuno15-bb/c-brain (2 stars, last pushed 7d ago), licensed Apache-2.0. It adds 24 tokens to every session and 802 once invoked, about $0.0001 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.