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 skills add Yuno15-bb/c-brain --skill distillgit clone --depth 1 https://github.com/Yuno15-bb/c-brainWrote 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/skills/yuno15-bb/c-brain/distill)<a href="https://agentmods.dev/skills/yuno15-bb/c-brain/distill"><img src="https://agentmods.dev/badge/skills/yuno15-bb/c-brain/distill/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/skills/yuno15-bb/c-brain/distill"><img src="https://agentmods.dev/badge/skills/yuno15-bb/c-brain/distill.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 | $0.00070 | $0.00430 |
| Opus 5.5 | $0.00028 | $0.00172 |
| Sonnet 5.5 | $0.00014 | $0.00086 |
| Haiku 4.5 | $0.00007 | $0.00043 |
Grade A, and why
distill 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 1mo 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.
What it actually says
Distill into a note
A session ends and its reasoning goes with it unless something is written down. This writes it down, in the shape the trunk expects.
What deserves a note
Only what a future reader could not re-derive cheaply:
- a defect and how it was found, not just the fix;
- a decision, its alternatives, and why they lost;
- a constraint that is not visible in the code.
Not: what the repository already records, what only matters to this conversation, or a summary of work anyone could read from the diff.
Shape
One fact per file, in ~/.c-brain/trunk/<zone>/<slug>.md where zone is
lessons (cross-project), projects/<name>, meta (ways of working) or
life.
---
name: <short-kebab-case-slug>
description: <one line — this is what recall ranks on, so make it say the fact>
metadata:
type: reference
---
<the fact, stated so it is useful without this conversation>
Why: <what makes it non-obvious>
How to apply: <the reflex it should produce next time>
Link related notes with [[their-slug]]. Link generously — a link to a note
that does not exist yet marks something worth writing, not an error.
Then
- Add one line to
MEMORY.md:- [Title](path.md) — hook. - Check first whether a note already covers it and update that one instead. Two notes on one subject is how a trunk starts lying.
- Convert relative dates to absolute ones. "Last Tuesday" rots.
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.
- 1mo ago First seen · 51 lines · 70 tokens per session scan A 2893910c9f2c
distill is a skill published in the GitHub repository Yuno15-bb/c-brain (3 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 70 tokens to every session and 430 once invoked, about $0.0003 per session on Opus 5.5. 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 skills, from other repositories
linglu-discipline
A set of 16 operating rules for an AI coding agent, including when to read or write long-term memory and how to report completed actions. It is designed to work with the Lingshu memory service through an MCP connection.
kip-cognitive-nexus
Archived KIP 1.x integration for historical reference. Persistent graph-based memory for AI agents via KIP (Knowledge Interaction Protocol). Provides retrieval-first memory operations (KQL), durable writes (KML), schema discovery (META), and memory hygiene patterns. Use whenever the agent needs to consult or update…
memesh
Use MeMesh to remember, recall, and manage AI knowledge across sessions, and to exchange task-focused messages with local agents. Triggers when the user asks to remember something, recall past decisions, forget outdated info, learn from mistakes, analyze work patterns, contact another agent, or handle a memeshmessage…
memesh-review
Review and optimize the MeMesh memory database. Analyzes health score, finds stale or noisy memories, shows work patterns, and suggests human-reviewed cleanup actions. Use when asked to "review memories", "check memory health", "clean up knowledge", or "what's in my memory".
vellum-memory-v3-migration
One-time migration of an existing memory-v2 concept corpus into the memory-v3 section-grain "wiki" — topical articles with a stand-alone lead and queryable sections — with loss-proof staging, assistant-reviewed authoring, and a retrieval-eval gate before cutover.
mem9
Persistent cloud memory plugin for OpenClaw. This document routes setup, troubleshooting, and uninstall flows and defines config boundaries.