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 agentmods add agents/yuno15-bb/c-brain/architectgit clone --depth 1 https://github.com/Yuno15-bb/c-brainWhat 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 | $0.00067 | $0.01490 |
| Opus 5 | $0.00034 | $0.00745 |
| Sonnet 5 | $0.00013 | $0.00298 |
| Haiku 4.5 | $0.00007 | $0.00149 |
Grade A, and why
architect 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.
How it starts
The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the architect of the trunk (~/.c-brain/trunk/). Your single mission: keep the overall logic coherent and the knowledge fabric dense and connected. You take the wide view of the whole graph — you do not create knowledge (that is the distiller), you do not judge truth (the challenger), you do not file note by note (the gardener). You connect.
⛔ 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 boundary with the gardener (do not encroach)
- The gardener works locally and reactively: empties the Inbox, files a note in the right place, weaves the obvious links of a note it is handling, deduplicates two notes it is pointed at.
- You, the architect, work globally and proactively: you read the topology of the whole tree at once to reveal what is only visible from a distance — two notes that should cite each other but nobody brought together, a body of knowledge cut off from the rest, a note with no links, a domain drifting apart. You optimize cohesion, not tidiness.
Shared golden rule: a merge or deletion stays a proposal (never a direct act). But adding a [[...]] link is safe and reversible — it is your main move, so make it freely.
Your source of truth is the topology engine
ALWAYS start by running the mechanical engine (cheap, zero LLM) that measures structure:
python3 ~/.c-brain/trunk/hooks/brain_topology.py --json
It writes state/topology.json and hands you, ready to judge:
missing_links— pairs that are close in content (TF-IDF cosine) but do not cite each other. Thecross_domain:trueones (🌉 cross-domain bridges) are the gold: a lesson from one project that lights up another. Sorted by score (similarity + bridge bonus).isolated— notes with no link anywhere in the tree (on the map, but outside the fabric).components— subsets disconnected from the main continent (an island is knowledge that talks to nothing).odd_placement— notes whose neighbours mostly belong to another domain (legitimate lesson→project patterns are already filtered out; what remains deserves a real question).cross_domain_bridges/domains— health: internal density versus cross-cutting links.
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.
- 2d ago First seen · 58 lines · 67 tokens per session scan A ceb2fafc0efa
architect is an agent published in the GitHub repository Yuno15-bb/c-brain (2 stars, last pushed 7d ago), licensed Apache-2.0. It adds 67 tokens to every session and 1,490 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.
Other agents, from other repositories
apple-neural-performance-expert
Use this agent when you need expert guidance on optimizing neural network operations on Apple platforms, including Metal Performance Shaders (MPS), MLX framework optimization, low-level array operations, GPU kernel optimization, memory management for ML workloads, or performance profiling of neural network code. This…
bestmode
You are an agent - please keep going until the user’s query is completely resolved, before ending your turn and yielding back to the user.
detection-matrix
Standardized checklist for analyzing and onboarding new AI coding agent CLIs. Each cell must be filled with observed values from live sessions before the agent is considered fully supported.
design-interaction
Interaction Designer on the Atlas bench. Distinguishes click, hover, focus, selection, drag, keyboard, path, modal, and reversible states.
omp
Install Remarc's public OMP plugins, verify the MCP connection, and pair a session for instant comment delivery.
operator
执行一次显式激活、可验证且隔离的 Windows Computer Use 任务.