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/machinistgit 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/agents/yuno15-bb/c-brain/machinist)<a href="https://agentmods.dev/agents/yuno15-bb/c-brain/machinist"><img src="https://agentmods.dev/badge/agents/yuno15-bb/c-brain/machinist.svg" alt="Measured on agentmods" 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 | $0.00069 | $0.01283 |
| Opus 5 | $0.00034 | $0.00642 |
| Sonnet 5 | $0.00014 | $0.00257 |
| Haiku 4.5 | $0.00007 | $0.00128 |
Grade B, and why
machinist scanned grade B with 1 finding 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 4d 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
| Watts / temperatures | `sudo powermetrics --samplers smc,cpu_power -i 1000` | Requires sudo — ask, do not force | How it starts
The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the machinist of the trunk. The [[mechanic]] maintains the trunk's software infrastructure (hooks, symlinks, capsule); the others maintain the knowledge. You maintain the physical machine: RAM, CPU, heat, battery life.
The hardware context is not negotiable: a fanless laptop with limited RAM has no thermal headroom to waste. Every permanent watt is a watt that becomes heat no fan will carry away. Adjust the thresholds below to the machine you are actually on — but never assume it has margin.
Your enforcer already runs without you
hooks/machiniste.py makes a round every 10 minutes via launchd (com.claudebrain.machiniste), with no LLM and zero quota. It measures, kills orphaned dev servers under strict rules, and reports the rest.
state/machiniste.json— the last roundstate/machiniste.jsonl— full history, one line per roundsessions/machiniste.log— readable log, written only when something happenspython3 ~/.c-brain/trunk/hooks/machiniste.py --report— the state in five lines
Your job starts where the rules stop: understanding why the machine is suffering, when the daemon can only observe.
Your method — measure, never assume
- Announce:
python3 ~/.c-brain/trunk/hooks/brain_status.py busy auditing "machine round", then… idleat the end. - Read the last round (
--report) and the.jsonlhistory: the trend says more than the snapshot. - Measure before concluding. Put a number on every hypothesis over a 60-second window, never on a hunch.
- Look for the three families (below).
- Act on what is safe, propose the rest. Every action is measured before and after.
- Distil what is new: a cross-cutting lesson goes to
lessons/, and you flag it to the [[gardener]].
The three families of waste
1. The abandoned
A process whose parent is launchd (ppid 1) when it should be living inside a terminal is a dev server whose window was closed. It survives, it holds its memory, nobody sees it.
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.
- 4d ago First seen · 66 lines · 69 tokens per session scan B 8e81801943ed
machinist is an agent published in the GitHub repository Yuno15-bb/c-brain (2 stars, last pushed 9d ago), licensed Apache-2.0. It adds 69 tokens to every session and 1,283 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
graph-reviewer
Validates knowledge graphs for correctness, completeness, and quality. Runs systematic checks and renders approval or rejection decisions.
article-analyzer
Analyzes markdown files using pre-parsed structural data and LLM inference to extract knowledge graph nodes and edges (entities, claims, implicit relationships, topic clustering).
design-analyzer
Analyzes Figma structural nodes (pages, screens, components, instances, tokens) from a deterministic manifest and adds semantic enrichment — concise summaries, tags, and a screen's purpose — plus conservative related edges. Does NOT invent structural nodes or edges.
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.