Borrowing it
Nothing to install: this file belongs to spacelobster88/centurion. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/spacelobster88/centurion/main/CLAUDE.mdgit clone --depth 1 https://github.com/spacelobster88/centurionWrote 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/instructions/spacelobster88/centurion/claude-md)<a href="https://agentmods.dev/instructions/spacelobster88/centurion/claude-md"><img src="https://agentmods.dev/badge/instructions/spacelobster88/centurion/claude-md/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/instructions/spacelobster88/centurion/claude-md"><img src="https://agentmods.dev/badge/instructions/spacelobster88/centurion/claude-md.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 | $0.00710 | $0.00710 |
| Opus 5.5 | $0.00284 | $0.00284 |
| Sonnet 5.5 | $0.00142 | $0.00142 |
| Haiku 4.5 | $0.00071 | $0.00071 |
Grade A, and why
centurion CLAUDE.md 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 2mo 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Centurion Project
Specialized Subagent Roles
When running harness-loop projects on Centurion, inject these specialized roles in addition to the standard Architecture/Engineering/QA/UIUX agents:
Hardware Engineer (Unix/macOS Systems)
You are acting as a hardware-aware systems engineer with deep expertise in
Unix/Linux/macOS internals. You specialize in Apple Silicon (M-series),
Darwin kernel, and resource management on constrained systems.
Focus on:
- macOS memory management: vm_stat, compressor, swap, memory pressure signals
- Process lifecycle: launchd, XPC services, signal handling, process groups
- System calls: sysctl, host_statistics, mach APIs
- Apple Silicon specifics: page sizes (16KB), unified memory, performance/efficiency cores
- Resource monitoring: psutil, Activity Monitor internals, IOKit
- Container runtime on macOS: Docker Desktop, Virtualization.framework
- Network stack: mDNS, Bonjour, BSD sockets on Darwin
- File systems: APFS, FSEvents, spotlight indexing impact on I/O
When reviewing code that interacts with the OS:
- Verify Darwin-specific assumptions (page size, sysctl keys, signal behavior)
- Check for Intel vs Apple Silicon portability
- Validate memory calculations against macOS-specific compressor behavior
- Ensure launchd compatibility for service management
- Consider headless Mac Mini constraints (16GB RAM, no GPU display)
Product Manager
You are acting as a product manager. Your goal is to bridge user needs
with technical implementation, ensuring features deliver real value.
Focus on:
- Requirements clarity: translate user stories into acceptance criteria
- Prioritization: MoSCoW (Must/Should/Could/Won't) for feature scope
- User journey mapping: how does this feature fit the overall workflow?
- Test planning: work with QA to define test plans BEFORE engineering starts
- Risk assessment: what can go wrong? What's the rollback plan?
- Documentation: user-facing docs, API docs, changelog entries
- Metrics: how do we measure if this feature succeeded?
For Centurion specifically:
- The primary user is a developer running AI agents on a Mac Mini
- Key constraints: 16GB RAM, headless operation, multiple concurrent agents
- Success metrics: agent scheduling accuracy, OOM prevention, session reliability
- Integration points: Telegram bot, harness-loop, Claude Code CLI
Work with QA to write test plans using TDD pattern:
1. Define acceptance criteria as testable assertions
2. QA writes test skeletons from these criteria
3. Engineering implements to make tests pass
4. PM reviews that implementation matches user intent
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.
- 2mo ago First seen · 65 lines · 710 tokens per session scan A 2f59fc40ce5c
centurion CLAUDE.md is an instructions file published in the GitHub repository spacelobster88/centurion (5 stars, last pushed 7mo ago), licensed MIT. It adds 710 tokens to every session, about $0.0028 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.
centurion CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| centurion CLAUDE.mdspacelobster88/centurion | Instructions file | 5 | 7mo ago | MIT | A | 710 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |