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 instructions/wsyjq/pollux/claude-mdgit clone --depth 1 https://github.com/Wsyjq/polluxWrote 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/wsyjq/pollux/claude-md)<a href="https://agentmods.dev/instructions/wsyjq/pollux/claude-md"><img src="https://agentmods.dev/badge/instructions/wsyjq/pollux/claude-md.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 5.1 | $0.00170 | $0.00170 |
| Opus 5 | $0.00085 | $0.00085 |
| Sonnet 5 | $0.00034 | $0.00034 |
| Haiku 4.5 | $0.00017 | $0.00017 |
Grade A, and why
pollux 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 5d 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
CLAUDE.md
projectmem (MANDATORY)
Use projectmem as this project's persistent engineering memory.
At session start call get_instructions(), then get_summary(), then
get_project_map() when structure matters, and get_plan() for current intent.
Call precheck_file(path) before modifying a file.
Log bugs before fixing, record every attempt and its outcome, close issues only after verification, and record decisions/gotchas with their reasons and evidence.
Do not hand-edit events.jsonl, summary.md, or generated issues/*.md.
PROJECT_MAP.md and plan.md are maintained directly when current structure or
intent changes. Confirm the session is recorded with get_summary() before exit.
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.
- 5d ago First seen · 19 lines · 170 tokens per session scan A e7fb290df40f
pollux CLAUDE.md is an instructions file published in the GitHub repository Wsyjq/pollux (1 stars, last pushed 17d ago), licensed MIT. It adds 170 tokens to every session, about $0.0009 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 instructions, from other repositories
remem-mcp AGENTS.md
AGENTS.md instructions for tinhien11/remem-mcp, covering agent rules, always use remem-mcp, before answering or coding, before searching code and for code navigation.
wctx CLAUDE.md
Instructions for Haroon-jay/wctx: This machine runs wctx, an MCP server holding evidence from previous coding sessions across related repositories. Use it as follows.
activity-frames AGENTS.md
Instructions for nossa-y/activity-frames, covering can i install it without asking?, the mental model (10 seconds), fastest integration: mcp, from python and things you should not do.
Meterless AGENTS.md
Instructions for Meterless/Meterless, covering agent instructions for meterless, routing table, isolation rule, repo-wide rules and non-coding agents.
personal-brain-builder AGENTS.md
AGENTS.md instructions for mikeshu2001/personal-brain-builder: When the user asks to start, resume, check, connect, or maintain their shared personal memory, read skills/build-personal-brain/SKILL.md completely and follow it.
personal-brain-builder CLAUDE.md
Claude Code instructions for mikeshu2001/personal-brain-builder: For requests to start, resume, check, connect, or maintain a shared personal memory, read skills/build-personal-brain/SKILL.md completely and follow it.