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/agents-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/agents-md)<a href="https://agentmods.dev/instructions/wsyjq/pollux/agents-md"><img src="https://agentmods.dev/badge/instructions/wsyjq/pollux/agents-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 | $0.00274 | $0.00274 |
| Opus 5 | $0.00137 | $0.00137 |
| Sonnet 5 | $0.00055 | $0.00055 |
| Haiku 4.5 | $0.00027 | $0.00027 |
Grade A, and why
pollux AGENTS.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 3d 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
AGENTS.md
Pollux Project Memory (MANDATORY)
This project uses projectmem as its persistent engineering memory.
At session start, call these MCP tools in order:
get_instructions()get_summary()get_project_map()when structure mattersget_plan()for current intent and parallel work
Before modifying a file, call precheck_file(path).
During work:
- Log a bug with
log_issuebefore attempting a fix. - Record every distinct attempt with
record_attemptand its real outcome. - Call
record_fixonly after verification. - Record durable choices with
add_decisionand gotchas withadd_note. - Include why the choice was made, rejected alternatives, and evidence.
Source-of-truth boundary:
- Never hand-edit
events.jsonl,summary.md, or generatedissues/*.md. - Maintain
PROJECT_MAP.mddirectly when structure or relationships change. - Maintain
plan.mddirectly for ideas, active plans, and shipped work. - Before finishing, call
get_summary()and confirm the session is recorded.
Git hooks are advisory. Search by commit title and inspect the event's
git_commit field before claiming auto-capture worked.
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.
- 3d ago First seen · 32 lines · 274 tokens per session scan A baf0a0a49af3
pollux AGENTS.md is an instructions file published in the GitHub repository Wsyjq/pollux (1 stars, last pushed 16d ago), licensed MIT. It adds 274 tokens to every session, about $0.0014 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.
cocoindex-code CLAUDE.md
Instructions for cocoindex-io/cocoindex-code, covering claude.md, build and test commands, architecture, process model and key layers.
awesome-harness-engineering AGENTS.md
AGENTS.md instructions for ai-boost/awesome-harness-engineering, covering agents.md, what this repo is, conventions, what belongs and what doesn't belong.
Meterless AGENTS.md
Instructions for Meterless/Meterless, covering agent instructions for meterless, routing table, isolation rule, repo-wide rules and non-coding agents.
open-index CLAUDE.md
Instructions for DrDroidLab/open-index, covering open index repository guidance and public-safety rules.