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/mlflow/mlflow/github-actionsgit clone --depth 1 https://github.com/mlflow/mlflowWhat 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 | $0.00046 | $0.00046 |
| Opus 5 | $0.00023 | $0.00023 |
| Sonnet 5 | $0.00009 | $0.00009 |
| Haiku 4.5 | $0.00005 | $0.00005 |
Grade A, and why
mlflow github-actions.instructions.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 yesterday.
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
GitHub Actions Code Review Instructions
For workflow style conventions, see .claude/rules/github-actions.md.
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.
- yesterday First seen · 8 lines · 46 tokens per session scan A e20edb6c3901
mlflow github-actions.instructions.md is an instructions file published in the GitHub repository mlflow/mlflow (27,737 stars, last pushed yesterday), licensed Apache-2.0. It adds 46 tokens to every session, about $0.0002 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 2026-08-30.
Other instructions, from other repositories
pycaret AGENTS.md
AGENTS.md instructions for pycaret/pycaret, covering agents.md — pycaret agent instructions, tl;dr — the 60-second briefing, start here, non-negotiables and universal rules.
pycaret CLAUDE.md
Claude Code instructions for pycaret/pycaret, covering claude.md — claude code guide for this repo, at a glance, how contributors use this repo with claude code, files claude code reads (in order) and common commands.
plexe AGENTS.md
Instructions for plexe-ai/plexe, covering agents.md, architecture, 6-phase workflow (plexe/workflow.py), multi-agent system (plexe/agents/) and tree search (plexe/search/).
claude-secure-coding-rules CLAUDE.md
Instructions for TikiTribe/claude-secure-coding-rules, covering claude.md - secure coding rules for claude code, project overview, repository structure, rule counts and rule format.
mflowy AGENTS.md
AGENTS.md instructions for ifoodsci-ai/mflowy, covering agents.md, project, 开发命令, 分层 and 添加能力.
ML-MLOps-Portfolio AGENTS.md
Instructions for DuqueOM/ML-MLOps-Portfolio, covering agents.md — ml service template, project identity, agent architecture, critical patterns — do not violate and ml serving invariants.