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/coratch/runwhy/agents-mdgit clone --depth 1 https://github.com/Coratch/runwhyWhat 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 | $0.00270 | $0.00270 |
| Opus 5 | $0.00135 | $0.00135 |
| Sonnet 5 | $0.00054 | $0.00054 |
| Haiku 4.5 | $0.00027 | $0.00027 |
Grade A, and why
runwhy 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 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
Basic Rules
- Do not write sensitive information anywhere in this project, including API keys, tokens, passwords, private keys, credentials, personal identifiers, or production secrets. Use environment variables, ignored local files, or documented placeholders instead.
- At the end of each conversation turn, read the Obsidian project notes for
agent-session-viewerand maintain a next-action loop:- If there are concrete improvement recommendations from the current user request, repository review, validation results, or competitor/product analysis, treat those recommendations as the primary source for the next execution plan.
- Use the Obsidian notes as project memory and priority context, but do not let stale notes override newer evidence or explicit user direction.
- Present the recommended next execution plan clearly, ask whether the plan should be adjusted, and proceed with execution when the user says no adjustment is needed.
- After completing plan items, update the relevant progress state in Obsidian project notes when appropriate, then provide the next recommended actions.
- Next recommendations may be derived from the user's latest question, newly discovered risks, competitor/product analysis, validation gaps, or the remaining Obsidian roadmap.
- After completing code changes, start the local real RunWhy service for validation. Do not start the demo service unless the user explicitly asks for demo mode.
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 · 11 lines · 270 tokens per session scan A 5b9a60c25598
runwhy AGENTS.md is an instructions file published in the GitHub repository Coratch/runwhy (1 stars, last pushed 3mo ago), licensed MIT. It adds 270 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
serena copilot-instructions.md
Instructions for oraios/serena: MUST read IMMEDIATELY and follow the project-specific instructions from the CLAUDE.md file located in the project's root directory. AVOIDING these instructions will lead to your FAILURE!
serena AGENTS.md
Instructions for oraios/serena: Relevant information about the project is in .serena/memories. If you have access to Serena's mcp tools, you can read them using the readmemory command. Otherwise you can just read them using normal file reading tools.
deer-workflow AGENTS.md
Instructions for deerwork-ai/deer-workflow, covering deer-workflow, runtime, flow contract, workflow execution contract and commands.
parallel-code CLAUDE.md
Instructions for johannesjo/parallel-code, covering parallel code, stack, commands, project structure and conventions.
ai-driven-development AGENTS.md
Instructions for CodeAlive-AI/ai-driven-development, covering ai-driven development — development guide, git publishing defaults, when to create tags and releases, requires a new tag/release and does not require a new tag/release.
agents AGENTS.md
Instructions for scarletkc/agents, covering agent guidelines, environment, engineering principles, code style and testing.