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/sorryorc/mythos-mcp/agents-mdgit clone --depth 1 https://github.com/sorryorc/mythos-mcpWrote 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/sorryorc/mythos-mcp/agents-md)<a href="https://agentmods.dev/instructions/sorryorc/mythos-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/sorryorc/mythos-mcp/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 5.1 | $0.00189 | $0.00189 |
| Opus 5 | $0.00095 | $0.00095 |
| Sonnet 5 | $0.00038 | $0.00038 |
| Haiku 4.5 | $0.00019 | $0.00019 |
Grade A, and why
mythos-mcp 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 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
Agent Guardrails
Workspace
- Use any local working directory; the project does not assume a fixed path.
- If your working directory sits inside a cloud-synced folder (OneDrive / Dropbox / etc.), prefer small patches and verify file integrity after edits — concurrent sync can truncate files mid-write.
Completion Gate
- A generated
dist/directory is not proof of success. - TypeScript must keep
"noEmitOnError": trueso compile errors cannot produce misleading output. - For gate/eval work, "done" means
npm run eval:gatehas run successfully and produced passing metrics. - For repository work, "done" means the relevant test command has run successfully.
- Do not claim completion from edited files, emitted artifacts, or partial checks.
Reporting
- Report the exact verification command and key result.
- If verification did not run, state that the work is unverified.
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 · 17 lines · 189 tokens per session scan A 2dd1b38442e3
mythos-mcp AGENTS.md is an instructions file published in the GitHub repository sorryorc/mythos-mcp (1 stars, last pushed 2mo ago), licensed MIT. It adds 189 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
rtl-agent-team CLAUDE.md
Claude Code instructions for babyworm/rtl-agent-team, covering language rule, important — project identity, why agentic coding for silicon ip, plugin runtime vs. development context (critical) and plugin architecture: dynamic prompt injection.
baerly-storage CLAUDE.md
Toolchain, verification matrix, module map, conventions, anti-patterns. The main agent entry point.
skills AGENTS.md
Instructions for workersio/skills, covering agents.md, canonical paths and maintenance rules.
skills CLAUDE.md
Instructions for workersio/skills, covering claude.md, canonical paths and maintenance rules.
hashloom CLAUDE.md
Claude Code instructions for davet47/hashloom, covering working rules for hashloom, git is the user's, scope discipline, hashloom develops on hashloom and definition of done: >5x token reduction.
anatomia CLAUDE.md
Instructions for anatomia-dev/anatomia, a project described as: Spec-driven agent harness for Claude Code and Codex — five-agent pipeline (scope, plan, build, verify, learn) with an auditable proof chain.