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/mbk-dev/okama-mcp/agents-mdgit clone --depth 1 https://github.com/mbk-dev/okama-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/mbk-dev/okama-mcp/agents-md)<a href="https://agentmods.dev/instructions/mbk-dev/okama-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/mbk-dev/okama-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 | $0.01859 | $0.01859 |
| Opus 5 | $0.00929 | $0.00929 |
| Sonnet 5 | $0.00372 | $0.00372 |
| Haiku 4.5 | $0.00186 | $0.00186 |
Grade B, and why
okama-mcp AGENTS.md scanned grade B with 2 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
`chilango`, so install new files via `sudo cp` (then `sudo chown chilango:chilango`, mode 644). Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`curl -s https://mcp.okama.io/ | diff - deploy/nginx/index.html`. How it starts
The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
okama-mcp — Development rules for AI agents
Environment
- Project uses poetry for environment & dependency management.
- New dependencies must be added in
pyproject.tomland additionally torequirements.txt. - Use interpreter in poetry env (
poetry run python ...). - Always use
poetry addinstead ofpip install. - All temporary files (including generated images, screenshots, scratch scripts, data
dumps) go into the gitignored
tmp/directory at the project root — never into the repo root,/tmp, or source directories. Clean it up freely; nothing intmp/is precious.
Worktrees
Worktrees for this repo live at ~/projects/rs/wt/okama-mcp/<branch> — never inside the
repository tree. Two Orca settings enforce that and they are stored locally, not in the
repo, so a machine rebuild loses them silently; re-apply both:
worktreeBasePath: ../../../wt—orca project setup-update --setup <setup-id> --worktree-base-path ../../../wt.- Wait for setup to complete before starting agent — a toggle in Orca's repository
settings, no CLI equivalent. Without it the agent (and its MCP client) starts while
poetry installis still running, which is exactly the failure below.
Never type anything into Orca's local Setup Script field: a non-empty local script flips
commandSourcePolicy to local-only and silently disables the committed orca.yaml.
A fresh worktree has no usable environment until its poetry env is built. orca.yaml
(scripts.setup) does that automatically for Orca-created worktrees; for a manual
git worktree add, run the same two commands in the new tree before anything else:
poetry env use python3.11 # `.python-version` is inert without pyenv: poetry would
# otherwise grab the system interpreter (3.14), for which
# the okama/scipy wheels do not exist
poetry install
Skipping this breaks more than the tests: .mcp.json starts the okama MCP server with
poetry run okama-mcp stdio in the current directory, so an unbuilt env makes the server
exit before the MCP handshake and the client reports only Connection closed.
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 · 120 lines · 1,859 tokens per session scan B c74dc7ae0b18
okama-mcp AGENTS.md is an instructions file published in the GitHub repository mbk-dev/okama-mcp (4 stars, last pushed 6d ago), licensed MIT. It adds 1,859 tokens to every session, about $0.0093 per session on Opus 5. A static security scan graded it B with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.