okama-mcp: Skill for Claude Code

.agents/skills/release-okama-mcp/SKILL.md

release-okama-mcp is a skill for Claude Code, Codex from mbk-dev/okama-mcp. It costs 149 tokens per session (2,872 once invoked), scanned B, original, MIT.

A release procedure for okama-mcp, a Model Context Protocol server distributed through PyPI and the MCP registry. It coordinates version checks, tests, documentation updates, tagging, publishing, and release notes.

In plain words
What is it for?
Use it to prepare and publish a new Python package and MCP registry release, keeping the project files, version tag, README, website, and release notes aligned.
Why use it?
It reduces the risk of publishing mismatched or unusable versions. It also requires approval before pushing the tag that starts the public release workflows.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents); mentions AGENTS.md.

This is mbk-dev/okama-mcp's own configuration. It tells Claude Code and Codex how to work on okama-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything okama-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to mbk-dev/okama-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/mbk-dev/okama-mcp/main/.agents/skills/release-okama-mcp/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/mbk-dev/okama-mcp

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for release-okama-mcp

README.md
[![agentmods](https://agentmods.dev/badge/skills/mbk-dev/okama-mcp/release-okama-mcp/github.svg)](https://agentmods.dev/skills/mbk-dev/okama-mcp/release-okama-mcp)
Your own site
<a href="https://agentmods.dev/skills/mbk-dev/okama-mcp/release-okama-mcp"><img src="https://agentmods.dev/badge/skills/mbk-dev/okama-mcp/release-okama-mcp/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for release-okama-mcp

Your own site · 80×15
<a href="https://agentmods.dev/skills/mbk-dev/okama-mcp/release-okama-mcp"><img src="https://agentmods.dev/badge/skills/mbk-dev/okama-mcp/release-okama-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 149 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,872 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00149 $0.02872
Opus 5 $0.00075 $0.01436
Sonnet 5 $0.00030 $0.00574
Haiku 4.5 $0.00015 $0.00287

Measured 10d ago against content hash a9d1d2aa1708, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade B, and why

release-okama-mcp 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 10d 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.

- **Deploy to secondvds** (dir owned by okama_mcp; passwordless sudo is set up;

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 && echo "LANDING == REPO"
.agents/skills/release-okama-mcp/SKILL.md · 237 lines

How it starts

The opening of the file, as written. The whole thing — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Releasing okama-mcp

Publishing is tag-driven: pushing a v* tag triggers two GitHub Actions workflows — release.yml (build + publish to PyPI via Trusted Publishing) and publish-mcp-registry.yml (wait for PyPI → GitHub OIDC → mcp-publisher publish to registry.modelcontextprotocol.io). Your job is the steps around that automation. Do them in order.

Guardrails (read first)

  • PyPI versions are immutable. A version can never be re-uploaded or reused. Never push a vX.Y.Z tag until every pre-flight check below is green. If a release fails after PyPI has accepted the upload, do not retry the same version — bump to the next patch and start over.
  • Three versions must match exactly: the tag (X.Y.Z), pyproject.toml [tool.poetry] version, server.json top-level version, and server.json packages[0].version. Both workflows hard-fail otherwise.
  • The tag push is the irreversible, outward step. Treat it like a deploy: get the user's go-ahead before pushing the tag.
  • Never commit poetry.lock (it is gitignored).

1. Pre-flight

git checkout main && git pull --ff-only
git status --short          # must be clean
git tag --sort=-v:refname | head -3   # see the latest released version

Pick the new version with semver, judged against changes since the last tag:

  • patch (x.y.Z) — bugfixes / docs only, no API change.
  • minor (x.Y.0) — new tools or new optional params, backward compatible.
  • major (X.0.0) — a breaking change to a tool/spec contract.

New okama tools or new optional parameters are minor.

Run the quality gates — all must be clean:

poetry run pytest -q
poetry run ruff check .
poetry run pytest -m integration   # optional but recommended: hits api.okama.io

2. Bump the version (three places, identical value)

Set NEW=X.Y.Z, then edit to that value:

  • pyproject.tomlversion = "X.Y.Z"
  • server.json → top-level "version": "X.Y.Z"
  • server.jsonpackages[0].version "version": "X.Y.Z"

Read the full file on GitHub · 237 lines

Changes

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.

  1. 10d ago First seen · 237 lines · 149 tokens per session scan B a9d1d2aa1708

Subscribe to this mod's changes

release-okama-mcp is a skill published in the GitHub repository mbk-dev/okama-mcp (4 stars, last pushed 9d ago), licensed MIT. It adds 149 tokens to every session and 2,872 once invoked, about $0.0007 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.