agentmods.dev

Mitsuro: Skill for Claude Code

.github/skills/sampo-changeset/SKILL.md

sampo-changeset is a skill for Claude Code, Codex from honeycomb-Technologies/Mitsuro. It costs 23 tokens per session (413 once invoked), scanned A, original, MIT.

A changeset tool for Sampo, Mitsuro's system for recording product changes, managing semantic version numbers, and preparing release changelogs. Semantic versioning uses major, minor, and patch numbers to describe the scale of a change.

In plain words
What is it for?
Use it when CLI, server, Hive, mobile, or desktop behaviour changes and should appear in a GitHub release. It also supports version bumps and changelog entries for Mitsuro packages.
Why use it?
It records user-visible changes in the right package and release category while avoiding changesets for internal refactors, tests, or documentation-only work.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

This is honeycomb-Technologies/Mitsuro's own configuration. It tells Claude Code and Codex how to work on Mitsuro 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 Mitsuro configures →

not rated 5repo 8d ago A scan 23 tokens original MIT
View source ↗ honeycomb-Technologies/Mitsuro
Reuse

Borrowing it

Nothing to install: this file belongs to honeycomb-Technologies/Mitsuro. 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/honeycomb-Technologies/Mitsuro/main/.github/skills/sampo-changeset/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/honeycomb-Technologies/Mitsuro

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 sampo-changeset

README.md
[![agentmods](https://agentmods.dev/badge/skills/honeycomb-technologies/mitsuro/sampo-changeset.svg)](https://agentmods.dev/skills/honeycomb-technologies/mitsuro/sampo-changeset)
Your own site
<a href="https://agentmods.dev/skills/honeycomb-technologies/mitsuro/sampo-changeset"><img src="https://agentmods.dev/badge/skills/honeycomb-technologies/mitsuro/sampo-changeset.svg" alt="Measured on agentmods" height="20"></a>
Per session 23 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 413 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 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 $0.00023 $0.00413
Opus 5 $0.00012 $0.00206
Sonnet 5 $0.00005 $0.00083
Haiku 4.5 $0.00002 $0.00041

Measured 8d ago against content hash c53b49089995, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

sampo-changeset 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 8d 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.

.github/skills/sampo-changeset/SKILL.md · 39 lines

What it actually says

Mitsuro uses Sampo for changelogs, SemVer, and v{version} tags. Pending changesets live in .sampo/changesets/.

When to add a changeset

Add one for any user-visible product change that should appear in a GitHub Release: CLI, Honey/server, Hive, mobile, or desktop behavior. Skip internal-only refactors, test-only work, and docs that do not change product behavior.

Create a changeset non-interactively

sampo add -p cargo/mitsuro -b patch -t Added -m "Short user-facing description."
  • -b is major, minor, or patch.
  • -t is one of Added, Changed, Deprecated, Removed, Fixed, Security.
  • Repeat -p to target more packages. Use cargo/mitsuro-hive for Hive-only daemon/protocol work. cargo/mitsuro is in a fixed group with the other 0.9.x product crates, so one bump covers CLI, core, server, and desktop.

You can also write .sampo/changesets/<slug>.md directly. See .sampo/changeset.md.example.

Do not

  • Do not retag v0.9.22 or any existing protected tag.
  • Do not cargo publish product crates. They are publish = false.
  • Do not run sampo publish from a laptop unless you intend to create tags. Version (Sampo) tags after the version PR merges; Release binaries then uploads GitHub Release assets. A tag without those assets is not a release. See docs/operations/release.md.
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. 8d ago First seen · 39 lines · 23 tokens per session scan A c53b49089995

Subscribe to this mod's changes

sampo-changeset is a skill published in the GitHub repository honeycomb-Technologies/Mitsuro (5 stars, last pushed 8d ago), licensed MIT. It adds 23 tokens to every session and 413 once invoked, about $0.0001 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.

Git and workflowReleasesacpai-agentcoding-assistantexpoiosmcp
Related

Other skills, from other repositories

update-v8-version

Update Codex's pinned v8 / rustyv8 versions, validate the release-candidate path, and investigate failed V8 canary or artifact builds. Use when asked to bump V8, update rustyv8 artifacts, prepare or validate a V8 release candidate, check v8-canary, or diagnose why a V8 version update no longer builds.

openinterpreter/openinterpreter · 86 tokens

hatch3r-release

Cuts a release with version bump, changelog, tagging, and deploy verification. Use when preparing a release, cutting a version, or deploying to production.

hatch3r/hatch3r · 37 tokens

github

Use the gh CLI for GitHub issues, PR status, CI/logs, comments, reviews, releases, and API queries.

XAIHT/Tlamatini · 28 tokens

hatch3r-cli-gh

GitHub CLI — repos, issues, PRs, releases, gists. Use when drafting GitHub pull requests, issues, releases, gists, or workflow dispatches; invoke gh. Authenticates via the platform's native token mechanism (OAuth / PAT).

hatch3r/hatch3r · 62 tokens

github-release-notes-generator

GitHub webhook recipe for release note generation.

burin-labs/harn · 15 tokens

release-process

Step-by-step release checklist for Squad — prevents v0.8.22-style disasters.

dotnet/maui-labs · 20 tokens