junjo: Skill for Claude Code

.agents/skills/junjo-release-descriptions/SKILL.md

junjo-release-descriptions is a skill for Claude Code, Codex from mdrideout/junjo. It costs 70 tokens per session (1,249 once invoked), scanned A, original, Apache-2.0.

A skill for writing and reviewing GitHub release descriptions for the Junjo Python SDK and Junjo AI Studio. A release description explains what shipped, what changed for users, and where technical readers can verify it.

In plain words
What is it for?
Use it to draft, review, or publish descriptions for independently versioned Junjo releases without changing tags, assets, or other release settings.
Why use it?
It helps turn incomplete or overly technical release notes into accurate explanations for both nontechnical and technical readers. It also limits changes to the requested release description.

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 mdrideout/junjo's own configuration. It tells Claude Code and Codex how to work on junjo 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 junjo configures →

Reuse

Borrowing it

Nothing to install: this file belongs to mdrideout/junjo. 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/mdrideout/junjo/master/.agents/skills/junjo-release-descriptions/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/mdrideout/junjo

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 junjo-release-descriptions

README.md
[![agentmods](https://agentmods.dev/badge/skills/mdrideout/junjo/junjo-release-descriptions/github.svg)](https://agentmods.dev/skills/mdrideout/junjo/junjo-release-descriptions)
Your own site
<a href="https://agentmods.dev/skills/mdrideout/junjo/junjo-release-descriptions"><img src="https://agentmods.dev/badge/skills/mdrideout/junjo/junjo-release-descriptions/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 junjo-release-descriptions

Your own site · 80×15
<a href="https://agentmods.dev/skills/mdrideout/junjo/junjo-release-descriptions"><img src="https://agentmods.dev/badge/skills/mdrideout/junjo/junjo-release-descriptions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,249 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 $0.00070 $0.01249
Opus 5.5 $0.00028 $0.00500
Sonnet 5.5 $0.00014 $0.00250
Haiku 4.5 $0.00007 $0.00125

Measured 1mo ago against content hash 29b6f912bcef, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

junjo-release-descriptions 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 1mo 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.

.agents/skills/junjo-release-descriptions/SKILL.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Junjo Release Descriptions

Outcome

Produce an accurate release page that quickly explains what the component is, what people can now accomplish, what changed for existing users, and where technical readers can verify the release. Preserve the release transaction and its provenance evidence.

Scope and authorization

  • Treat the Python SDK and Studio as independently versioned products with namespaced sdk-python-v* and studio-v* tags.
  • When a request refers to the latest Junjo releases, inspect the live release list and normally handle the newest stable release for each named or active component. Do not rewrite older releases unless requested.
  • Drafting and review are read-only. Change a live GitHub description only when the user asked to create, improve, update, or publish it.
  • Edit only the requested release body. Do not create or move tags, create or republish releases, change release state or title, upload or remove assets, or mark a different release as latest unless explicitly requested.
  • Never use gh release create merely to add a description. Publishing an SDK release triggers the PyPI workflow; description work must not initiate a release transaction.

Establish the shipped facts

  1. Read the root AGENTS.md and the scoped owner guidance for any component whose behavior must be interpreted.
  2. Inspect the live release body and metadata with gh release list, gh release view, or the GitHub API. Confirm the exact tag and target commit before writing.
  3. Compare the release tag only with the previous tag in the same namespace. Never let a Studio tag become the SDK comparison base, or vice versa.
  4. Read evidence at the release tag, not only the current worktree:
    • SDK: sdks/python/CHANGELOG.md, its README, shipped guides, examples, and relevant public tests.
    • Studio: the tagged diff, apps/studio/README.md, deployment READMEs, accepted ADRs, user-facing frontend behavior, and relevant tests.
    • Paired versions: tooling/docs/stable-releases.json and the canonical deployment distributions.
    • Product language: the tagged component README and public website source.
  5. Treat post-tag commits as unreleased. Every product claim, compatibility statement, removal, and upgrade warning must be supported by the tagged release.
  6. For Studio, preserve the validated source, workflow, image digests, distribution hashes, mirror revisions, and attached release evidence. The deterministic evidence generated by tooling/scripts/build_studio_release_evidence.py is provenance, not editorial copy.
  7. Verify operational instructions against the actual tagged configuration, Compose mounts, migrations, and deployment behavior. If documentation and implementation disagree, state only the confirmed high-level warning in the release and report the discrepancy separately; do not invent a procedure.

Read the full file on GitHub · 112 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. 1mo ago First seen · 112 lines · 70 tokens per session scan A 29b6f912bcef

Subscribe to this mod's changes

junjo-release-descriptions is a skill published in the GitHub repository mdrideout/junjo (20 stars, last pushed 17d ago), licensed Apache-2.0. It adds 70 tokens to every session and 1,249 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-13.

Related

Other skills, from other repositories

changelog

Turn a range of commits or merged PRs into a changelog entry grouped by change type. Use when the user asks for release notes, a changelog, or "what changed" between two points.

omnigent-ai/omnigent · 44 tokens

otto-drive-pr

PR mergeability, CI, and live preview.

omnigent-ai/omnigent · 14 tokens

changelog

Update per-package CHANGELOG.md files for a Ratel release. Drafts entries with git-cliff (scoped per package), lets you curate, then writes the CHANGELOGs. Handles both RC entries and GA-graduation collapse (merging X.Y.Z-rc. sections into a single X.Y.Z section). Invoke before tagging a release.

ratel-ai/ratel · 74 tokens

jira-release

Assemble a release from a batch of Jira issues — one release branch, pull request, preview and tracking issue per repository — and, when a person says to ship it, merge it and move the cards on. Insert into the prompt of a run started on a batch of issues.

decocms/studio · 60 tokens

ship

Enter the Ship phase of CocoBrew. Reads review.md approval, generates structured commit, creates semantic version tag, optionally creates PR via gh CLI, and records deployment details. Requires approved review.

Snowflake-Labs/cocoplus · 41 tokens

swarm-migrate

Cross-repo migration swarm — one coordinator + N parallel subagents (one per target repo) that apply the same transformation, open PRs, wait for CI, and report back to a shared JSON ledger. Coordinator handles topology, conflict auto-rebase, and stop-on-novel-failure. Use when bumping a shared dependency, rolling out…

yonatangross/orchestkit · 103 tokens