yet-another-agentic-chat: Skill for Claude Code

.claude/skills/releasing/SKILL.md

releasing is a skill for Claude Code from amyodov/yet-another-agentic-chat. It costs 0 tokens per session (1,500 once invoked), scanned A, original, MIT.

A release checklist for YAAC, a messaging tool for concurrent AI coding sessions. It covers preparing a version and publishing it to the project's package, code-hosting, and directory indexes.

In plain words
What is it for?
Use it when the user explicitly asks to release a YAAC version, including updating files, creating a tag, publishing a release, and updating indexes.
Why use it?
It prevents incomplete releases by checking the repository, tests, version, and publishing steps in a defined order.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: mentions CLAUDE.md; positional $N argument.

This is amyodov/yet-another-agentic-chat's own configuration. It tells Claude Code how to work on yet-another-agentic-chat 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 yet-another-agentic-chat configures →

Reuse

Borrowing it

Nothing to install: this file belongs to amyodov/yet-another-agentic-chat. 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/amyodov/yet-another-agentic-chat/main/.claude/skills/releasing/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/amyodov/yet-another-agentic-chat

Made for: Claude Code.

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 releasing

README.md
[![agentmods](https://agentmods.dev/badge/skills/amyodov/yet-another-agentic-chat/releasing/github.svg)](https://agentmods.dev/skills/amyodov/yet-another-agentic-chat/releasing)
Your own site
<a href="https://agentmods.dev/skills/amyodov/yet-another-agentic-chat/releasing"><img src="https://agentmods.dev/badge/skills/amyodov/yet-another-agentic-chat/releasing/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 releasing

Your own site · 80×15
<a href="https://agentmods.dev/skills/amyodov/yet-another-agentic-chat/releasing"><img src="https://agentmods.dev/badge/skills/amyodov/yet-another-agentic-chat/releasing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,500 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00000 $0.01500
Opus 5 $0.00000 $0.00750
Sonnet 5 $0.00000 $0.00300
Haiku 4.5 $0.00000 $0.00150

Measured 9d ago against content hash 864c3060a300, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

releasing scanned grade A with 1 finding 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 9d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/generate_manifests.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- Confirm PyPI serves the new version: `curl -s https://pypi.org/pypi/yet-another-agentic-chat/json` →
.claude/skills/releasing/SKILL.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Release a version of YAAC

One release reaches PyPI, the git tag and GitHub release, the official MCP registry, and Context7. Releases only happen when the user asks for one — disable-model-invocation enforces that, and nothing in this file overrides it. The version being released is $1 (e.g. 0.1.1): a bare semver, no leading v — the tag adds it.

The publish pipeline is: GitHub release → .github/workflows/publish.yml → PyPI trusted publisher (OIDC, no tokens). This skill's job is everything around that trigger, in order, aborting loudly at the first failure rather than improvising past it.

1. Preconditions

  • Working tree clean, on main, in sync with origin/main (git status -sb). Unpushed work either goes into the release consciously or waits — it must not ride along by accident.
  • $1 is not already released: absent from git tag and from https://pypi.org/pypi/yet-another-agentic-chat/json.
  • The full local suite passes: uv run pytest.
  • CI is green on HEAD for all three OSes: gh run list --branch main --limit 1. Local tests cannot vouch for Windows; only the matrix can.

2. Version bump

Set version = "$1" in pyproject.toml, run uv sync so uv.lock follows, then regenerate the plugin manifests, which carry the version too:

uv run python ${CLAUDE_SKILL_DIR}/scripts/generate_manifests.py

Commit all of it together. The version in the code and the version being tagged must be the same string — a wheel that reports a different version than its tag is a support puzzle nobody needs.

3. Tag and release

Push the bump first, then wait for its own CI run to go green before tagging. The green checked in step 1 was for the commit before the bump; pushing starts a fresh run, and the commit being released is the one nobody has verified yet. A red Windows job has hidden here before.

git push origin main
until [ "$(gh run list --branch main --limit 1 --json status --jq '.[0].status')" = completed ]; do sleep 20; done
gh run list --branch main --limit 1 --json headSha,conclusion --jq '.[0] | "\(.headSha[0:7]) \(.conclusion)"'

Read the full file on GitHub · 114 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 9d ago First seen · 114 lines · 0 tokens per session scan A 864c3060a300

Subscribe to this mod's changes

releasing is a skill published in the GitHub repository amyodov/yet-another-agentic-chat (4 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,500 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.