A release workflow for one plug-in in a repository. It increases the version, records what changed, commits the release, and pushes it.

Use it to release a named plug-in, or to choose which plug-in to release when no name is supplied.

It keeps the version, changelog, and published Git history aligned. The changelog also gives the upgrade process information about what changed.

release — Skill by gtapps

Install

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.

agentmods

npx agentmods add skills/gtapps/claude-code-hermit/release

Any agent

npx skills add gtapps/claude-code-hermit --skill release

Clone the repo

git clone --depth 1 https://github.com/gtapps/claude-code-hermit

Made for: Claude Code, Codex.

Per session 104 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 4,110 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5	$0.00104	$0.04110
Opus 5	$0.00052	$0.02055
Sonnet 5	$0.00021	$0.00822
Haiku 4.5	$0.00010	$0.00411

Measured 2d ago against content hash 6285a77b31be, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

release 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 2d 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/release/SKILL.md · 254 lines

How it starts

The opening of the file, as written. The whole thing — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Release

Bump version, write changelog, commit, and push for a single plugin in the monorepo. The changelog entry is critical because the upgrade skill (skills/hermit-evolve/SKILL.md) reads it to know what to tell hermits during /claude-code-hermit:hermit-evolve.

Usage

/release <plugin-slug> — release the plugin at plugins/<plugin-slug>/.

Examples:

/release claude-code-hermit — release the core plugin
/release claude-code-dev-hermit — release the dev hermit
/release claude-code-homeassistant-hermit — release the HA hermit
/release laravel-forge-hermit — release the Laravel Forge hermit

If invoked without a slug, list all plugins/<name>/ directories that contain .claude-plugin/plugin.json and ask the operator which one via AskUserQuestion before proceeding.

Steps

0. Identify target plugin

Resolve the plugin slug:

If the user passed <slug> as argument, use that.
Otherwise, glob plugins/*/.claude-plugin/plugin.json, collect the directory names, and ask via AskUserQuestion: "Which plugin to release?" with one option per slug.

Validate plugins/<slug>/.claude-plugin/plugin.json exists. If it does not, abort: Plugin 'plugins/<slug>/' not found. Suggest the available slugs.

Throughout the rest of this skill, $PLUGIN_DIR refers to plugins/<slug>/.

1. Pre-release validation

Run before anything else. Abort the release if any step fails.

Run the native plugin validator (CLI form):
```
claude plugin validate plugins/<slug> 2>&1
```
Abort on any error other than Unrecognized keys — that one means an incomplete hermit-meta.json migration; fix the migration elsewhere, then resume. Background on the migration lives in each plugin's CONTRIBUTING.md.
Run test suites for the target plugin. Detect the convention and dispatch:
- If plugins/<slug>/tests/run-all.sh exists (bash entrypoint, used by dev/fitness/scribe/forge):
```
bash plugins/<slug>/tests/run-all.sh 2>&1
```
- Else if any plugins/<slug>/tests/*.test.ts exists (bun entrypoint, used by core/HA):
```
cd plugins/<slug> && bun test 2>&1
```
- Else if a plugins/<slug>/tests/ dir exists but neither marker matched: abort the release with Plugin '<slug>' has a tests/ dir but no recognized convention (run-all.sh or *.test.ts) — fix the dispatch before releasing. Do not silently skip.
- Else (no tests/ dir at all): skip this step and note it in the release report.

Read the full file on GitHub · 254 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.

2d ago First seen · 254 lines · 104 tokens per session scan A 6285a77b31be

Subscribe to this mod's changes

release is a skill published in the GitHub repository gtapps/claude-code-hermit (73 stars, last pushed today), licensed MIT. It adds 104 tokens to every session and 4,110 once invoked, about $0.0005 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 2026-08-30.

Git and workflow ai ai-agent anthropic claude claude-code claude-code-plugin

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

agent-host-chat-contributions

Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.

microsoft/vscode · 56 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens