tag

tag is a skill for Claude Code from geniro-io/geniro-claude-harness. It costs 51 tokens per session (614 once invoked), scanned A, original, Apache-2.0.

A release workflow for choosing the next version, writing its changelog entry, and pushing an annotated Git tag. A Git tag is a named marker for a specific code version.

In plain words
What is it for?
Use it when preparing a new software release, updating the changelog, and creating the tag that starts the publication process.
Why use it?
It separates release notes, version tagging, and publication, while requiring approval before the tag is pushed.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter; names the AskUserQuestion tool.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the geniro plugin — 37 skills, 8 agents, 1 hook shipped together

Good fit Use it when preparing a new software release, updating the changelog, and creating the tag that starts the publication process.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add geniro-io/geniro-claude-harness
Claude Code
/plugin install geniro

Made for: Claude Code.

Or install geniro, the plugin that ships this one along with the rest of its 37 skills, 8 agents, 1 hook.

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 tag

README.md
[![agentmods](https://agentmods.dev/badge/skills/geniro-io/geniro-claude-harness/tag/github.svg)](https://agentmods.dev/skills/geniro-io/geniro-claude-harness/tag)
Your own site
<a href="https://agentmods.dev/skills/geniro-io/geniro-claude-harness/tag"><img src="https://agentmods.dev/badge/skills/geniro-io/geniro-claude-harness/tag/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 tag

Your own site · 80×15
<a href="https://agentmods.dev/skills/geniro-io/geniro-claude-harness/tag"><img src="https://agentmods.dev/badge/skills/geniro-io/geniro-claude-harness/tag.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 614 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 $0.00051 $0.00614
Opus 5 $0.00026 $0.00307
Sonnet 5 $0.00010 $0.00123
Haiku 4.5 $0.00005 $0.00061

Measured 12d ago against content hash b22c5479330e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

tag 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 12d 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.

evals/loop/modules/audit-plugin/benchmarks/dev/plugin-neg-1/tree/skills/tag/SKILL.md · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tag — cut a release tag

You are the release tagger. You compute the next version, write its changelog entry, and push one annotated tag. You never publish; publishing is the CI job the tag triggers.

Phases overview

  1. Phase 0 — Resolve. Determine the next version from $ARGUMENTS or the changelog.
  2. Phase 1 — Entry. Write the changelog entry for the version.
  3. Phase 2 — Tag. Create and push the annotated tag after the user approves.

Loop invariants

  1. The tag is pushed only after an explicit approval. A pushed tag triggers publication, which no later step can retract — so the approval gate is the last reversible point in the run.
  2. Version resolution reads the changelog, never the tag list. A tag can exist for a version whose changelog entry was reverted; trusting the tag list would then skip a version.

Anti-rationalization

Your reasoning Why it's wrong
"The tag already exists, so the release is done — I'll skip Phase 1." An existing tag proves a tag was pushed, not that its changelog entry survived. Invariant 2: resolve from the changelog.
"The user asked for a release, so pushing the tag is authorized." NEVER push before the Phase 2 gate. Asking for a release authorizes the run, not the one irreversible step inside it — publication starts the moment the tag lands.

Budgets

Budget Value
Changelog entries read when inferring a version 20 — deeper than any real gap between released versions, and bounded so a repo with a decade of history does not stream its whole changelog into context

PHASE 0 — Resolve

Read CHANGELOG.md. Take the version from $ARGUMENTS when given; otherwise increment the most recent released entry.

PHASE 1 — Entry

Write the entry for the resolved version, grouping merged changes by type.

PHASE 2 — Tag

Ask the user to approve the version and entry. On approval, create the annotated tag and push it. See ${CLAUDE_PLUGIN_ROOT}/skills/_shared/git-contract.md §Annotated tags for the exact tag body.

Read the full file on GitHub · 55 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. 12d ago First seen · 55 lines · 51 tokens per session scan A b22c5479330e

Subscribe to this mod's changes

tag is a skill published in the GitHub repository geniro-io/geniro-claude-harness (8 stars, last pushed yesterday), licensed Apache-2.0. It adds 51 tokens to every session and 614 once invoked, about $0.0003 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.