deploy

deploy is a skill for Claude Code from geniro-io/geniro-claude-harness. It costs 32 tokens per session (470 once invoked), scanned A, original, Apache-2.0.

A release workflow for moving a build to a staging or production environment. It creates a release tag, builds the software, runs smoke tests—short checks that the main functions work—and then promotes the result.

In plain words
What is it for?
Use it when shipping a release to staging or production, including preflight checks, artifact creation, smoke testing, promotion, and failed-promotion handoff.
Why use it?
It prevents a release from being promoted when its basic checks have not passed. It also records the build and test state and provides a path for handling a partly completed promotion.

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 shipping a release to staging or production, including preflight checks, artifact creation, smoke testing, promotion, and failed-promotion handoff.

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 deploy

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/geniro-io/geniro-claude-harness/deploy"><img src="https://agentmods.dev/badge/skills/geniro-io/geniro-claude-harness/deploy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 470 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 $0.00032 $0.00470
Opus 5 $0.00016 $0.00235
Sonnet 5 $0.00006 $0.00094
Haiku 4.5 $0.00003 $0.00047

Measured 8d ago against content hash 18d950dcb7b8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

deploy 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.

evals/loop/modules/audit-plugin/benchmarks/dev/plugin-1/tree/skills/deploy/SKILL.md · 45 lines

What it actually says

Deploy — release pipeline

Phases overview

  1. Phase 0 — Preflight. Verify the working tree is clean and the tag does not exist.
  2. Phase 1 — Build. Produce the artifact and record its digest.
  3. Phase 2 — Smoke. Run the smoke suite against the built artifact.
  4. Phase 3 — Promote. Move the artifact into the target environment.

Loop invariants

  1. No promote without a green smoke run. Phase 3 reads Phase 2's result file; a missing result is a failure, never a pass.
  2. State writes go through the helper. Write state.md via atomic_state_write from ${CLAUDE_PLUGIN_ROOT}/lib/atomic-write.sh — a direct write truncates and rewrites, so a reader hitting that window sees a partial file.

PHASE 0 — Preflight

Confirm the tree is clean. Read the rollback contract at ${CLAUDE_PLUGIN_ROOT}/skills/_shared/rollback-contract.md before proceeding — it names what a half-promoted release leaves behind.

PHASE 1 — Build

Build the artifact. Record the digest in the state file.

PHASE 2 — Smoke

Run the smoke suite. Write the result to the state file.

PHASE 3 — Promote

Promote the artifact. When promotion fails midway, hand off to /geniro:promote for the manual completion walk.

REFERENCE

  • ${CLAUDE_PLUGIN_ROOT}/skills/deploy/steps-reference.md — per-phase step detail
  • ${CLAUDE_PLUGIN_ROOT}/skills/deploy/SKILL.md §Phase 4 — the rollback walk, run when a promote is reverted
  • ${CLAUDE_PLUGIN_ROOT}/skills/_shared/state-write.md — state-write helper API
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. 8d ago First seen · 45 lines · 32 tokens per session scan A 18d950dcb7b8

Subscribe to this mod's changes

deploy is a skill published in the GitHub repository geniro-io/geniro-claude-harness (8 stars, last pushed yesterday), licensed Apache-2.0. It adds 32 tokens to every session and 470 once invoked, about $0.0002 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.