What is release-harn?

A release command for Harn, a software tool, that runs the tag-first release workflow through the project's standard release script. It supports preparing a release and opening a release pull request.

Use it to prepare release content, commit and push it, push a signed version tag, open a release pull request, and turn on automatic merging.

It keeps releases inside the approved workflow, including the required environment checks. The process ties publishing to a specific version tag and release commit.

How burin-labs/harn configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to burin-labs/harn. 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/burin-labs/harn/main/.claude/commands/release-harn.md

Clone the repo

git clone --depth 1 https://github.com/burin-labs/harn

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/burin-labs/harn/release-harn.svg)](https://agentmods.dev/commands/burin-labs/harn/release-harn)

Your own site

<a href="https://agentmods.dev/commands/burin-labs/harn/release-harn"><img src="https://agentmods.dev/badge/commands/burin-labs/harn/release-harn.svg" alt="Measured on agentmods" height="20"></a>

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 342 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.

Model	Per session	Once invoked
Fable 5.1	$0.00000	$0.00342
Opus 5	$0.00000	$0.00171
Sonnet 5	$0.00000	$0.00068
Haiku 4.5	$0.00000	$0.00034

Measured 6d ago against content hash e669473cc4fa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

release-harn 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 6d 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.

.claude/commands/release-harn.md · 32 lines

What it actually says

Run the tag-first Harn release workflow.

The canonical playbook is .codex/skills/harn-release/SKILL.md; use it with the repo scripts as the source of truth.

Default live command:

cd ~/projects/harn-bump-fleet
scripts/run_harn_release.sh \
  --repo ~/projects/harn --mode ship-pr --agent --yes-live-release

scripts/run_harn_release.sh is the canonical release boundary. Call it rather than invoking release_harn.harn through harn run directly: on macOS it intercepts a live prepare or ship-pr and dispatches the canonical hosted Linux workflow, because the release audit exercises nested OS sandboxes that Seatbelt refuses to apply under Harn's default-deny outer profile. The harness does not perform that handoff itself, so calling it directly on macOS starts a local release the gate cannot certify.

ship-pr prepares the release content, commits it, pushes the branch, pushes the signed vX.Y.Z tag at the pinned release commit, opens the Release vX.Y.Z PR, and enables auto-merge. The tag is pushed before the PR merges so publishing is tied to the pinned tag commit.

Do not run scripts/release_ship.sh --prepare directly for normal releases. It is an implementation detail of release_harn.harn and refuses standalone use. Use scripts/release_ship.sh --finalize, scripts/release_ship.sh --bump, and the release workflows only for recovery after reading their help text.

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.

6d ago First seen · 32 lines · 0 tokens per session scan A e669473cc4fa

Subscribe to this mod's changes

release-harn is a command published in the GitHub repository burin-labs/harn (20 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 342 tokens. 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 Releases acp agents ai-agents language mcp-client programming-language

harn: Command for Claude Code

Borrowing it

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other commands, from other repositories

release-checklist

changelog

land-and-deploy

hatch3r-release

release-notes

ship