harn: Skill for Codex

.codex/skills/harn-release/SKILL.md

harn-release is a skill for Codex from burin-labs/harn. It costs 22 tokens per session (2,061 once invoked), scanned A, original, Apache-2.0.

A release-preparation runbook for Harn, covering version changes, publishing, tags, and release notes. A tag is a named marker for a specific code version.

In plain words
What is it for?
Use it to prepare or ship Harn releases, select release modes and version bumps, publish tags, create or verify release pull requests, and recover from release problems.
Why use it?
It sets out the required release flow and checks, including the correct launcher, exact source revision, expected pull requests, and platform-specific handling.

Skill for Codex

Written for Codex: installed under .codex/. Also seen: mentions CLAUDE.md; mentions AGENTS.md.

This is burin-labs/harn's own configuration. It tells Codex how to work on harn 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 harn configures →

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/.codex/skills/harn-release/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/burin-labs/harn

Made for: Codex.

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 harn-release

README.md
[![agentmods](https://agentmods.dev/badge/skills/burin-labs/harn/harn-release/github.svg)](https://agentmods.dev/skills/burin-labs/harn/harn-release)
Your own site
<a href="https://agentmods.dev/skills/burin-labs/harn/harn-release"><img src="https://agentmods.dev/badge/skills/burin-labs/harn/harn-release/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 harn-release

Your own site · 80×15
<a href="https://agentmods.dev/skills/burin-labs/harn/harn-release"><img src="https://agentmods.dev/badge/skills/burin-labs/harn/harn-release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,061 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00022 $0.02061
Opus 5 $0.00011 $0.01030
Sonnet 5 $0.00004 $0.00412
Haiku 4.5 $0.00002 $0.00206

Measured 9d ago against content hash 85b7e7bed185, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

harn-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 9d 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.

.codex/skills/harn-release/SKILL.md · 182 lines

How it starts

The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Harn release

Use the tag-first release flow. ~/projects/harn-bump-fleet/release_harn.harn owns the orchestration and scripts/run_harn_release.sh is the canonical boundary that invokes it; local scripts in this repo are building blocks and recovery tools.

cd ~/projects/harn-bump-fleet
scripts/run_harn_release.sh \
  --repo ~/projects/harn \
  --mode ship-pr \
  --at-sha <exact-origin-main-sha> \
  --expect-pr <required-pr-number> \
  --agent \
  --yes-live-release

Call the launcher rather than harn run release_harn.harn directly. On macOS the launcher routes a live prepare or ship-pr to the canonical hosted Linux workflow: the release audit exercises nested OS sandboxes, and Seatbelt refuses a second sandbox-exec profile under Harn's default-deny outer profile. The harness does not self-dispatch, so a direct call on macOS starts a local release the gate cannot certify.

The hosted path accepts a closed input tuple — mode, bump, prerelease_identifier, at_sha, converge_fleet, expected_prs. Flags outside it, --reject-pr and --focus among them, fail before dispatch rather than being silently dropped. Express an exclusion with --at-sha and prove it with git merge-base --is-ancestor.

ship-pr does the following:

  • Prepares the release content and commits it.
  • Pushes the branch, and pushes the signed vX.Y.Z tag at the pinned release commit.
  • Opens the Release vX.Y.Z PR and enables auto-merge.
  • Writes a durable post-tag watch receipt.

The tag is pushed before the PR merges. That way crates.io, release notes, binaries, and the container are all built from the pinned tag commit, not from whatever is on main later.

Flow

release_harn.harn --mode ship-pr
  -> prepare release content and version bump
  -> commit "Release vX.Y.Z"
  -> push branch
  -> push signed vX.Y.Z tag at the pinned commit
  -> open Release vX.Y.Z PR and enable auto-merge
  -> tag push triggers publish-release and build-release-binaries
  -> watch_harn_release.harn resumes the durable receipt to terminal health

Read the full file on GitHub · 182 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. 9d ago First seen · 182 lines · 22 tokens per session scan A 85b7e7bed185

Subscribe to this mod's changes

harn-release is a skill published in the GitHub repository burin-labs/harn (21 stars, last pushed today), licensed Apache-2.0. It adds 22 tokens to every session and 2,061 once invoked, about $0.0001 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.

Related

Other skills, from other repositories

managing-archestra-releases

Runs rolling beta releases, stable patches, and complete stable-line cutovers. Use when backporting fixes, cutting or retiring release branches, configuring release protections, testing artifacts, recovering failed runs, or approving releases.

archestra-ai/archestra · 51 tokens

agent-framework-py-release

Use when cutting a Python release for the microsoft/agent-framework monorepo. Triggers on "bump py versions", "cut a python release", "prepare release PR for python", "release py packages", "bump python to X.Y.Z", or similar requests to bump Python package versions and prepare a release PR. Handles all four lifecycle…

microsoft/agent-framework · 103 tokens

release-notes

Draft short release notes from a list of changes. Use when the user asks for changelogs, release notes, or a concise product update.

cloudflare/agents · 33 tokens

changelog

Turn a range of commits or merged PRs into a changelog entry grouped by change type. Use when the user asks for release notes, a changelog, or "what changed" between two points.

omnigent-ai/omnigent · 44 tokens

github

Drive GitHub via the official gh CLI — repos, issues, pull requests, releases, gists, Actions runs, and raw REST through gh api. Use when the user asks to inspect or manage GitHub.

AtomicBot-ai/atomic-agent · 48 tokens

release-notes

Create release notes for a new version tag. Gathers all commits, PRs, issues fixed, and breaking changes since a previous release. Creates the release notes markdown file, tags the repo, and pushes. Asks the user to confirm the base version to diff against.

agentic-community/mcp-gateway-registry · 59 tokens