release

release is a command for Claude Code from jhlee111/ash_grant. It costs 0 tokens per session (871 once invoked), scanned A, original, MIT.

End-to-end release workflow: analyze changes, update docs + version, verify, PR, merge, tag. Run this on main after feature PRs are merged.

Command for Claude Code

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 commands/jhlee111/ash_grant/release
Clone the repo
git clone --depth 1 https://github.com/jhlee111/ash_grant

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.

agentmods badge for release

README.md
[![agentmods](https://agentmods.dev/badge/commands/jhlee111/ash_grant/release.svg)](https://agentmods.dev/commands/jhlee111/ash_grant/release)
Your own site
<a href="https://agentmods.dev/commands/jhlee111/ash_grant/release"><img src="https://agentmods.dev/badge/commands/jhlee111/ash_grant/release.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 871 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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00871
Opus 5 $0.00000 $0.00436
Sonnet 5 $0.00000 $0.00174
Haiku 4.5 $0.00000 $0.00087

Measured 2d ago against content hash 4ad0701653d8, 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.

.claude/commands/release.md · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Release

End-to-end release workflow: analyze changes, update docs + version, verify, PR, merge, tag. Run this on main after feature PRs are merged.

Input

$ARGUMENTS — version number (e.g., 0.11.0) or semver bump type (major, minor, patch). If omitted, suggest version based on changes since last tag.

Steps

1. Pre-checks

git checkout main && git pull

Verify clean working tree (no uncommitted changes except PLAN.md, docs/).

2. Analyze changes since last release

# Find last version tag
git describe --tags --abbrev=0

# All commits since last tag
git log --oneline <last-tag>..HEAD

# All changed files since last tag
git diff --stat <last-tag>..HEAD

Categorize:

  • Features (feat:)
  • Fixes (fix:)
  • Docs (docs:)
  • Refactors (refactor:)
  • Tests (test:)

Determine version bump if not specified:

  • Breaking change → major
  • New feature → minor
  • Bug fix / docs only → patch

3. Documentation gate

Check ALL of these before creating release branch:

CHANGELOG.md:

  • Add new version section with date
  • List all changes categorized by Added/Changed/Fixed/Removed
  • Move from commit messages, but write user-facing descriptions (not just commit text)

README.md:

  • Installation version matches new release?
  • Any new features from this release missing from README?
  • Examples still accurate with current API?
  • Feature list at top of README reflects new capabilities?

@moduledoc:

  • New public modules have @moduledoc?
  • Changed modules have accurate @moduledoc?

CLAUDE.md:

  • Architecture section reflects new modules?
  • Any new commands, patterns, or test structures?

usage-rules.md:

  • AI-agent-facing rulebook — audit as seriously as README.
  • New DSL options / entities / recommended patterns since last release are surfaced as "DO:" rules?
  • Deprecated or removed options are surfaced as "DON'T:" rules?
  • Examples still reflect current API (e.g., post-deprecation they no longer demonstrate the deprecated path)?

Read the full file on GitHub · 143 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. 2d ago First seen · 143 lines · 0 tokens per session scan A 4ad0701653d8

Subscribe to this mod's changes

release is a command published in the GitHub repository jhlee111/ash_grant (17 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 871 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 2026-09-01.