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.
npx agentmods add commands/adham90/ruby_llm-agents/releasegit clone --depth 1 https://github.com/adham90/ruby_llm-agentsWhat 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 | $0.00017 | $0.02113 |
| Opus 5 | $0.00009 | $0.01056 |
| Sonnet 5 | $0.00003 | $0.00423 |
| Haiku 4.5 | $0.00002 | $0.00211 |
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.
How it starts
The opening of the file, as written. The whole thing — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ruby LLM Agents Release Command
You are automating a gem release for ruby_llm-agents. The user has provided: $ARGUMENTS
Step 1: Prerequisites Check
Verify required tools are available:
which gem && which gh && which bundle
If any are missing, inform the user what needs to be installed and stop.
Step 2: Pre-flight Checks
Run these checks and stop if any fail:
# Check we're on main branch
git branch --show-current
# Check git status is clean
git status --porcelain
# Pull latest changes
git pull --ff-only origin main
- If not on
mainbranch, warn the user and ask if they want to continue. - If there are uncommitted changes, stop and ask the user to commit or stash them.
- If pull fails, warn and ask if they want to continue.
Step 3: Read Current Version
Read the current version from lib/ruby_llm/agents/core/version.rb. Parse the VERSION = "X.Y.Z" string to extract major, minor, and patch numbers.
Step 4: Determine Version Bump Type
If the user provided an explicit bump type (patch, minor, or major) as $ARGUMENTS, use that.
Otherwise, automatically detect the bump type by analyzing changes since the last git tag:
4a: Gather Change Data
Run these commands to collect change information:
# Get the last tag
git describe --tags --abbrev=0
# Commits since last tag
git log $(git describe --tags --abbrev=0)..HEAD --oneline
# Files changed since last tag
git diff --name-only $(git describe --tags --abbrev=0)..HEAD
# Full diff stat
git diff --stat $(git describe --tags --abbrev=0)..HEAD
Also read CHANGELOG.md and look for any unreleased section at the top (a version entry that matches the next version or has no tag yet).
4b: Apply Semver Rules
Analyze ALL of the following signals to determine the bump type:
MAJOR (X+1.0.0) — if ANY of these are true:
- CHANGELOG has a
### Breaking Changessection in the unreleased entry - Commit messages contain
BREAKING CHANGE,BREAKING:, or use conventional commit!:suffix (e.g.,feat!:,fix!:) - Commit messages mention "remove", "drop support", "rename" for public APIs
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.
- 2d ago First seen · 239 lines · 0 tokens per session scan A 7790b5c72e3f
release is a command published in the GitHub repository adham90/ruby_llm-agents (136 stars, last pushed 1mo ago), licensed MIT. It adds 17 tokens to every session and 2,113 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.
Other commands, from other repositories
diagnose
Diagnose dev environment — checks Cargo build, clippy, deps, binary. Auto-suggest on Rust/Cargo errors.
diagram
Generate ASCII diagrams explaining architecture or decisions from the current session.
refine-requirements
リリース要件の壁打ち。対話で要件を固め、config の requirementsPath が指す requirements.md に確定要件を書き出し、automation.pipeline に従って run-release を起動する.
run-release
リリース自動パイプライン(run-release)の起動。workflow.config.json を読込・スキーマ検証したうえで scriptPath 指定で起動し、完了・停止時の戻り値をユーザーに報告する.
logical-commits
Command "logical-commits" from sumihiro3/Monomi, covering logical commits command, 処理の流れ, コミットの分類基準, 機能追加 (feat:) and リファクタリング (refactor:).
session-end
Cleanup and persist session state before ending work.