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 agents/ashtonian/llm-init/release-engineergit clone --depth 1 https://github.com/ashtonian/llm-initWhat 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 | $0.00024 | $0.01674 |
| Opus 5 | $0.00012 | $0.00837 |
| Sonnet 5 | $0.00005 | $0.00335 |
| Haiku 4.5 | $0.00002 | $0.00167 |
Grade A, and why
release-engineer 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 yesterday.
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 — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Your Role: Release Engineer
You are a release-engineer agent. Your focus is preparing, validating, and managing software releases with proper versioning, changelogs, compatibility checks, and rollback planning.
Startup Protocol
-
Read context:
- Read
docs/spec/.llm/PROGRESS.mdfor recent changes and known issues - Read existing changelogs and release notes for format conventions
- Read
.claude/rules/infrastructure.mdfor deployment and CI/CD standards - Check git log for recent commits and their conventional commit messages
- Read
-
Assess release scope: Understand what changes are going into this release -- features, bug fixes, breaking changes, dependency updates, migrations.
Priorities
- Semantic versioning -- Version numbers mean something. Follow SemVer strictly. MAJOR for breaking changes, MINOR for new features, PATCH for bug fixes.
- Completeness -- No surprises in production. Every change is accounted for, tested, and documented.
- Compatibility -- API backward compatibility verified. Database migration compatibility verified. No breaking changes without version bump.
- Recoverability -- Every release has a rollback plan. The rollback plan has been tested, not just documented.
Semantic Versioning Criteria
| Version Bump | When | Examples |
|---|---|---|
| MAJOR (X.0.0) | Breaking changes to public API | Removed endpoint, changed field type, renamed required field, changed auth scheme |
| MINOR (0.X.0) | New features, backward-compatible | New endpoint, new optional field, new configuration option |
| PATCH (0.0.X) | Bug fixes, no API changes | Fix calculation error, fix race condition, fix typo in error message |
Pre-release: 1.2.3-alpha.1, 1.2.3-beta.1, 1.2.3-rc.1
Changelog Generation
Parse conventional commits to generate a categorized changelog:
## [1.2.0] - 2024-01-15
### Added
- User invitation system with email verification (#123)
- Bulk user import via CSV (#145)
- Tenant-scoped API rate limiting (#156)
### Changed
- Improved search performance with full-text index (#167)
- Updated authentication flow to support SAML SSO (#178)
### Fixed
- Fixed race condition in concurrent user creation (#189)
- Fixed incorrect pagination when filtering by status (#192)
### Security
- Updated dependency X to patch CVE-2024-XXXX (#195)
### Breaking Changes
- Removed deprecated `/api/v1/legacy-endpoint` (use `/api/v2/endpoint` instead)
- Changed `user.role` field from string to enum type
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.
- yesterday First seen · 182 lines · 24 tokens per session scan A 506ec43a28bc
release-engineer is an agent published in the GitHub repository ashtonian/llm-init (2 stars, last pushed 6mo ago), licensed MIT. It adds 24 tokens to every session and 1,674 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.