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 instructions/raulgomis/semversioner/agents-mdgit clone --depth 1 https://github.com/raulgomis/semversionerWhat 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 | $0.01250 | $0.01250 |
| Opus 5 | $0.00625 | $0.00625 |
| Sonnet 5 | $0.00250 | $0.00250 |
| Haiku 4.5 | $0.00125 | $0.00125 |
Grade A, and why
semversioner AGENTS.md 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Semversioner - AI Agent Guidelines
This document provides a comprehensive overview of the semversioner project to help AI agents (and human developers) understand the architecture, coding standards, and development workflows when contributing to the codebase.
1. Project Overview
semversioner is a Python CLI tool designed to simplify semantic versioning and changelog generation. It automates the semver release process for projects, utilizing a specific directory structure (.semversioner/) to track changes over time and aggregate them into single versioned releases.
The tool uses a workflow where individual "changesets" are created during development (e.g., patch, minor, major) and stored as JSON files. During a release, these changesets are merged into a single release JSON file, and a changelog can be generated from these release records using Jinja2 templates.
2. Tech Stack & Dependencies
- Language: Python >= 3.10
- CLI Framework:
click - Templating:
jinja2(for changelog generation) - Versioning parsing:
packaging - Build System:
setuptools(pyproject.tomlbased) - Linting & Formatting:
ruff - Testing:
pytest,pytest-cov
3. Architecture & Core Components
The codebase is structured to separate concerns between the CLI interface, the business logic, storage, and data models:
semversioner/cli.py: The entry point for the CLI commands (e.g.,add-change,release,changelog,status,next-version,current-version,check). It parses user inputs usingclickand delegates execution to the core layer.semversioner/core.py: The main business logic layer containing theSemversionerorchestrator class. It coordinates actions between the CLI and the storage layer, handles version incrementing logic, and formats the changelog using Jinja2 templates.semversioner/models.py: Data representations using Pythondataclasses(e.g.,Changeset,Release,ReleaseStatus).semversioner/storage.py: Handles file system interactions. Uses an abstractSemversionerStorageclass with a concreteSemversionerFileSystemStorageimplementation. It creates JSON changesets in the.semversioner/next-release/directory and aggregates them into versioned JSON files in.semversioner/.
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 · 65 lines · 1,250 tokens per session scan A 2488d8f50682
semversioner AGENTS.md is an instructions file published in the GitHub repository raulgomis/semversioner (48 stars, last pushed 1mo ago), licensed MIT. It adds 1,250 tokens to every session, about $0.0063 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 instructions, from other repositories
zvm CLAUDE.md
Instructions for tristanisham/zvm, covering claude.md, project overview, build & test commands, architecture and packaging & generated files.
zvm AGENTS.md
Instructions for tristanisham/zvm, covering repository guidelines, project structure & module organization, build, test, and development commands, coding style & naming conventions and testing guidelines.
flutter_enterprise_starter_kit CLAUDE.md
Instructions for nicolinx/flutter_enterprise_starter_kit, covering claude.md, start here, commands and non-negotiables.
testkube AGENTS.md
AGENTS.md instructions for kubeshop/testkube, covering working with testkube core (testkube), deprecated components — do not reference, purpose, entry points and mcp integration.
sfdx-hardis CLAUDE.md
Claude Code instructions for hardisgroupcom/sfdx-hardis, covering sfdx-hardis, quick reference, contribution workflow, monitoring and grafana skills and behavior preferences.
eIsland AGENTS.md
AGENTS.md instructions for JNTMTMTM/eIsland, covering codegraph, 1. think before coding, 2. simplicity first, 3. surgical changes and 4. goal-driven execution.