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/newbpydev/mcp-diagnostics-extension/release-workflowgit clone --depth 1 https://github.com/newbpydev/mcp-diagnostics-extensionWrote 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.
[](https://agentmods.dev/instructions/newbpydev/mcp-diagnostics-extension/release-workflow)<a href="https://agentmods.dev/instructions/newbpydev/mcp-diagnostics-extension/release-workflow"><img src="https://agentmods.dev/badge/instructions/newbpydev/mcp-diagnostics-extension/release-workflow.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.01533 | $0.01533 |
| Opus 5 | $0.00766 | $0.00766 |
| Sonnet 5 | $0.00307 | $0.00307 |
| Haiku 4.5 | $0.00153 | $0.00153 |
Grade A, and why
mcp-diagnostics-extension release-workflow.instructions.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 5d 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 — 240 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Complete Release Management Workflow
This rule defines the comprehensive end-to-end release management workflow that must be followed for all software releases, based on industry best practices from LaunchDarkly and Zeet.
🎯 Overview
Every software release must follow this systematic checklist to minimize downtime risks, ensure quality, and maintain professional standards. This workflow combines traditional best practices with modern feature management approaches.
📋 Complete Release Management Checklist
Phase 1: Pre-Release Quality Assurance
1.1 Test Suite Validation
# Run comprehensive test suite
npm run test:ci
# Verify all tests pass (target: 100% pass rate)
# Check test coverage (target: >90%)
# Ensure no failing or skipped tests
1.2 Code Quality Checks
# Run linting
npm run lint
# Check code formatting
npm run format:check
# Verify TypeScript compilation
npm run compile
1.3 Build Verification
# Clean build
npm run clean
npm run compile:prod
# Package extension
npm run package
# Verify package contents and size
Phase 2: Version Management & Documentation
2.1 Semantic Versioning
# Choose appropriate version bump:
npm run release:patch # Bug fixes (1.0.0 → 1.0.1)
npm run release:minor # New features (1.0.0 → 1.1.0)
npm run release:major # Breaking changes (1.0.0 → 2.0.0)
# For pre-releases:
npm run release:alpha # Alpha releases
npm run release:beta # Beta releases
2.2 Changelog Generation
- Automatic:
standard-versiongenerates changelog from conventional commits - Manual Review: Verify changelog accuracy and completeness
- Enhancement: Add detailed descriptions for major features/fixes
2.3 Documentation Updates
- README.md: Update features, installation, usage instructions
- API Documentation: Update MCP tools, resources, configuration
- Troubleshooting: Add new known issues and solutions
- Migration Guides: For breaking 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.
- 5d ago First seen · 240 lines · 1,533 tokens per session scan A f93fca31bb77
mcp-diagnostics-extension release-workflow.instructions.md is an instructions file published in the GitHub repository newbpydev/mcp-diagnostics-extension (22 stars, last pushed 10mo ago), licensed MIT. It adds 1,533 tokens to every session, about $0.0077 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
stealth-browser-mcp AGENTS.md
Instructions for vibheksoni/stealth-browser-mcp, covering agent instructions, start here, recommended proxy services, environment and validation.
mcpls changelog.instructions.md
Instructions for bug-ops/mcpls: Breaking changes to public APIs must appear under ### Changed with an explicit "Breaking change:" prefix. A ### Fixed entry alone is not sufficient — downstream users scanning the changelog for breakage will miss it.
PawFlow-Agents AGENTS.md
AGENTS.md instructions for allcolor/PawFlow-Agents, covering agent instructions and releases.
kana-code-plugins CLAUDE.md
Instructions for Linaqruf/kana-code-plugins, covering kana-code-plugins — maintainer instructions, hard rules, workflow, versioning (semver — majors are not rewrite counters) and per-plugin notes.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.