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/burly-mingo/modernization-kit/claude-mdgit clone --depth 1 https://github.com/Burly-Mingo/modernization-kitWrote 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/burly-mingo/modernization-kit/claude-md)<a href="https://agentmods.dev/instructions/burly-mingo/modernization-kit/claude-md"><img src="https://agentmods.dev/badge/instructions/burly-mingo/modernization-kit/claude-md.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 | $0.00789 | $0.00789 |
| Opus 5 | $0.00394 | $0.00394 |
| Sonnet 5 | $0.00158 | $0.00158 |
| Haiku 4.5 | $0.00079 | $0.00079 |
Grade A, and why
modernization-kit CLAUDE.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 4d 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Application Modernization — Claude Code Instructions
Part of the Legacy Application Modernization Kit by Burly Mingo LLC
You are assisting with a legacy application modernization project. This workspace contains a structured, multi-phase methodology that produces real engineering deliverables through iterative collaboration between you and a human domain expert.
How to Use This
This methodology has 6 phases (0-5), each with a dedicated slash command. Work through them in order:
- Run the command for the current phase (e.g.,
/phase-0-discovery) - Follow the instructions to produce the phase deliverable
- The human reviews and corrects your output
- Move to the next phase only after human approval
Available commands: /phase-0-discovery, /phase-1-codebase-analysis, /phase-2-pain-points, /phase-3-target-architecture, /phase-4-modernization-plan, /phase-5-supporting-docs
For the full methodology reference, see MODERNIZATION_METHODOLOGY.md.
Non-Negotiable Principles
- Modernize, don't translate. Changing the language without rethinking the architecture is not modernization. Every legacy system has workflows that exist because of technical limitations that no longer apply.
- Containers by default, not by dogma. Recommend containerized, cloud-agnostic deployment. But respect organizational preferences and document trade-offs.
- Buy vs. build at every decision point. Ask about open-source policy and procurement requirements early — it changes the calculus.
- AI-assisted, spec-driven development is the baseline. If traditional development is planned, multiply timelines by 2.5-4x.
- New languages are not the barrier they once were. AI IDEs lower adoption cost. But all else being equal, prefer the team's existing expertise.
- Comprehensive automated testing is a baseline. Unit, integration, API contract, and e2e tests are standard deliverables.
- Honest about unknowns. "Open Questions" section is mandatory in every deliverable.
- Security is Phase 0, not Phase Last.
- The human is always right about their domain.
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.
- 4d ago First seen · 58 lines · 789 tokens per session scan A b96cc7378c82
modernization-kit CLAUDE.md is an instructions file published in the GitHub repository Burly-Mingo/modernization-kit (11 stars, last pushed 6mo ago), licensed MIT. It adds 789 tokens to every session, about $0.0039 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
kiro-kit GEMINI.md
Gemini CLI instructions for ihatesea69/kiro-kit, covering mcp proxy for kiro, mandatory response format, response constraints, field definitions and examples.
nuxt-supabase-starter CLAUDE.md
Claude Code instructions for YuDefine/nuxt-supabase-starter, covering claude.md, language, project structure and meta vs template 邊界.
kirocc CLAUDE.md
Claude Code instructions for d-kuro/kirocc, covering agent guidelines, core principles, project overview, commands and code conventions.
outsystems-mcp CLAUDE.md
Claude Code instructions for OutSystems/outsystems-mcp, covering claude.md, supported harnesses, validate every change against every supported harness, skill docs must stay in lockstep across hosts and check before opening a pr.
kaiord AGENTS.md
Instructions for pablo-albaladejo/kaiord, covering kaiord, purpose, key files, subdirectories and for ai agents.
cli AGENTS.md
AGENTS.md instructions for vibgrate/cli, covering agents.md, build, test, and check, prefer vg over grepping, determinism rules (non-negotiable) and public-only rule.